Spaces:
Sleeping
Sleeping
Deploy native Gradio OCT inference app
Browse filesPublish the app source, configuration, and original trained checkpoint with explicit user approval. Configure Python 3.12 and CPU inference.
- README.md +32 -2
- SHA256SUMS +34 -0
- app.py +49 -0
- artifacts/checkpoint.pt +3 -0
- artifacts/config.json +495 -0
- deployment-manifest.json +173 -0
- requirements.txt +12 -0
- src/__init__.py +0 -0
- src/annotations.py +104 -0
- src/app.py +605 -0
- src/inference/__init__.py +0 -0
- src/inference/combination.py +129 -0
- src/inference/context.py +52 -0
- src/inference/decoding.py +63 -0
- src/inference/ensemble.py +172 -0
- src/inference/postprocess.py +88 -0
- src/inference/predict.py +182 -0
- src/inference/runtime.py +26 -0
- src/inference/stream.py +182 -0
- src/inference/writer.py +52 -0
- src/io.py +74 -0
- src/models/__init__.py +174 -0
- src/models/auxiliary.py +142 -0
- src/models/axial_prior.py +26 -0
- src/models/context.py +29 -0
- src/models/global_context.py +56 -0
- src/models/unet.py +112 -0
- src/models/wide.py +40 -0
- src/paths.py +5 -0
- src/protocol.py +208 -0
- src/training/__init__.py +0 -0
- src/training/guard.py +37 -0
- src/training/unet.py +790 -0
- src/viewer.js +50 -0
- src/viewer.py +637 -0
README.md
CHANGED
|
@@ -5,11 +5,41 @@ colorFrom: green
|
|
| 5 |
colorTo: purple
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 6.31.0
|
| 8 |
-
python_version:
|
| 9 |
app_file: app.py
|
| 10 |
pinned: false
|
| 11 |
license: apache-2.0
|
| 12 |
short_description: MYXOS OCT Segmentation AI-READI (agent1)
|
| 13 |
---
|
| 14 |
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
colorTo: purple
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 6.31.0
|
| 8 |
+
python_version: "3.12"
|
| 9 |
app_file: app.py
|
| 10 |
pinned: false
|
| 11 |
license: apache-2.0
|
| 12 |
short_description: MYXOS OCT Segmentation AI-READI (agent1)
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# MYXOS OCT Segmentation · Agent 1
|
| 16 |
+
|
| 17 |
+
Visualize retinal OCT boundaries using a model trained on AI-READI.
|
| 18 |
+
|
| 19 |
+
1. Upload one structural OCT DICOM volume, or its contiguous split parts.
|
| 20 |
+
2. Choose the scanner family and processor. Spectralis is selected initially;
|
| 21 |
+
**Detect from DICOM** is also available.
|
| 22 |
+
3. Run **Full volume** inference, or choose a fast **Selected B-scan preview**.
|
| 23 |
+
4. Browse the boundary-overlay and original-OCT tabs. Use the toolbar to zoom,
|
| 24 |
+
pan, fit, or view fullscreen; adjust visible boundaries and display settings.
|
| 25 |
+
5. Choose NPZ predictions or the current overlay PNG, then download the result.
|
| 26 |
+
|
| 27 |
+
Supported scanners: Heidelberg Spectralis, Topcon Maestro2, Topcon Triton, and
|
| 28 |
+
Zeiss Cirrus. This Space runs on CPU with batch size 1 initially; full-volume
|
| 29 |
+
inference can take longer than a slice preview. The model uses its saved FP32
|
| 30 |
+
inference configuration. Preview mode omits smoothing between B-scans.
|
| 31 |
+
|
| 32 |
+
NPZ files contain `positions[boundary, B-scan, A-scan]` in original zero-based
|
| 33 |
+
axial pixels and `boundary_keys`. Slice previews also include `frame_indices`.
|
| 34 |
+
|
| 35 |
+
Inference runs on this Space's server. Uploads and exports are temporary;
|
| 36 |
+
**Clear volume** removes the staged volume and its results. Idle viewer sessions
|
| 37 |
+
expire after two hours, and Gradio clears cached files on a two-hour schedule.
|
| 38 |
+
|
| 39 |
+
This model is specialized to AI-READI structural OCT exports. The boundaries
|
| 40 |
+
retain supplied vendor label distinctions and are research predictions.
|
| 41 |
+
|
| 42 |
+
The retained checkpoint achieved 1.427501 native axial pixels MAE (3.733009 µm)
|
| 43 |
+
on 2,392 frozen validation volumes. Those historical results measure agreement
|
| 44 |
+
with supplied automatic annotations; they do not establish clinical performance
|
| 45 |
+
or numerical equivalence on this hosting hardware.
|
SHA256SUMS
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
e3ebb3772d3e81ce38adfb24faa6c3bbb228428bbad1e26ba8d6914ff7868d88 README.md
|
| 2 |
+
174cc76b331c66ccd66212ba9affc9f1bdddc5d4cf0b29748d5cdc7ead406e71 app.py
|
| 3 |
+
3885e357513ee8bb5d016edfdf1a32aa2693a4b3957159edd0a258cff5af82f6 artifacts/checkpoint.pt
|
| 4 |
+
27ec4256c8e819455477c01ac58b55e56f0e431d3159e60dea71ed240179efe7 artifacts/config.json
|
| 5 |
+
488d9c3cb32685b93d71f65392ca721b8880dfaf9b47e62916fdf8c075562554 deployment-manifest.json
|
| 6 |
+
4462d9add0ce6b4da2719a8ddb766c741adc4629189dc9a2121f5c1751bc27d2 requirements.txt
|
| 7 |
+
e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 src/__init__.py
|
| 8 |
+
e173e85d01aec05b90439ad0ad8901e71168114046568fba3a93629b73b053cb src/annotations.py
|
| 9 |
+
16d2a26af365572a05d3bdd489c49bb3e5f2b20e3cde91b35e799d578fe38373 src/app.py
|
| 10 |
+
e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 src/inference/__init__.py
|
| 11 |
+
5db770acac3968725ddc792d2ed7dfea0696cc2afaf0755a7d7020b6236d81f0 src/inference/combination.py
|
| 12 |
+
bcc926d0bf9815ea7c4240d7d81ccd80d6f147d4da9d09df5474bf23bbf89afd src/inference/context.py
|
| 13 |
+
bb61a0844faaf35b907921e2d2ff0654dfd5973a740d8ae4d55d98e3f85ec260 src/inference/decoding.py
|
| 14 |
+
8fb30517646603138f3ae59853865725fcf3b9f33e852e69f17e8fc63c0867ea src/inference/ensemble.py
|
| 15 |
+
bec5f06c903b609cb5a81407c5ff330ee92303e6d0097fd5afce6b6f47c2963b src/inference/postprocess.py
|
| 16 |
+
77a4df00a035877c81fe50666eab85fe39e184a32b53998f25cf47ce58a66e10 src/inference/predict.py
|
| 17 |
+
be8083fef3073fec66d7597bb2b6162a71374250280be03a1a9def1423ddb011 src/inference/runtime.py
|
| 18 |
+
532e5fc012975b26a2c878afdabc6f9a3460d15400f971994b98798de823b853 src/inference/stream.py
|
| 19 |
+
dc20c2fc824c4e139be7325f31e5c478f6fa0b1649f4be7f4854c95285ab0980 src/inference/writer.py
|
| 20 |
+
f98a90699cd60d434bce6ec4a972f7e6cc61443c4c793478d73ddf5c4710ff6e src/io.py
|
| 21 |
+
9492b95e91a4f5763bd2051b9cb701aa446f8bddee0c44ab4464090a526e4820 src/models/__init__.py
|
| 22 |
+
c27c7cec00f7ec8793a4a60099ea6b5d58fd50a550ef17a3318f60349852d232 src/models/auxiliary.py
|
| 23 |
+
5a4f94f4367a1d64068bc7d9e659bc9c73f88dd710f813b95e09aa371c87e29d src/models/axial_prior.py
|
| 24 |
+
a8c3545793eb5f9641347b37926992ae9cee87f27e5d75631a45d56f2dbc570c src/models/context.py
|
| 25 |
+
04e9d96e400e8e3a810bd1715eaf108556efd2f353a8e9387debeef136561c62 src/models/global_context.py
|
| 26 |
+
b32fe6dfdaa14315168cfcdbb089caea2b657bd750d00ee6934cd17a999413cc src/models/unet.py
|
| 27 |
+
ed6afbab0b1b5be688e9ee8d215a0d6d7d21bf5c4b5dd8b475aab6025710210a src/models/wide.py
|
| 28 |
+
ae1086d80632488af53810ffd3174a4310ed7ff08629403fead0eaecf0d153a6 src/paths.py
|
| 29 |
+
7daf3444431e52d28547ca11d213cd0670dbe4283f4e46eec6fcd668ab1fba0b src/protocol.py
|
| 30 |
+
e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 src/training/__init__.py
|
| 31 |
+
494a07c49ae2a3d50ac42d62aa7a8d980814d014544d663c32248819094290ae src/training/guard.py
|
| 32 |
+
d8a1be7675de472522fb23b355c8106c5b4392bcee3b27ce3b44c24b7fd77117 src/training/unet.py
|
| 33 |
+
a10d79e8681dbe05a9c36896850587a6e8984ff500b0c1475edf41a830b61580 src/viewer.js
|
| 34 |
+
1b3bebd10774adfb115d884dbb8eb549a08b0a39f569117946e8acf161c8f32f src/viewer.py
|
app.py
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Launch OCT boundary inference locally or on Hugging Face Spaces."""
|
| 2 |
+
|
| 3 |
+
import argparse
|
| 4 |
+
import os
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
def parse_args(argv=None):
|
| 8 |
+
parser = argparse.ArgumentParser(description=__doc__)
|
| 9 |
+
parser.add_argument(
|
| 10 |
+
"--port", type=int, default=os.environ.get("GRADIO_SERVER_PORT", "7860")
|
| 11 |
+
)
|
| 12 |
+
parser.add_argument(
|
| 13 |
+
"--host",
|
| 14 |
+
default=os.environ.get(
|
| 15 |
+
"GRADIO_SERVER_NAME",
|
| 16 |
+
"0.0.0.0" if os.environ.get("SPACE_ID") else "127.0.0.1",
|
| 17 |
+
),
|
| 18 |
+
)
|
| 19 |
+
parser.add_argument(
|
| 20 |
+
"--open", action="store_true", help="Open the viewer in your browser"
|
| 21 |
+
)
|
| 22 |
+
args = parser.parse_args(argv)
|
| 23 |
+
if not 1 <= args.port <= 65535:
|
| 24 |
+
parser.error("Port must be between 1 and 65535")
|
| 25 |
+
return args
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
def main():
|
| 29 |
+
args = parse_args()
|
| 30 |
+
os.environ.setdefault("GRADIO_ANALYTICS_ENABLED", "False")
|
| 31 |
+
|
| 32 |
+
from src.app import build_app
|
| 33 |
+
from src.viewer import CHECKPOINT
|
| 34 |
+
|
| 35 |
+
if not CHECKPOINT.is_file():
|
| 36 |
+
raise SystemExit(f"Checkpoint does not exist: {CHECKPOINT}")
|
| 37 |
+
demo = build_app()
|
| 38 |
+
demo.queue(default_concurrency_limit=1, max_size=12).launch(
|
| 39 |
+
server_name=args.host,
|
| 40 |
+
server_port=args.port,
|
| 41 |
+
inbrowser=args.open and not bool(os.environ.get("SPACE_ID")),
|
| 42 |
+
share=False,
|
| 43 |
+
show_error=False,
|
| 44 |
+
blocked_paths=[str(CHECKPOINT)],
|
| 45 |
+
)
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
if __name__ == "__main__":
|
| 49 |
+
main()
|
artifacts/checkpoint.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3885e357513ee8bb5d016edfdf1a32aa2693a4b3957159edd0a258cff5af82f6
|
| 3 |
+
size 44047582
|
artifacts/config.json
ADDED
|
@@ -0,0 +1,495 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architecture": "BoundaryEnsemble",
|
| 3 |
+
"boundary_keys": [
|
| 4 |
+
"DCM_128289",
|
| 5 |
+
"DCM_128290",
|
| 6 |
+
"DCM_128291",
|
| 7 |
+
"DCM_128292",
|
| 8 |
+
"DCM_128293",
|
| 9 |
+
"DCM_128297",
|
| 10 |
+
"DCM_128298",
|
| 11 |
+
"DCM_128299",
|
| 12 |
+
"DCM_128300",
|
| 13 |
+
"DCM_128301",
|
| 14 |
+
"DCM_128320",
|
| 15 |
+
"DCM_128321",
|
| 16 |
+
"DCM_128323",
|
| 17 |
+
"SCT_280677004",
|
| 18 |
+
"SCT_76710003"
|
| 19 |
+
],
|
| 20 |
+
"device_keys": {
|
| 21 |
+
"zeiss_cirrus": [
|
| 22 |
+
"SCT_280677004",
|
| 23 |
+
"DCM_128298"
|
| 24 |
+
],
|
| 25 |
+
"heidelberg_spectralis": [
|
| 26 |
+
"SCT_280677004",
|
| 27 |
+
"DCM_128300",
|
| 28 |
+
"DCM_128289",
|
| 29 |
+
"DCM_128290",
|
| 30 |
+
"DCM_128291",
|
| 31 |
+
"DCM_128292",
|
| 32 |
+
"DCM_128293",
|
| 33 |
+
"SCT_76710003",
|
| 34 |
+
"DCM_128321",
|
| 35 |
+
"DCM_128323",
|
| 36 |
+
"DCM_128297"
|
| 37 |
+
],
|
| 38 |
+
"topcon_triton": [
|
| 39 |
+
"SCT_280677004",
|
| 40 |
+
"DCM_128289",
|
| 41 |
+
"DCM_128290",
|
| 42 |
+
"DCM_128291",
|
| 43 |
+
"DCM_128320",
|
| 44 |
+
"DCM_128297",
|
| 45 |
+
"DCM_128299",
|
| 46 |
+
"DCM_128293",
|
| 47 |
+
"SCT_76710003",
|
| 48 |
+
"DCM_128301"
|
| 49 |
+
],
|
| 50 |
+
"topcon_maestro2": [
|
| 51 |
+
"SCT_280677004",
|
| 52 |
+
"DCM_128289",
|
| 53 |
+
"DCM_128290",
|
| 54 |
+
"DCM_128291",
|
| 55 |
+
"DCM_128320",
|
| 56 |
+
"DCM_128297",
|
| 57 |
+
"DCM_128299",
|
| 58 |
+
"DCM_128293",
|
| 59 |
+
"SCT_76710003"
|
| 60 |
+
]
|
| 61 |
+
},
|
| 62 |
+
"combination": {
|
| 63 |
+
"method": "weighted_heads",
|
| 64 |
+
"head_weights_by_device": {
|
| 65 |
+
"zeiss_cirrus": {
|
| 66 |
+
"SCT_280677004": {
|
| 67 |
+
"global_l1_10000": 1.0
|
| 68 |
+
},
|
| 69 |
+
"DCM_128298": {
|
| 70 |
+
"global_l1_10000": 1.0
|
| 71 |
+
}
|
| 72 |
+
},
|
| 73 |
+
"heidelberg_spectralis": {
|
| 74 |
+
"SCT_280677004": {
|
| 75 |
+
"highres_context150": 0.75,
|
| 76 |
+
"global_l1_10000": 0.25
|
| 77 |
+
},
|
| 78 |
+
"DCM_128300": {
|
| 79 |
+
"highres_context150": 0.75,
|
| 80 |
+
"global_l1_10000": 0.25
|
| 81 |
+
},
|
| 82 |
+
"DCM_128289": {
|
| 83 |
+
"highres_context150": 0.5,
|
| 84 |
+
"global_l1_10000": 0.5
|
| 85 |
+
},
|
| 86 |
+
"DCM_128290": {
|
| 87 |
+
"highres_context150": 0.5,
|
| 88 |
+
"global_l1_10000": 0.5
|
| 89 |
+
},
|
| 90 |
+
"DCM_128291": {
|
| 91 |
+
"highres_context150": 0.5,
|
| 92 |
+
"global150": 0.5
|
| 93 |
+
},
|
| 94 |
+
"DCM_128292": {
|
| 95 |
+
"highres_context150": 0.5,
|
| 96 |
+
"global150": 0.5
|
| 97 |
+
},
|
| 98 |
+
"DCM_128293": {
|
| 99 |
+
"highres_context150": 0.75,
|
| 100 |
+
"global150": 0.25
|
| 101 |
+
},
|
| 102 |
+
"SCT_76710003": {
|
| 103 |
+
"highres_context150": 0.75,
|
| 104 |
+
"global150": 0.25
|
| 105 |
+
},
|
| 106 |
+
"DCM_128321": {
|
| 107 |
+
"highres_context150": 0.75,
|
| 108 |
+
"global150": 0.25
|
| 109 |
+
},
|
| 110 |
+
"DCM_128323": {
|
| 111 |
+
"highres_context150": 0.75,
|
| 112 |
+
"global150": 0.25
|
| 113 |
+
},
|
| 114 |
+
"DCM_128297": {
|
| 115 |
+
"highres_context150": 0.75,
|
| 116 |
+
"global150": 0.25
|
| 117 |
+
}
|
| 118 |
+
},
|
| 119 |
+
"topcon_triton": {
|
| 120 |
+
"SCT_280677004": {
|
| 121 |
+
"global_l1_10000": 1.0
|
| 122 |
+
},
|
| 123 |
+
"DCM_128289": {
|
| 124 |
+
"highres_context150": 0.5,
|
| 125 |
+
"global_l1_10000": 0.5
|
| 126 |
+
},
|
| 127 |
+
"DCM_128290": {
|
| 128 |
+
"highres_context150": 0.5,
|
| 129 |
+
"global_l1_10000": 0.5
|
| 130 |
+
},
|
| 131 |
+
"DCM_128291": {
|
| 132 |
+
"highres_context150": 0.5,
|
| 133 |
+
"global_l1_10000": 0.5
|
| 134 |
+
},
|
| 135 |
+
"DCM_128320": {
|
| 136 |
+
"highres_context150": 0.5,
|
| 137 |
+
"global_l1_10000": 0.5
|
| 138 |
+
},
|
| 139 |
+
"DCM_128297": {
|
| 140 |
+
"highres_context150": 0.5,
|
| 141 |
+
"global_l1_10000": 0.5
|
| 142 |
+
},
|
| 143 |
+
"DCM_128299": {
|
| 144 |
+
"highres_context150": 0.75,
|
| 145 |
+
"global_l1_10000": 0.25
|
| 146 |
+
},
|
| 147 |
+
"DCM_128293": {
|
| 148 |
+
"highres_context150": 0.5,
|
| 149 |
+
"global_l1_10000": 0.5
|
| 150 |
+
},
|
| 151 |
+
"SCT_76710003": {
|
| 152 |
+
"highres_context150": 0.75,
|
| 153 |
+
"global_l1_10000": 0.25
|
| 154 |
+
},
|
| 155 |
+
"DCM_128301": {
|
| 156 |
+
"highres_context150": 0.75,
|
| 157 |
+
"global_l1_10000": 0.25
|
| 158 |
+
}
|
| 159 |
+
},
|
| 160 |
+
"topcon_maestro2": {
|
| 161 |
+
"SCT_280677004": {
|
| 162 |
+
"highres_context150": 0.5,
|
| 163 |
+
"global_l1_10000": 0.5
|
| 164 |
+
},
|
| 165 |
+
"DCM_128289": {
|
| 166 |
+
"highres_context150": 0.25,
|
| 167 |
+
"global_l1_10000": 0.75
|
| 168 |
+
},
|
| 169 |
+
"DCM_128290": {
|
| 170 |
+
"global_l1_10000": 1.0
|
| 171 |
+
},
|
| 172 |
+
"DCM_128291": {
|
| 173 |
+
"global_l1_10000": 1.0
|
| 174 |
+
},
|
| 175 |
+
"DCM_128320": {
|
| 176 |
+
"global_l1_10000": 1.0
|
| 177 |
+
},
|
| 178 |
+
"DCM_128297": {
|
| 179 |
+
"global_l1_10000": 1.0
|
| 180 |
+
},
|
| 181 |
+
"DCM_128299": {
|
| 182 |
+
"global_l1_10000": 1.0
|
| 183 |
+
},
|
| 184 |
+
"DCM_128293": {
|
| 185 |
+
"global_l1_10000": 1.0
|
| 186 |
+
},
|
| 187 |
+
"SCT_76710003": {
|
| 188 |
+
"global_l1_10000": 1.0
|
| 189 |
+
}
|
| 190 |
+
}
|
| 191 |
+
}
|
| 192 |
+
},
|
| 193 |
+
"inference": {
|
| 194 |
+
"precision": "fp32",
|
| 195 |
+
"batch_size": 32,
|
| 196 |
+
"workers": 4,
|
| 197 |
+
"postprocess": {
|
| 198 |
+
"by_device": {
|
| 199 |
+
"zeiss_cirrus": {
|
| 200 |
+
"boundary_filters": [
|
| 201 |
+
{
|
| 202 |
+
"filter": "gaussian",
|
| 203 |
+
"round_devices": [
|
| 204 |
+
"topcon_maestro2",
|
| 205 |
+
"topcon_triton",
|
| 206 |
+
"zeiss_cirrus"
|
| 207 |
+
],
|
| 208 |
+
"sigma_b": 0.75
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"filter": "gaussian",
|
| 212 |
+
"round_devices": [
|
| 213 |
+
"topcon_maestro2",
|
| 214 |
+
"topcon_triton",
|
| 215 |
+
"zeiss_cirrus"
|
| 216 |
+
],
|
| 217 |
+
"sigma_b": 0.75
|
| 218 |
+
}
|
| 219 |
+
]
|
| 220 |
+
},
|
| 221 |
+
"heidelberg_spectralis": {
|
| 222 |
+
"boundary_filters": [
|
| 223 |
+
{
|
| 224 |
+
"filter": "gaussian",
|
| 225 |
+
"round_devices": [
|
| 226 |
+
"topcon_maestro2",
|
| 227 |
+
"topcon_triton",
|
| 228 |
+
"zeiss_cirrus"
|
| 229 |
+
],
|
| 230 |
+
"sigma_b": 6.0
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"filter": "gaussian",
|
| 234 |
+
"round_devices": [
|
| 235 |
+
"topcon_maestro2",
|
| 236 |
+
"topcon_triton",
|
| 237 |
+
"zeiss_cirrus"
|
| 238 |
+
],
|
| 239 |
+
"sigma_b": 9.0
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"filter": "gaussian",
|
| 243 |
+
"round_devices": [
|
| 244 |
+
"topcon_maestro2",
|
| 245 |
+
"topcon_triton",
|
| 246 |
+
"zeiss_cirrus"
|
| 247 |
+
],
|
| 248 |
+
"sigma_b": 6.0
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"filter": "gaussian",
|
| 252 |
+
"round_devices": [
|
| 253 |
+
"topcon_maestro2",
|
| 254 |
+
"topcon_triton",
|
| 255 |
+
"zeiss_cirrus"
|
| 256 |
+
],
|
| 257 |
+
"sigma_b": 6.0
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"filter": "gaussian",
|
| 261 |
+
"round_devices": [
|
| 262 |
+
"topcon_maestro2",
|
| 263 |
+
"topcon_triton",
|
| 264 |
+
"zeiss_cirrus"
|
| 265 |
+
],
|
| 266 |
+
"sigma_b": 6.0
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"filter": "gaussian",
|
| 270 |
+
"round_devices": [
|
| 271 |
+
"topcon_maestro2",
|
| 272 |
+
"topcon_triton",
|
| 273 |
+
"zeiss_cirrus"
|
| 274 |
+
],
|
| 275 |
+
"sigma_b": 6.0
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"filter": "gaussian",
|
| 279 |
+
"round_devices": [
|
| 280 |
+
"topcon_maestro2",
|
| 281 |
+
"topcon_triton",
|
| 282 |
+
"zeiss_cirrus"
|
| 283 |
+
],
|
| 284 |
+
"sigma_b": 6.0
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"filter": "gaussian",
|
| 288 |
+
"round_devices": [
|
| 289 |
+
"topcon_maestro2",
|
| 290 |
+
"topcon_triton",
|
| 291 |
+
"zeiss_cirrus"
|
| 292 |
+
],
|
| 293 |
+
"sigma_b": 9.0
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"filter": "gaussian",
|
| 297 |
+
"round_devices": [
|
| 298 |
+
"topcon_maestro2",
|
| 299 |
+
"topcon_triton",
|
| 300 |
+
"zeiss_cirrus"
|
| 301 |
+
],
|
| 302 |
+
"sigma_b": 9.0
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"filter": "gaussian",
|
| 306 |
+
"round_devices": [
|
| 307 |
+
"topcon_maestro2",
|
| 308 |
+
"topcon_triton",
|
| 309 |
+
"zeiss_cirrus"
|
| 310 |
+
],
|
| 311 |
+
"sigma_b": 6.0
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"filter": "gaussian",
|
| 315 |
+
"round_devices": [
|
| 316 |
+
"topcon_maestro2",
|
| 317 |
+
"topcon_triton",
|
| 318 |
+
"zeiss_cirrus"
|
| 319 |
+
],
|
| 320 |
+
"sigma_b": 6.0
|
| 321 |
+
}
|
| 322 |
+
]
|
| 323 |
+
},
|
| 324 |
+
"topcon_triton": {
|
| 325 |
+
"boundary_filters": [
|
| 326 |
+
{
|
| 327 |
+
"round_devices": [
|
| 328 |
+
"topcon_maestro2",
|
| 329 |
+
"topcon_triton",
|
| 330 |
+
"zeiss_cirrus"
|
| 331 |
+
]
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"filter": "gaussian",
|
| 335 |
+
"round_devices": [
|
| 336 |
+
"topcon_maestro2",
|
| 337 |
+
"topcon_triton",
|
| 338 |
+
"zeiss_cirrus"
|
| 339 |
+
],
|
| 340 |
+
"sigma_b": 0.375
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"filter": "gaussian",
|
| 344 |
+
"round_devices": [
|
| 345 |
+
"topcon_maestro2",
|
| 346 |
+
"topcon_triton",
|
| 347 |
+
"zeiss_cirrus"
|
| 348 |
+
],
|
| 349 |
+
"sigma_b": 0.375
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"filter": "gaussian",
|
| 353 |
+
"round_devices": [
|
| 354 |
+
"topcon_maestro2",
|
| 355 |
+
"topcon_triton",
|
| 356 |
+
"zeiss_cirrus"
|
| 357 |
+
],
|
| 358 |
+
"sigma_b": 0.375
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"filter": "gaussian",
|
| 362 |
+
"round_devices": [
|
| 363 |
+
"topcon_maestro2",
|
| 364 |
+
"topcon_triton",
|
| 365 |
+
"zeiss_cirrus"
|
| 366 |
+
],
|
| 367 |
+
"sigma_b": 0.25
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"filter": "gaussian",
|
| 371 |
+
"round_devices": [
|
| 372 |
+
"topcon_maestro2",
|
| 373 |
+
"topcon_triton",
|
| 374 |
+
"zeiss_cirrus"
|
| 375 |
+
],
|
| 376 |
+
"sigma_b": 0.25
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"filter": "gaussian",
|
| 380 |
+
"round_devices": [
|
| 381 |
+
"topcon_maestro2",
|
| 382 |
+
"topcon_triton",
|
| 383 |
+
"zeiss_cirrus"
|
| 384 |
+
],
|
| 385 |
+
"sigma_b": 0.25
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"filter": "gaussian",
|
| 389 |
+
"round_devices": [
|
| 390 |
+
"topcon_maestro2",
|
| 391 |
+
"topcon_triton",
|
| 392 |
+
"zeiss_cirrus"
|
| 393 |
+
],
|
| 394 |
+
"sigma_b": 0.375
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"filter": "gaussian",
|
| 398 |
+
"round_devices": [
|
| 399 |
+
"topcon_maestro2",
|
| 400 |
+
"topcon_triton",
|
| 401 |
+
"zeiss_cirrus"
|
| 402 |
+
],
|
| 403 |
+
"sigma_b": 0.375
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"filter": "gaussian",
|
| 407 |
+
"round_devices": [
|
| 408 |
+
"topcon_maestro2",
|
| 409 |
+
"topcon_triton",
|
| 410 |
+
"zeiss_cirrus"
|
| 411 |
+
],
|
| 412 |
+
"sigma_b": 0.375
|
| 413 |
+
}
|
| 414 |
+
]
|
| 415 |
+
},
|
| 416 |
+
"topcon_maestro2": {
|
| 417 |
+
"boundary_filters": [
|
| 418 |
+
{
|
| 419 |
+
"filter": "gaussian",
|
| 420 |
+
"round_devices": [
|
| 421 |
+
"topcon_maestro2",
|
| 422 |
+
"topcon_triton",
|
| 423 |
+
"zeiss_cirrus"
|
| 424 |
+
],
|
| 425 |
+
"sigma_b": 0.25
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"filter": "gaussian",
|
| 429 |
+
"round_devices": [
|
| 430 |
+
"topcon_maestro2",
|
| 431 |
+
"topcon_triton",
|
| 432 |
+
"zeiss_cirrus"
|
| 433 |
+
],
|
| 434 |
+
"sigma_b": 0.375
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"filter": "gaussian",
|
| 438 |
+
"round_devices": [
|
| 439 |
+
"topcon_maestro2",
|
| 440 |
+
"topcon_triton",
|
| 441 |
+
"zeiss_cirrus"
|
| 442 |
+
],
|
| 443 |
+
"sigma_b": 0.375
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"round_devices": [
|
| 447 |
+
"topcon_maestro2",
|
| 448 |
+
"topcon_triton",
|
| 449 |
+
"zeiss_cirrus"
|
| 450 |
+
]
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"round_devices": [
|
| 454 |
+
"topcon_maestro2",
|
| 455 |
+
"topcon_triton",
|
| 456 |
+
"zeiss_cirrus"
|
| 457 |
+
]
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"round_devices": [
|
| 461 |
+
"topcon_maestro2",
|
| 462 |
+
"topcon_triton",
|
| 463 |
+
"zeiss_cirrus"
|
| 464 |
+
]
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"round_devices": [
|
| 468 |
+
"topcon_maestro2",
|
| 469 |
+
"topcon_triton",
|
| 470 |
+
"zeiss_cirrus"
|
| 471 |
+
]
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"round_devices": [
|
| 475 |
+
"topcon_maestro2",
|
| 476 |
+
"topcon_triton",
|
| 477 |
+
"zeiss_cirrus"
|
| 478 |
+
]
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"round_devices": [
|
| 482 |
+
"topcon_maestro2",
|
| 483 |
+
"topcon_triton",
|
| 484 |
+
"zeiss_cirrus"
|
| 485 |
+
]
|
| 486 |
+
}
|
| 487 |
+
]
|
| 488 |
+
}
|
| 489 |
+
}
|
| 490 |
+
}
|
| 491 |
+
},
|
| 492 |
+
"initialization": "own random-root supervised CNNs with fixed validation-selected anatomical mixtures",
|
| 493 |
+
"validation_manifest_sha256": "d7e10d32e377b098245f9f675849903998a1c60df7834b6f2bc09436494b7cfb",
|
| 494 |
+
"test_payloads_used": false
|
| 495 |
+
}
|
deployment-manifest.json
ADDED
|
@@ -0,0 +1,173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"space": "farrell236/OCT_Segmentation_a1",
|
| 3 |
+
"python_version": "3.12",
|
| 4 |
+
"gradio_version": "6.31.0",
|
| 5 |
+
"hardware": "cpu-basic",
|
| 6 |
+
"files": {
|
| 7 |
+
"README.md": {
|
| 8 |
+
"source": "deploy/huggingface/README.md",
|
| 9 |
+
"sha256": "e3ebb3772d3e81ce38adfb24faa6c3bbb228428bbad1e26ba8d6914ff7868d88",
|
| 10 |
+
"bytes": 2012
|
| 11 |
+
},
|
| 12 |
+
"app.py": {
|
| 13 |
+
"source": "app.py",
|
| 14 |
+
"sha256": "174cc76b331c66ccd66212ba9affc9f1bdddc5d4cf0b29748d5cdc7ead406e71",
|
| 15 |
+
"bytes": 1377
|
| 16 |
+
},
|
| 17 |
+
"artifacts/checkpoint.pt": {
|
| 18 |
+
"source": "artifacts/checkpoint.pt",
|
| 19 |
+
"sha256": "3885e357513ee8bb5d016edfdf1a32aa2693a4b3957159edd0a258cff5af82f6",
|
| 20 |
+
"bytes": 44047582
|
| 21 |
+
},
|
| 22 |
+
"artifacts/config.json": {
|
| 23 |
+
"source": "artifacts/config.json",
|
| 24 |
+
"sha256": "27ec4256c8e819455477c01ac58b55e56f0e431d3159e60dea71ed240179efe7",
|
| 25 |
+
"bytes": 12416
|
| 26 |
+
},
|
| 27 |
+
"requirements.txt": {
|
| 28 |
+
"source": "deploy/huggingface/requirements.txt",
|
| 29 |
+
"sha256": "4462d9add0ce6b4da2719a8ddb766c741adc4629189dc9a2121f5c1751bc27d2",
|
| 30 |
+
"bytes": 320
|
| 31 |
+
},
|
| 32 |
+
"src/__init__.py": {
|
| 33 |
+
"source": "src/__init__.py",
|
| 34 |
+
"sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
| 35 |
+
"bytes": 0
|
| 36 |
+
},
|
| 37 |
+
"src/annotations.py": {
|
| 38 |
+
"source": "src/annotations.py",
|
| 39 |
+
"sha256": "e173e85d01aec05b90439ad0ad8901e71168114046568fba3a93629b73b053cb",
|
| 40 |
+
"bytes": 5865
|
| 41 |
+
},
|
| 42 |
+
"src/app.py": {
|
| 43 |
+
"source": "src/app.py",
|
| 44 |
+
"sha256": "16d2a26af365572a05d3bdd489c49bb3e5f2b20e3cde91b35e799d578fe38373",
|
| 45 |
+
"bytes": 19812
|
| 46 |
+
},
|
| 47 |
+
"src/inference/__init__.py": {
|
| 48 |
+
"source": "src/inference/__init__.py",
|
| 49 |
+
"sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
| 50 |
+
"bytes": 0
|
| 51 |
+
},
|
| 52 |
+
"src/inference/combination.py": {
|
| 53 |
+
"source": "src/inference/combination.py",
|
| 54 |
+
"sha256": "5db770acac3968725ddc792d2ed7dfea0696cc2afaf0755a7d7020b6236d81f0",
|
| 55 |
+
"bytes": 5484
|
| 56 |
+
},
|
| 57 |
+
"src/inference/context.py": {
|
| 58 |
+
"source": "src/inference/context.py",
|
| 59 |
+
"sha256": "bcc926d0bf9815ea7c4240d7d81ccd80d6f147d4da9d09df5474bf23bbf89afd",
|
| 60 |
+
"bytes": 2152
|
| 61 |
+
},
|
| 62 |
+
"src/inference/decoding.py": {
|
| 63 |
+
"source": "src/inference/decoding.py",
|
| 64 |
+
"sha256": "bb61a0844faaf35b907921e2d2ff0654dfd5973a740d8ae4d55d98e3f85ec260",
|
| 65 |
+
"bytes": 2729
|
| 66 |
+
},
|
| 67 |
+
"src/inference/ensemble.py": {
|
| 68 |
+
"source": "src/inference/ensemble.py",
|
| 69 |
+
"sha256": "8fb30517646603138f3ae59853865725fcf3b9f33e852e69f17e8fc63c0867ea",
|
| 70 |
+
"bytes": 7113
|
| 71 |
+
},
|
| 72 |
+
"src/inference/postprocess.py": {
|
| 73 |
+
"source": "src/inference/postprocess.py",
|
| 74 |
+
"sha256": "bec5f06c903b609cb5a81407c5ff330ee92303e6d0097fd5afce6b6f47c2963b",
|
| 75 |
+
"bytes": 2862
|
| 76 |
+
},
|
| 77 |
+
"src/inference/predict.py": {
|
| 78 |
+
"source": "src/inference/predict.py",
|
| 79 |
+
"sha256": "77a4df00a035877c81fe50666eab85fe39e184a32b53998f25cf47ce58a66e10",
|
| 80 |
+
"bytes": 6472
|
| 81 |
+
},
|
| 82 |
+
"src/inference/runtime.py": {
|
| 83 |
+
"source": "src/inference/runtime.py",
|
| 84 |
+
"sha256": "be8083fef3073fec66d7597bb2b6162a71374250280be03a1a9def1423ddb011",
|
| 85 |
+
"bytes": 947
|
| 86 |
+
},
|
| 87 |
+
"src/inference/stream.py": {
|
| 88 |
+
"source": "src/inference/stream.py",
|
| 89 |
+
"sha256": "532e5fc012975b26a2c878afdabc6f9a3460d15400f971994b98798de823b853",
|
| 90 |
+
"bytes": 7186
|
| 91 |
+
},
|
| 92 |
+
"src/inference/writer.py": {
|
| 93 |
+
"source": "src/inference/writer.py",
|
| 94 |
+
"sha256": "dc20c2fc824c4e139be7325f31e5c478f6fa0b1649f4be7f4854c95285ab0980",
|
| 95 |
+
"bytes": 1773
|
| 96 |
+
},
|
| 97 |
+
"src/io.py": {
|
| 98 |
+
"source": "src/io.py",
|
| 99 |
+
"sha256": "f98a90699cd60d434bce6ec4a972f7e6cc61443c4c793478d73ddf5c4710ff6e",
|
| 100 |
+
"bytes": 3591
|
| 101 |
+
},
|
| 102 |
+
"src/models/__init__.py": {
|
| 103 |
+
"source": "src/models/__init__.py",
|
| 104 |
+
"sha256": "9492b95e91a4f5763bd2051b9cb701aa446f8bddee0c44ab4464090a526e4820",
|
| 105 |
+
"bytes": 7318
|
| 106 |
+
},
|
| 107 |
+
"src/models/auxiliary.py": {
|
| 108 |
+
"source": "src/models/auxiliary.py",
|
| 109 |
+
"sha256": "c27c7cec00f7ec8793a4a60099ea6b5d58fd50a550ef17a3318f60349852d232",
|
| 110 |
+
"bytes": 5010
|
| 111 |
+
},
|
| 112 |
+
"src/models/axial_prior.py": {
|
| 113 |
+
"source": "src/models/axial_prior.py",
|
| 114 |
+
"sha256": "5a4f94f4367a1d64068bc7d9e659bc9c73f88dd710f813b95e09aa371c87e29d",
|
| 115 |
+
"bytes": 969
|
| 116 |
+
},
|
| 117 |
+
"src/models/context.py": {
|
| 118 |
+
"source": "src/models/context.py",
|
| 119 |
+
"sha256": "a8c3545793eb5f9641347b37926992ae9cee87f27e5d75631a45d56f2dbc570c",
|
| 120 |
+
"bytes": 992
|
| 121 |
+
},
|
| 122 |
+
"src/models/global_context.py": {
|
| 123 |
+
"source": "src/models/global_context.py",
|
| 124 |
+
"sha256": "04e9d96e400e8e3a810bd1715eaf108556efd2f353a8e9387debeef136561c62",
|
| 125 |
+
"bytes": 2168
|
| 126 |
+
},
|
| 127 |
+
"src/models/unet.py": {
|
| 128 |
+
"source": "src/models/unet.py",
|
| 129 |
+
"sha256": "b32fe6dfdaa14315168cfcdbb089caea2b657bd750d00ee6934cd17a999413cc",
|
| 130 |
+
"bytes": 3796
|
| 131 |
+
},
|
| 132 |
+
"src/models/wide.py": {
|
| 133 |
+
"source": "src/models/wide.py",
|
| 134 |
+
"sha256": "ed6afbab0b1b5be688e9ee8d215a0d6d7d21bf5c4b5dd8b475aab6025710210a",
|
| 135 |
+
"bytes": 1525
|
| 136 |
+
},
|
| 137 |
+
"src/paths.py": {
|
| 138 |
+
"source": "src/paths.py",
|
| 139 |
+
"sha256": "ae1086d80632488af53810ffd3174a4310ed7ff08629403fead0eaecf0d153a6",
|
| 140 |
+
"bytes": 139
|
| 141 |
+
},
|
| 142 |
+
"src/protocol.py": {
|
| 143 |
+
"source": "src/protocol.py",
|
| 144 |
+
"sha256": "7daf3444431e52d28547ca11d213cd0670dbe4283f4e46eec6fcd668ab1fba0b",
|
| 145 |
+
"bytes": 11426
|
| 146 |
+
},
|
| 147 |
+
"src/training/__init__.py": {
|
| 148 |
+
"source": "src/training/__init__.py",
|
| 149 |
+
"sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
| 150 |
+
"bytes": 0
|
| 151 |
+
},
|
| 152 |
+
"src/training/guard.py": {
|
| 153 |
+
"source": "src/training/guard.py",
|
| 154 |
+
"sha256": "494a07c49ae2a3d50ac42d62aa7a8d980814d014544d663c32248819094290ae",
|
| 155 |
+
"bytes": 1485
|
| 156 |
+
},
|
| 157 |
+
"src/training/unet.py": {
|
| 158 |
+
"source": "src/training/unet.py",
|
| 159 |
+
"sha256": "d8a1be7675de472522fb23b355c8106c5b4392bcee3b27ce3b44c24b7fd77117",
|
| 160 |
+
"bytes": 33225
|
| 161 |
+
},
|
| 162 |
+
"src/viewer.js": {
|
| 163 |
+
"source": "src/viewer.js",
|
| 164 |
+
"sha256": "a10d79e8681dbe05a9c36896850587a6e8984ff500b0c1475edf41a830b61580",
|
| 165 |
+
"bytes": 2320
|
| 166 |
+
},
|
| 167 |
+
"src/viewer.py": {
|
| 168 |
+
"source": "src/viewer.py",
|
| 169 |
+
"sha256": "1b3bebd10774adfb115d884dbb8eb549a08b0a39f569117946e8acf161c8f32f",
|
| 170 |
+
"bytes": 22993
|
| 171 |
+
}
|
| 172 |
+
}
|
| 173 |
+
}
|
requirements.txt
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# CPU build for the existing cpu-basic Space; the model's numerical code is unchanged.
|
| 2 |
+
--extra-index-url https://download.pytorch.org/whl/cpu
|
| 3 |
+
torch==2.9.1+cpu
|
| 4 |
+
gradio==6.31.0
|
| 5 |
+
numpy==2.5.4
|
| 6 |
+
pydicom==3.0.2
|
| 7 |
+
Pillow==12.3.0
|
| 8 |
+
scipy==1.18.1
|
| 9 |
+
pylibjpeg==2.1.0
|
| 10 |
+
pylibjpeg-openjpeg==2.6.0
|
| 11 |
+
pylibjpeg-libjpeg==2.5.0
|
| 12 |
+
pylibjpeg-rle==2.2.0
|
src/__init__.py
ADDED
|
File without changes
|
src/annotations.py
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Canonical boundary conversion primitives; cohort/geometry audit must precede use.
|
| 2 |
+
|
| 3 |
+
Source depths are stored pixel coordinates. RWVM is retained for provenance and is
|
| 4 |
+
not blindly applied: Zeiss metadata can carry lateral rather than axial scale.
|
| 5 |
+
"""
|
| 6 |
+
from pathlib import Path
|
| 7 |
+
import numpy as np
|
| 8 |
+
import pydicom
|
| 9 |
+
|
| 10 |
+
def code_key(segment):
|
| 11 |
+
codes=segment.get('SegmentedPropertyTypeCodeSequence',[])
|
| 12 |
+
if len(codes)!=1:raise ValueError('Boundary needs one unambiguous anatomical code')
|
| 13 |
+
return str(codes[0].CodingSchemeDesignator)+'_'+str(codes[0].CodeValue)
|
| 14 |
+
|
| 15 |
+
FRAME_MAPPING_VERSION='aireadi-heightmap-anatomy-v2'
|
| 16 |
+
|
| 17 |
+
def heightmap_frame_numbers(ds,device=None):
|
| 18 |
+
"""Return effective anatomy IDs for stored frames, with a Topcon export erratum.
|
| 19 |
+
|
| 20 |
+
AI-READI Topcon payloads are in anatomical depth order. Their sequential frame
|
| 21 |
+
IDs use a different SegmentSequence order for OPL/ELM/EZ/RPE. The fixed mapping
|
| 22 |
+
below is supported by train/validation raw B-scan overlays, layer definitions,
|
| 23 |
+
and depth ordering; it does not sort or otherwise alter per-location values.
|
| 24 |
+
Heidelberg and Zeiss follow their explicit frame IDs. See discovery evidence.
|
| 25 |
+
"""
|
| 26 |
+
declared=[int(f.SegmentIdentificationSequence[0].ReferencedSegmentNumber) for f in ds.get('PerFrameFunctionalGroupsSequence',[])]
|
| 27 |
+
if device not in ['topcon_maestro2','topcon_triton']:return declared
|
| 28 |
+
expected_n=9 if device=='topcon_maestro2' else 10
|
| 29 |
+
expected_codes=['SCT_280677004','DCM_128289','DCM_128290','DCM_128291','DCM_128320','DCM_128297','DCM_128299','DCM_128293','SCT_76710003']+(['DCM_128301'] if expected_n==10 else [])
|
| 30 |
+
segments={int(s.SegmentNumber):s for s in ds.SegmentSequence}
|
| 31 |
+
if sorted(segments)!=list(range(1,expected_n+1)) or [code_key(segments[n]) for n in sorted(segments)]!=expected_codes:raise ValueError('Unsupported Topcon codebook')
|
| 32 |
+
effective=[1,2,3,4,8,9,5,6,7]+([10] if expected_n==10 else [])
|
| 33 |
+
if declared==effective:return declared
|
| 34 |
+
if declared!=list(range(1,expected_n+1)):raise ValueError('Unsupported Topcon frame identity pattern')
|
| 35 |
+
return effective
|
| 36 |
+
|
| 37 |
+
def read_heightmap(path,height,device=None):
|
| 38 |
+
ds=pydicom.dcmread(path)
|
| 39 |
+
if str(ds.get('SegmentationType',''))!='HEIGHTMAP':raise ValueError('Unsupported segmentation representation')
|
| 40 |
+
raw=ds.pixel_array.astype(np.float32)
|
| 41 |
+
if raw.ndim==2:raw=raw[None]
|
| 42 |
+
frames=ds.get('PerFrameFunctionalGroupsSequence',[])
|
| 43 |
+
if len(frames)!=len(raw):raise ValueError('Missing frame-to-segment identities')
|
| 44 |
+
frame_numbers=heightmap_frame_numbers(ds,device)
|
| 45 |
+
segments={int(s.SegmentNumber):s for s in ds.SegmentSequence}
|
| 46 |
+
if len(frame_numbers)!=len(set(frame_numbers)) or set(frame_numbers)!=set(segments):raise ValueError('Ambiguous or incomplete heightmap frame mapping')
|
| 47 |
+
keys=[code_key(segments[n]) for n in sorted(segments)]
|
| 48 |
+
if len(keys)!=len(set(keys)):raise ValueError('Duplicate anatomical boundary code')
|
| 49 |
+
values=raw[[frame_numbers.index(n) for n in sorted(segments)]]
|
| 50 |
+
valid=np.isfinite(values)
|
| 51 |
+
padding=ds.get('FloatPixelPaddingValue',None)
|
| 52 |
+
if padding is not None:
|
| 53 |
+
low=float(padding);high=float(ds.get('FloatPixelPaddingRangeLimit',padding))
|
| 54 |
+
valid &= ~((values>=min(low,high))&(values<=max(low,high)))
|
| 55 |
+
# Zero is a real location. Values outside the imaged axial support cannot be
|
| 56 |
+
# scored in original-volume coordinates and remain source-invalid locations.
|
| 57 |
+
valid &= (values>=0)&(values<=height-1)
|
| 58 |
+
values=np.where(valid,values,0).astype(np.float32)
|
| 59 |
+
return values,np.asarray(keys),valid,ds
|
| 60 |
+
|
| 61 |
+
def source_support_statistics(ds,height,device=None):
|
| 62 |
+
"""Audit every source location without changing reference measurement support."""
|
| 63 |
+
raw=np.asarray(ds.pixel_array,dtype=np.float32)
|
| 64 |
+
if raw.ndim==2:raw=raw[None]
|
| 65 |
+
numbers=heightmap_frame_numbers(ds,device)
|
| 66 |
+
segments={int(s.SegmentNumber):s for s in ds.SegmentSequence}
|
| 67 |
+
padding=ds.get('FloatPixelPaddingValue',None)
|
| 68 |
+
result={}
|
| 69 |
+
for number in sorted(segments):
|
| 70 |
+
values=raw[numbers.index(number)];finite=np.isfinite(values);pad=np.zeros(values.shape,bool)
|
| 71 |
+
if padding is not None:
|
| 72 |
+
low=float(padding);high=float(ds.get('FloatPixelPaddingRangeLimit',padding))
|
| 73 |
+
pad=(values>=min(low,high))&(values<=max(low,high))
|
| 74 |
+
outside=finite&~pad&((values<0)|(values>height-1));valid=finite&~pad&~outside
|
| 75 |
+
result[code_key(segments[number])]={'locations':int(values.size),'valid_points':int(valid.sum()),
|
| 76 |
+
'nonfinite_points':int((~finite).sum()),'padding_points':int((finite&pad).sum()),
|
| 77 |
+
'outside_imaged_axial_support':int(outside.sum()),'valid_zero_depth_points':int(((values==0)&valid).sum()),
|
| 78 |
+
'b_scans_with_support':int(valid.any(-1).sum())}
|
| 79 |
+
return result
|
| 80 |
+
|
| 81 |
+
def axial_spacing_um(headers,device):
|
| 82 |
+
spacings=[]
|
| 83 |
+
for path,ds in headers:
|
| 84 |
+
shared=ds.get('SharedFunctionalGroupsSequence',[])
|
| 85 |
+
base=shared[0] if shared else ds
|
| 86 |
+
for fr in ds.get('PerFrameFunctionalGroupsSequence',[ds]):
|
| 87 |
+
pm=fr.get('PixelMeasuresSequence',base.get('PixelMeasuresSequence',[]))
|
| 88 |
+
if not pm:return None
|
| 89 |
+
spacing=float(pm[0].PixelSpacing[0])
|
| 90 |
+
if not np.isfinite(spacing) or spacing<=0:return None
|
| 91 |
+
spacings.append(spacing)
|
| 92 |
+
if not spacings or not np.allclose(spacings,spacings[0],rtol=1e-5,atol=1e-9):return None
|
| 93 |
+
return spacings[0]*1000
|
| 94 |
+
|
| 95 |
+
def convert_case(row,root,headers,geometry,with_audit=False):
|
| 96 |
+
b,h,a=geometry
|
| 97 |
+
if len(row['segmentation_paths'])!=1:raise ValueError('Multiple segmentation assembly requires explicit frozen mapping')
|
| 98 |
+
values,keys,valid,ds=read_heightmap(Path(root)/row['segmentation_paths'][0],h,row['device'])
|
| 99 |
+
if values.shape[1:]!=(b,a):raise ValueError('Heightmap and structural grid differ')
|
| 100 |
+
# Frame order and axes are verified by frozen metadata audit plus source overlays.
|
| 101 |
+
spacing=axial_spacing_um(headers,row['device'])
|
| 102 |
+
data={'positions':values,'boundary_keys':keys,'valid':valid,'height':np.asarray(h,dtype=np.int32),**({'axial_spacing_um':np.asarray(spacing)} if spacing else {})}
|
| 103 |
+
if with_audit:return data,source_support_statistics(ds,h,row['device'])
|
| 104 |
+
return data
|
src/app.py
ADDED
|
@@ -0,0 +1,605 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Native Gradio controls for the retained OCT model and B-scan viewer."""
|
| 2 |
+
|
| 3 |
+
from __future__ import annotations
|
| 4 |
+
|
| 5 |
+
import html
|
| 6 |
+
import os
|
| 7 |
+
from pathlib import Path
|
| 8 |
+
|
| 9 |
+
os.environ.setdefault("GRADIO_ANALYTICS_ENABLED", "False")
|
| 10 |
+
|
| 11 |
+
import gradio as gr
|
| 12 |
+
from PIL import Image
|
| 13 |
+
|
| 14 |
+
from src.viewer import (
|
| 15 |
+
AUTO,
|
| 16 |
+
ENGINE,
|
| 17 |
+
FAMILIES,
|
| 18 |
+
STORE,
|
| 19 |
+
boundary_choices,
|
| 20 |
+
compute_choices,
|
| 21 |
+
legend,
|
| 22 |
+
load_upload,
|
| 23 |
+
render,
|
| 24 |
+
resolve_family,
|
| 25 |
+
volume_info,
|
| 26 |
+
)
|
| 27 |
+
|
| 28 |
+
DEFAULT_SCANNER = "heidelberg_spectralis"
|
| 29 |
+
EMPTY_MESSAGE = "Upload a structural OCT DICOM to begin."
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
def download_result(volume, artifact, png=None):
|
| 33 |
+
if artifact not in {"predictions", "overlay"}:
|
| 34 |
+
raise gr.Error("Choose a supported export format.")
|
| 35 |
+
label = "Download NPZ" if artifact == "predictions" else "Download PNG"
|
| 36 |
+
path = None
|
| 37 |
+
if volume and volume.prediction:
|
| 38 |
+
path = volume.prediction.export if artifact == "predictions" else png
|
| 39 |
+
ready = path is not None and Path(path).is_file()
|
| 40 |
+
return gr.update(value=str(path) if ready else None, label=label, interactive=ready)
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
def display_outputs(
|
| 44 |
+
identity,
|
| 45 |
+
frame,
|
| 46 |
+
keys,
|
| 47 |
+
overlay,
|
| 48 |
+
opacity,
|
| 49 |
+
width,
|
| 50 |
+
labels,
|
| 51 |
+
contrast,
|
| 52 |
+
brightness,
|
| 53 |
+
physical,
|
| 54 |
+
artifact="predictions",
|
| 55 |
+
):
|
| 56 |
+
if not identity:
|
| 57 |
+
return (
|
| 58 |
+
None,
|
| 59 |
+
None,
|
| 60 |
+
"Upload a scan to browse B-scans.",
|
| 61 |
+
download_result(None, artifact),
|
| 62 |
+
)
|
| 63 |
+
volume = STORE.get(identity)
|
| 64 |
+
index = max(0, min(volume.shape[0] - 1, int(frame) - 1))
|
| 65 |
+
volume.view_frame = index
|
| 66 |
+
volume.view_settings = (
|
| 67 |
+
keys,
|
| 68 |
+
overlay,
|
| 69 |
+
opacity,
|
| 70 |
+
width,
|
| 71 |
+
labels,
|
| 72 |
+
contrast,
|
| 73 |
+
brightness,
|
| 74 |
+
physical,
|
| 75 |
+
artifact,
|
| 76 |
+
)
|
| 77 |
+
raw, result = render(
|
| 78 |
+
volume,
|
| 79 |
+
index,
|
| 80 |
+
keys,
|
| 81 |
+
overlay,
|
| 82 |
+
opacity,
|
| 83 |
+
width,
|
| 84 |
+
labels,
|
| 85 |
+
contrast,
|
| 86 |
+
brightness,
|
| 87 |
+
physical,
|
| 88 |
+
)
|
| 89 |
+
caption = f"B-scan {index + 1:,} / {volume.shape[0]:,}"
|
| 90 |
+
png = None
|
| 91 |
+
if result is not None:
|
| 92 |
+
png = volume.directory / f"overlay-bscan-{index + 1:04d}.png"
|
| 93 |
+
Image.fromarray(result).save(png)
|
| 94 |
+
caption += " · " + (
|
| 95 |
+
"full-volume prediction"
|
| 96 |
+
if volume.prediction.complete_volume
|
| 97 |
+
else "single-slice preview"
|
| 98 |
+
)
|
| 99 |
+
elif volume.prediction:
|
| 100 |
+
caption += " · this slice has not been segmented"
|
| 101 |
+
return raw, result, caption, download_result(volume, artifact, png)
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
def on_upload(
|
| 105 |
+
files,
|
| 106 |
+
previous,
|
| 107 |
+
scanner,
|
| 108 |
+
overlay,
|
| 109 |
+
opacity,
|
| 110 |
+
width,
|
| 111 |
+
labels,
|
| 112 |
+
contrast,
|
| 113 |
+
brightness,
|
| 114 |
+
physical,
|
| 115 |
+
artifact,
|
| 116 |
+
):
|
| 117 |
+
volume = None
|
| 118 |
+
try:
|
| 119 |
+
volume = load_upload(files)
|
| 120 |
+
identity = STORE.add(volume)
|
| 121 |
+
frame = (volume.shape[0] - 1) // 2 + 1
|
| 122 |
+
family = volume.detected_family if scanner == AUTO else scanner
|
| 123 |
+
choices = boundary_choices(family)
|
| 124 |
+
keys = [value for _, value in choices]
|
| 125 |
+
raw, result, caption, download = display_outputs(
|
| 126 |
+
identity,
|
| 127 |
+
frame,
|
| 128 |
+
keys,
|
| 129 |
+
overlay,
|
| 130 |
+
opacity,
|
| 131 |
+
width,
|
| 132 |
+
labels,
|
| 133 |
+
contrast,
|
| 134 |
+
brightness,
|
| 135 |
+
physical,
|
| 136 |
+
artifact,
|
| 137 |
+
)
|
| 138 |
+
if previous:
|
| 139 |
+
STORE.remove(previous)
|
| 140 |
+
message = "Scan loaded. Check the scanner family, then run inference."
|
| 141 |
+
if family is None:
|
| 142 |
+
message = "Scan loaded. Select its scanner family, then run inference."
|
| 143 |
+
return (
|
| 144 |
+
identity,
|
| 145 |
+
raw,
|
| 146 |
+
result,
|
| 147 |
+
gr.update(
|
| 148 |
+
minimum=1,
|
| 149 |
+
maximum=max(2, volume.shape[0]),
|
| 150 |
+
value=frame,
|
| 151 |
+
interactive=volume.shape[0] > 1,
|
| 152 |
+
),
|
| 153 |
+
gr.update(choices=choices, value=keys),
|
| 154 |
+
volume_info(volume, family),
|
| 155 |
+
legend(keys),
|
| 156 |
+
caption,
|
| 157 |
+
download,
|
| 158 |
+
message,
|
| 159 |
+
gr.update(interactive=True),
|
| 160 |
+
)
|
| 161 |
+
except Exception as exc:
|
| 162 |
+
if volume is not None:
|
| 163 |
+
STORE.remove(volume.identity)
|
| 164 |
+
raise gr.Error(str(exc)) from exc
|
| 165 |
+
|
| 166 |
+
|
| 167 |
+
def clear_upload(identity, artifact="predictions"):
|
| 168 |
+
STORE.remove(identity)
|
| 169 |
+
return (
|
| 170 |
+
None,
|
| 171 |
+
None,
|
| 172 |
+
None,
|
| 173 |
+
gr.update(minimum=1, maximum=2, value=1, interactive=False),
|
| 174 |
+
gr.update(choices=[], value=[]),
|
| 175 |
+
"No scan loaded.",
|
| 176 |
+
legend([]),
|
| 177 |
+
"Upload a scan to browse B-scans.",
|
| 178 |
+
download_result(None, artifact),
|
| 179 |
+
EMPTY_MESSAGE,
|
| 180 |
+
gr.update(interactive=False),
|
| 181 |
+
)
|
| 182 |
+
|
| 183 |
+
|
| 184 |
+
def clear_volume(identity):
|
| 185 |
+
return (
|
| 186 |
+
*clear_upload(identity),
|
| 187 |
+
gr.update(value=None),
|
| 188 |
+
DEFAULT_SCANNER,
|
| 189 |
+
"predictions",
|
| 190 |
+
)
|
| 191 |
+
|
| 192 |
+
|
| 193 |
+
def scanner_changed(
|
| 194 |
+
identity,
|
| 195 |
+
scanner,
|
| 196 |
+
frame,
|
| 197 |
+
overlay,
|
| 198 |
+
opacity,
|
| 199 |
+
width,
|
| 200 |
+
labels,
|
| 201 |
+
contrast,
|
| 202 |
+
brightness,
|
| 203 |
+
physical,
|
| 204 |
+
artifact,
|
| 205 |
+
):
|
| 206 |
+
if not identity:
|
| 207 |
+
return (gr.skip(),) * 8
|
| 208 |
+
volume = STORE.get(identity)
|
| 209 |
+
family = volume.detected_family if scanner == AUTO else scanner
|
| 210 |
+
if volume.prediction is not None and volume.prediction.family != family:
|
| 211 |
+
volume.prediction = None
|
| 212 |
+
choices = boundary_choices(family)
|
| 213 |
+
keys = [value for _, value in choices]
|
| 214 |
+
outputs = display_outputs(
|
| 215 |
+
identity,
|
| 216 |
+
frame,
|
| 217 |
+
keys,
|
| 218 |
+
overlay,
|
| 219 |
+
opacity,
|
| 220 |
+
width,
|
| 221 |
+
labels,
|
| 222 |
+
contrast,
|
| 223 |
+
brightness,
|
| 224 |
+
physical,
|
| 225 |
+
artifact,
|
| 226 |
+
)
|
| 227 |
+
return (
|
| 228 |
+
gr.update(choices=choices, value=keys),
|
| 229 |
+
volume_info(volume, family),
|
| 230 |
+
legend(keys),
|
| 231 |
+
*outputs,
|
| 232 |
+
"Scanner selection updated. Run inference to apply it.",
|
| 233 |
+
)
|
| 234 |
+
|
| 235 |
+
|
| 236 |
+
def move_frame(delta):
|
| 237 |
+
def move(identity, frame, *settings):
|
| 238 |
+
if not identity:
|
| 239 |
+
return (gr.skip(),) * 5
|
| 240 |
+
volume = STORE.get(identity)
|
| 241 |
+
next_frame = max(1, min(volume.shape[0], int(frame) + delta))
|
| 242 |
+
return gr.update(value=next_frame), *display_outputs(
|
| 243 |
+
identity, next_frame, *settings
|
| 244 |
+
)
|
| 245 |
+
|
| 246 |
+
return move
|
| 247 |
+
|
| 248 |
+
|
| 249 |
+
def update_display(identity, frame, *settings):
|
| 250 |
+
outputs = display_outputs(identity, frame, *settings)
|
| 251 |
+
return *outputs, legend(settings[0]) if identity else legend([])
|
| 252 |
+
|
| 253 |
+
|
| 254 |
+
def segment(
|
| 255 |
+
identity,
|
| 256 |
+
frame,
|
| 257 |
+
scanner,
|
| 258 |
+
compute,
|
| 259 |
+
scope,
|
| 260 |
+
batch_size,
|
| 261 |
+
*settings,
|
| 262 |
+
progress=gr.Progress(),
|
| 263 |
+
):
|
| 264 |
+
try:
|
| 265 |
+
volume = STORE.get(identity)
|
| 266 |
+
family = resolve_family(volume, scanner)
|
| 267 |
+
if batch_size is None or not 1 <= int(batch_size) <= 16:
|
| 268 |
+
raise ValueError("Enter a batch size from 1 to 16.")
|
| 269 |
+
progress(0, desc="Loading the saved model")
|
| 270 |
+
yield (
|
| 271 |
+
gr.skip(),
|
| 272 |
+
None,
|
| 273 |
+
"Loading model…",
|
| 274 |
+
download_result(None, settings[-1]),
|
| 275 |
+
"Loading the saved model. First use takes a little longer.",
|
| 276 |
+
gr.update(interactive=False),
|
| 277 |
+
)
|
| 278 |
+
for event in ENGINE.predict(
|
| 279 |
+
volume, family, compute, int(batch_size), scope == "volume", int(frame) - 1
|
| 280 |
+
):
|
| 281 |
+
if "result" not in event:
|
| 282 |
+
progress(
|
| 283 |
+
event["completed"] / event["total"],
|
| 284 |
+
desc=f"Segmenting B-scans · {event['completed']:,}/{event['total']:,}",
|
| 285 |
+
)
|
| 286 |
+
message = (
|
| 287 |
+
f"Segmenting {event['completed']:,} / {event['total']:,} B-scans · "
|
| 288 |
+
f"{event['device'].upper()} · {event['seconds']:.0f} s elapsed"
|
| 289 |
+
)
|
| 290 |
+
yield (
|
| 291 |
+
gr.skip(),
|
| 292 |
+
gr.skip(),
|
| 293 |
+
gr.skip(),
|
| 294 |
+
gr.skip(),
|
| 295 |
+
message,
|
| 296 |
+
gr.update(interactive=False),
|
| 297 |
+
)
|
| 298 |
+
else:
|
| 299 |
+
result = event["result"]
|
| 300 |
+
outputs = display_outputs(
|
| 301 |
+
identity, volume.view_frame + 1, *(volume.view_settings or settings)
|
| 302 |
+
)
|
| 303 |
+
message = (
|
| 304 |
+
f"**Completed** · {FAMILIES[family]} · {result.compute.upper()} · "
|
| 305 |
+
f"{len(result.frames):,} B-scans · {len(result.keys)} boundaries · "
|
| 306 |
+
f"{result.seconds:.1f} s"
|
| 307 |
+
)
|
| 308 |
+
if not result.complete_volume:
|
| 309 |
+
message += " \nSlice preview omits smoothing between B-scans. Use Full volume for the saved pipeline."
|
| 310 |
+
yield *outputs, message, gr.update(interactive=True)
|
| 311 |
+
except Exception as exc:
|
| 312 |
+
message = html.escape(str(exc))
|
| 313 |
+
if "out of memory" in str(exc).lower():
|
| 314 |
+
message += " Try batch size 1, or select CPU."
|
| 315 |
+
yield (
|
| 316 |
+
gr.skip(),
|
| 317 |
+
gr.skip(),
|
| 318 |
+
gr.skip(),
|
| 319 |
+
gr.skip(),
|
| 320 |
+
f"**Error:** {message}",
|
| 321 |
+
gr.update(interactive=True),
|
| 322 |
+
)
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
def cancel(identity):
|
| 326 |
+
if identity:
|
| 327 |
+
STORE.get(identity).cancelled = True
|
| 328 |
+
return (
|
| 329 |
+
"Stop requested. Inference stops after the current model batch.",
|
| 330 |
+
gr.update(interactive=True),
|
| 331 |
+
)
|
| 332 |
+
|
| 333 |
+
|
| 334 |
+
def build_app():
|
| 335 |
+
zoom_js = Path(__file__).with_name("viewer.js").read_text()
|
| 336 |
+
with gr.Blocks(
|
| 337 |
+
title="MYXOS · OCT Viewer", analytics_enabled=False, delete_cache=(7200, 7200)
|
| 338 |
+
) as demo:
|
| 339 |
+
identity = gr.State(value=None, time_to_live=7200, delete_callback=STORE.remove)
|
| 340 |
+
gr.Markdown("# OCT Boundary Explorer")
|
| 341 |
+
with gr.Row():
|
| 342 |
+
with gr.Column(scale=1, min_width=300):
|
| 343 |
+
gr.Markdown("### Configuration")
|
| 344 |
+
upload = gr.File(
|
| 345 |
+
label="OCT volume",
|
| 346 |
+
file_types=[".dcm", ".dicom"],
|
| 347 |
+
file_count="multiple",
|
| 348 |
+
type="filepath",
|
| 349 |
+
height=135,
|
| 350 |
+
)
|
| 351 |
+
scanner = gr.Dropdown(
|
| 352 |
+
choices=[
|
| 353 |
+
*[(name, key) for key, name in FAMILIES.items()],
|
| 354 |
+
("Detect from DICOM", AUTO),
|
| 355 |
+
],
|
| 356 |
+
value=DEFAULT_SCANNER,
|
| 357 |
+
label="Scanner family",
|
| 358 |
+
)
|
| 359 |
+
compute = gr.Dropdown(
|
| 360 |
+
choices=compute_choices(),
|
| 361 |
+
value="auto",
|
| 362 |
+
label="Processor",
|
| 363 |
+
info="Auto uses an available GPU, otherwise CPU.",
|
| 364 |
+
)
|
| 365 |
+
scope = gr.Radio(
|
| 366 |
+
choices=[
|
| 367 |
+
("Full volume", "volume"),
|
| 368 |
+
("Selected B-scan preview", "preview"),
|
| 369 |
+
],
|
| 370 |
+
value="volume",
|
| 371 |
+
label="Inference scope",
|
| 372 |
+
)
|
| 373 |
+
with gr.Accordion("Performance settings", open=False):
|
| 374 |
+
batch = gr.Number(
|
| 375 |
+
value=1,
|
| 376 |
+
minimum=1,
|
| 377 |
+
maximum=16,
|
| 378 |
+
step=1,
|
| 379 |
+
precision=0,
|
| 380 |
+
label="Batch size",
|
| 381 |
+
info="Lower this if GPU memory is limited.",
|
| 382 |
+
)
|
| 383 |
+
with gr.Row():
|
| 384 |
+
run = gr.Button(
|
| 385 |
+
"Run inference",
|
| 386 |
+
variant="primary",
|
| 387 |
+
interactive=False,
|
| 388 |
+
scale=3,
|
| 389 |
+
min_width=135,
|
| 390 |
+
)
|
| 391 |
+
stop = gr.Button("Stop", variant="stop", scale=1, min_width=70)
|
| 392 |
+
clear = gr.Button("Clear volume", size="sm")
|
| 393 |
+
scan_info = gr.Markdown("No scan loaded.")
|
| 394 |
+
gr.Markdown(
|
| 395 |
+
"Upload one volume, or its contiguous DICOM parts together."
|
| 396 |
+
)
|
| 397 |
+
with gr.Column(scale=3, min_width=480):
|
| 398 |
+
gr.Markdown("### Boundary viewer")
|
| 399 |
+
messages = gr.Markdown(EMPTY_MESSAGE)
|
| 400 |
+
with gr.Tabs():
|
| 401 |
+
viewers = []
|
| 402 |
+
for tab, label, viewer_id in [
|
| 403 |
+
("Boundary overlay", "Predicted boundaries", "overlay-viewer"),
|
| 404 |
+
("Original OCT", "OCT B-scan", "source-viewer"),
|
| 405 |
+
]:
|
| 406 |
+
with gr.Tab(tab):
|
| 407 |
+
buttons = []
|
| 408 |
+
for text, action in [
|
| 409 |
+
("Zoom in", "in"),
|
| 410 |
+
("Zoom out", "out"),
|
| 411 |
+
("Fit", "fit"),
|
| 412 |
+
]:
|
| 413 |
+
button = gr.Button(text, size="sm", render=False)
|
| 414 |
+
button.click(
|
| 415 |
+
fn=None,
|
| 416 |
+
js=f"() => ({zoom_js})('{viewer_id}', '{action}')",
|
| 417 |
+
queue=False,
|
| 418 |
+
api_name=False,
|
| 419 |
+
)
|
| 420 |
+
buttons.append(button)
|
| 421 |
+
viewers.append(
|
| 422 |
+
gr.Image(
|
| 423 |
+
label=label,
|
| 424 |
+
type="numpy",
|
| 425 |
+
format="png",
|
| 426 |
+
interactive=False,
|
| 427 |
+
height=480,
|
| 428 |
+
buttons=[*buttons, "fullscreen"],
|
| 429 |
+
elem_id=viewer_id,
|
| 430 |
+
)
|
| 431 |
+
)
|
| 432 |
+
segmented, original = viewers
|
| 433 |
+
gr.Markdown(
|
| 434 |
+
"Use Zoom in / Zoom out, then drag to pan. Fit resets the view."
|
| 435 |
+
)
|
| 436 |
+
with gr.Row():
|
| 437 |
+
previous = gr.Button("Previous", scale=0, min_width=85)
|
| 438 |
+
frame = gr.Slider(
|
| 439 |
+
1,
|
| 440 |
+
2,
|
| 441 |
+
value=1,
|
| 442 |
+
step=1,
|
| 443 |
+
label="B-scan",
|
| 444 |
+
scale=6,
|
| 445 |
+
interactive=False,
|
| 446 |
+
)
|
| 447 |
+
following = gr.Button("Next", scale=0, min_width=85)
|
| 448 |
+
caption = gr.Markdown("Upload a scan to browse B-scans.")
|
| 449 |
+
colors = gr.Markdown(legend([]))
|
| 450 |
+
with gr.Accordion("Visible boundaries", open=False):
|
| 451 |
+
boundaries = gr.CheckboxGroup(
|
| 452 |
+
choices=[], value=[], label="Overlay boundaries"
|
| 453 |
+
)
|
| 454 |
+
with gr.Accordion("Display settings", open=False):
|
| 455 |
+
with gr.Row():
|
| 456 |
+
show_overlay = gr.Checkbox(value=True, label="Show boundaries")
|
| 457 |
+
show_labels = gr.Checkbox(value=False, label="Label curves")
|
| 458 |
+
physical = gr.Checkbox(
|
| 459 |
+
value=True, label="Use physical pixel aspect"
|
| 460 |
+
)
|
| 461 |
+
with gr.Row():
|
| 462 |
+
opacity = gr.Slider(
|
| 463 |
+
0.1, 1.0, value=0.9, step=0.05, label="Overlay opacity"
|
| 464 |
+
)
|
| 465 |
+
width = gr.Slider(1, 5, value=2, step=1, label="Line width")
|
| 466 |
+
with gr.Row():
|
| 467 |
+
contrast = gr.Slider(
|
| 468 |
+
0.5, 3.0, value=1.0, step=0.05, label="Display contrast"
|
| 469 |
+
)
|
| 470 |
+
brightness = gr.Slider(
|
| 471 |
+
-0.4, 0.4, value=0.0, step=0.02, label="Display brightness"
|
| 472 |
+
)
|
| 473 |
+
with gr.Row():
|
| 474 |
+
artifact = gr.Dropdown(
|
| 475 |
+
choices=[
|
| 476 |
+
("Boundary predictions · NPZ", "predictions"),
|
| 477 |
+
("Current B-scan overlay · PNG", "overlay"),
|
| 478 |
+
],
|
| 479 |
+
value="predictions",
|
| 480 |
+
label="Export format",
|
| 481 |
+
scale=2,
|
| 482 |
+
)
|
| 483 |
+
download = gr.DownloadButton(
|
| 484 |
+
"Download selected output",
|
| 485 |
+
interactive=False,
|
| 486 |
+
scale=1,
|
| 487 |
+
min_width=175,
|
| 488 |
+
)
|
| 489 |
+
gr.Markdown(
|
| 490 |
+
"Display settings change the view only. Predictions retain original OCT coordinates."
|
| 491 |
+
)
|
| 492 |
+
|
| 493 |
+
display_settings = [
|
| 494 |
+
boundaries,
|
| 495 |
+
show_overlay,
|
| 496 |
+
opacity,
|
| 497 |
+
width,
|
| 498 |
+
show_labels,
|
| 499 |
+
contrast,
|
| 500 |
+
brightness,
|
| 501 |
+
physical,
|
| 502 |
+
artifact,
|
| 503 |
+
]
|
| 504 |
+
settings_without_keys = display_settings[1:]
|
| 505 |
+
display_widgets = [original, segmented, caption, download]
|
| 506 |
+
upload_outputs = [
|
| 507 |
+
identity,
|
| 508 |
+
original,
|
| 509 |
+
segmented,
|
| 510 |
+
frame,
|
| 511 |
+
boundaries,
|
| 512 |
+
scan_info,
|
| 513 |
+
colors,
|
| 514 |
+
caption,
|
| 515 |
+
download,
|
| 516 |
+
messages,
|
| 517 |
+
run,
|
| 518 |
+
]
|
| 519 |
+
upload.upload(
|
| 520 |
+
on_upload,
|
| 521 |
+
[upload, identity, scanner, *settings_without_keys],
|
| 522 |
+
upload_outputs,
|
| 523 |
+
api_name="load_oct",
|
| 524 |
+
concurrency_id="viewer",
|
| 525 |
+
concurrency_limit=1,
|
| 526 |
+
)
|
| 527 |
+
upload.clear(
|
| 528 |
+
clear_upload,
|
| 529 |
+
[identity, artifact],
|
| 530 |
+
upload_outputs,
|
| 531 |
+
concurrency_id="viewer",
|
| 532 |
+
concurrency_limit=1,
|
| 533 |
+
)
|
| 534 |
+
clear.click(
|
| 535 |
+
clear_volume,
|
| 536 |
+
[identity],
|
| 537 |
+
upload_outputs + [upload, scanner, artifact],
|
| 538 |
+
api_name="clear_volume",
|
| 539 |
+
concurrency_id="viewer",
|
| 540 |
+
concurrency_limit=1,
|
| 541 |
+
)
|
| 542 |
+
scanner.change(
|
| 543 |
+
scanner_changed,
|
| 544 |
+
[identity, scanner, frame, *settings_without_keys],
|
| 545 |
+
[boundaries, scan_info, colors, *display_widgets, messages],
|
| 546 |
+
concurrency_id="viewer",
|
| 547 |
+
concurrency_limit=1,
|
| 548 |
+
)
|
| 549 |
+
frame.release(
|
| 550 |
+
display_outputs,
|
| 551 |
+
[identity, frame, *display_settings],
|
| 552 |
+
display_widgets,
|
| 553 |
+
queue=False,
|
| 554 |
+
api_name="view_bscan",
|
| 555 |
+
)
|
| 556 |
+
for button, delta in [(previous, -1), (following, 1)]:
|
| 557 |
+
button.click(
|
| 558 |
+
move_frame(delta),
|
| 559 |
+
[identity, frame, *display_settings],
|
| 560 |
+
[frame, *display_widgets],
|
| 561 |
+
queue=False,
|
| 562 |
+
api_name=False,
|
| 563 |
+
)
|
| 564 |
+
for control in (show_overlay, show_labels, physical, boundaries):
|
| 565 |
+
control.input(
|
| 566 |
+
update_display,
|
| 567 |
+
[identity, frame, *display_settings],
|
| 568 |
+
[*display_widgets, colors],
|
| 569 |
+
queue=False,
|
| 570 |
+
api_name=False,
|
| 571 |
+
)
|
| 572 |
+
for control in (opacity, width, contrast, brightness):
|
| 573 |
+
control.release(
|
| 574 |
+
display_outputs,
|
| 575 |
+
[identity, frame, *display_settings],
|
| 576 |
+
display_widgets,
|
| 577 |
+
queue=False,
|
| 578 |
+
api_name=False,
|
| 579 |
+
)
|
| 580 |
+
artifact.input(
|
| 581 |
+
display_outputs,
|
| 582 |
+
[identity, frame, *display_settings],
|
| 583 |
+
display_widgets,
|
| 584 |
+
queue=False,
|
| 585 |
+
api_name="select_export",
|
| 586 |
+
)
|
| 587 |
+
inference = run.click(
|
| 588 |
+
segment,
|
| 589 |
+
[identity, frame, scanner, compute, scope, batch, *display_settings],
|
| 590 |
+
[*display_widgets, messages, run],
|
| 591 |
+
api_name="segment_oct",
|
| 592 |
+
show_progress="full",
|
| 593 |
+
show_progress_on=[segmented, original],
|
| 594 |
+
concurrency_id="viewer",
|
| 595 |
+
concurrency_limit=1,
|
| 596 |
+
)
|
| 597 |
+
stop.click(
|
| 598 |
+
cancel,
|
| 599 |
+
[identity],
|
| 600 |
+
[messages, run],
|
| 601 |
+
cancels=[inference],
|
| 602 |
+
queue=False,
|
| 603 |
+
api_name="stop_segmentation",
|
| 604 |
+
)
|
| 605 |
+
return demo
|
src/inference/__init__.py
ADDED
|
File without changes
|
src/inference/combination.py
ADDED
|
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Combine model positions only, in the original structural coordinate grid."""
|
| 2 |
+
|
| 3 |
+
import numpy as np
|
| 4 |
+
from src.inference.postprocess import transform
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
def combine_positions(positions, method="mean", weights=None):
|
| 8 |
+
if not positions:
|
| 9 |
+
raise ValueError("No ensemble members")
|
| 10 |
+
shape = positions[0].shape
|
| 11 |
+
if any(p.shape != shape for p in positions):
|
| 12 |
+
raise ValueError("Ensemble geometry differs")
|
| 13 |
+
stack = np.stack(positions).astype(np.float32, copy=False)
|
| 14 |
+
if not np.isfinite(stack).all():
|
| 15 |
+
raise ValueError("Nonfinite ensemble member")
|
| 16 |
+
if method == "mean":
|
| 17 |
+
if weights is None:
|
| 18 |
+
return stack.mean(axis=0, dtype=np.float32)
|
| 19 |
+
weight = np.asarray(weights, dtype=np.float32)
|
| 20 |
+
if (
|
| 21 |
+
weight.shape != (len(positions),)
|
| 22 |
+
or not np.isfinite(weight).all()
|
| 23 |
+
or (weight < 0).any()
|
| 24 |
+
or weight.sum() <= 0
|
| 25 |
+
):
|
| 26 |
+
raise ValueError("Invalid ensemble weights")
|
| 27 |
+
weight = weight / weight.sum()
|
| 28 |
+
return (stack * weight.reshape((-1,) + (1,) * len(shape))).sum(
|
| 29 |
+
0, dtype=np.float32
|
| 30 |
+
)
|
| 31 |
+
if weights is not None:
|
| 32 |
+
raise ValueError("Only means accept weights")
|
| 33 |
+
if method == "median":
|
| 34 |
+
return np.median(stack, axis=0).astype(np.float32)
|
| 35 |
+
raise ValueError("Unknown position combination")
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
def finish_positions(positions, device, height, configuration):
|
| 39 |
+
return transform(positions, device, height, configuration or {})
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
def combine_named_heads(positions, member_names, boundary_keys, device, configuration):
|
| 43 |
+
"""Select fixed trained heads by device/anatomy; no case-dependent routing."""
|
| 44 |
+
weighted = configuration.get("head_weights_by_device")
|
| 45 |
+
if weighted is not None:
|
| 46 |
+
if (
|
| 47 |
+
"head_source_by_device" in configuration
|
| 48 |
+
or "weights" in configuration
|
| 49 |
+
or configuration.get("method") != "weighted_heads"
|
| 50 |
+
):
|
| 51 |
+
raise ValueError(
|
| 52 |
+
"Weighted anatomical heads require their own explicit combination method"
|
| 53 |
+
)
|
| 54 |
+
if (
|
| 55 |
+
not positions
|
| 56 |
+
or len(member_names) != len(positions)
|
| 57 |
+
or len(set(member_names)) != len(member_names)
|
| 58 |
+
):
|
| 59 |
+
raise ValueError("Invalid weighted head sources")
|
| 60 |
+
if not boundary_keys or len(set(boundary_keys)) != len(boundary_keys):
|
| 61 |
+
raise ValueError("Invalid weighted boundary identities")
|
| 62 |
+
shape = positions[0].shape
|
| 63 |
+
if (
|
| 64 |
+
len(shape) != 3
|
| 65 |
+
or shape[0] != len(boundary_keys)
|
| 66 |
+
or any(p.shape != shape or not np.isfinite(p).all() for p in positions)
|
| 67 |
+
):
|
| 68 |
+
raise ValueError("Invalid weighted head geometry or values")
|
| 69 |
+
if device not in weighted or set(weighted[device]) != set(boundary_keys):
|
| 70 |
+
raise ValueError("Weighted anatomical identities differ")
|
| 71 |
+
output = []
|
| 72 |
+
for index, key in enumerate(boundary_keys):
|
| 73 |
+
rule = weighted[device][key]
|
| 74 |
+
if (
|
| 75 |
+
not isinstance(rule, dict)
|
| 76 |
+
or not 1 <= len(rule) <= 2
|
| 77 |
+
or not set(rule) <= set(member_names)
|
| 78 |
+
):
|
| 79 |
+
raise ValueError("One or two known weighted heads are required")
|
| 80 |
+
names = [name for name in member_names if name in rule]
|
| 81 |
+
weights = np.asarray([rule[name] for name in names], dtype=np.float32)
|
| 82 |
+
if (
|
| 83 |
+
not np.isfinite(weights).all()
|
| 84 |
+
or (weights <= 0).any()
|
| 85 |
+
or abs(float(weights.sum()) - 1) > 1e-6
|
| 86 |
+
):
|
| 87 |
+
raise ValueError(
|
| 88 |
+
"Weighted head coefficients must be positive and sum to one"
|
| 89 |
+
)
|
| 90 |
+
output.append(
|
| 91 |
+
combine_positions(
|
| 92 |
+
[positions[member_names.index(name)][index] for name in names],
|
| 93 |
+
"mean",
|
| 94 |
+
weights,
|
| 95 |
+
)
|
| 96 |
+
)
|
| 97 |
+
return np.stack(output).astype(np.float32, copy=False)
|
| 98 |
+
mapping = configuration.get("head_source_by_device")
|
| 99 |
+
if mapping is None:
|
| 100 |
+
return combine_positions(
|
| 101 |
+
positions, configuration.get("method", "mean"), configuration.get("weights")
|
| 102 |
+
)
|
| 103 |
+
if "weights" in configuration or configuration.get("method", "mean") != "mean":
|
| 104 |
+
raise ValueError("Head selection cannot also configure averaging weights")
|
| 105 |
+
if len(member_names) != len(positions) or len(set(member_names)) != len(
|
| 106 |
+
member_names
|
| 107 |
+
):
|
| 108 |
+
raise ValueError("Invalid named head sources")
|
| 109 |
+
if not positions or len(set(boundary_keys)) != len(boundary_keys):
|
| 110 |
+
raise ValueError("Invalid boundary identities")
|
| 111 |
+
shape = positions[0].shape
|
| 112 |
+
if (
|
| 113 |
+
len(shape) != 3
|
| 114 |
+
or shape[0] != len(boundary_keys)
|
| 115 |
+
or any(p.shape != shape for p in positions)
|
| 116 |
+
):
|
| 117 |
+
raise ValueError("Head-source prediction geometry differs")
|
| 118 |
+
if device not in mapping or set(mapping[device]) != set(boundary_keys):
|
| 119 |
+
raise ValueError("Head-source anatomical identities differ")
|
| 120 |
+
if any(name not in member_names for name in mapping[device].values()):
|
| 121 |
+
raise ValueError("Unknown selected head source")
|
| 122 |
+
if any(not np.isfinite(p).all() for p in positions):
|
| 123 |
+
raise ValueError("Nonfinite head source")
|
| 124 |
+
return np.stack(
|
| 125 |
+
[
|
| 126 |
+
positions[member_names.index(mapping[device][key])][index]
|
| 127 |
+
for index, key in enumerate(boundary_keys)
|
| 128 |
+
]
|
| 129 |
+
).astype(np.float32, copy=False)
|
src/inference/context.py
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Bounded native B-scan windows, including adjacent/distant and global views."""
|
| 2 |
+
|
| 3 |
+
import numpy as np
|
| 4 |
+
from src.io import iter_volume_frames, normalize_frame, read_frames
|
| 5 |
+
|
| 6 |
+
OFFSETS = {1: [0], 3: [-1, 0, 1], 5: [-8, -1, 0, 1, 8], 6: [-1, 0, 1]}
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
def iter_normalized_contexts(headers, shapes):
|
| 10 |
+
if any(shape[2] not in OFFSETS for shape in shapes):
|
| 11 |
+
raise ValueError("Unsupported OCT image context")
|
| 12 |
+
spatial = sorted({tuple(shape[:2]) for shape in shapes})
|
| 13 |
+
total = sum(int(ds.get("NumberOfFrames", 1)) for _, ds in headers)
|
| 14 |
+
if total < 1:
|
| 15 |
+
raise ValueError("Empty structural volume")
|
| 16 |
+
global_views = {}
|
| 17 |
+
if any(shape[2] == 6 for shape in shapes):
|
| 18 |
+
selected = [0, total // 2, total - 1]
|
| 19 |
+
raw = read_frames(headers, sorted(set(selected)))
|
| 20 |
+
for shape in spatial:
|
| 21 |
+
global_views[shape] = np.stack(
|
| 22 |
+
[normalize_frame(raw[index], shape) for index in selected]
|
| 23 |
+
)
|
| 24 |
+
radius = max(abs(offset) for shape in shapes for offset in OFFSETS[shape[2]])
|
| 25 |
+
iterator = iter(iter_volume_frames(headers))
|
| 26 |
+
cache = {}
|
| 27 |
+
loaded = -1
|
| 28 |
+
for center in range(total):
|
| 29 |
+
last = min(total - 1, center + radius)
|
| 30 |
+
while loaded < last:
|
| 31 |
+
frame = next(iterator, None)
|
| 32 |
+
if frame is None:
|
| 33 |
+
raise ValueError("Structural frames ended before declared geometry")
|
| 34 |
+
loaded += 1
|
| 35 |
+
cache[loaded] = {shape: normalize_frame(frame, shape) for shape in spatial}
|
| 36 |
+
images = []
|
| 37 |
+
for shape in shapes:
|
| 38 |
+
key = tuple(shape[:2])
|
| 39 |
+
indices = [
|
| 40 |
+
max(0, min(total - 1, center + offset)) for offset in OFFSETS[shape[2]]
|
| 41 |
+
]
|
| 42 |
+
image = np.stack([cache[index][key] for index in indices])
|
| 43 |
+
if shape[2] == 6:
|
| 44 |
+
image = np.concatenate([image, global_views[key]], axis=0)
|
| 45 |
+
images.append(image)
|
| 46 |
+
yield images
|
| 47 |
+
oldest = center + 1 - radius
|
| 48 |
+
for index in list(cache):
|
| 49 |
+
if index < oldest:
|
| 50 |
+
del cache[index]
|
| 51 |
+
if next(iterator, None) is not None:
|
| 52 |
+
raise ValueError("Surplus structural frames")
|
src/inference/decoding.py
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Alternative point estimators for axial categorical distributions."""
|
| 2 |
+
|
| 3 |
+
import torch
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
def estimates(logits, names):
|
| 7 |
+
probability = logits.float().softmax(-2)
|
| 8 |
+
height = logits.shape[-2]
|
| 9 |
+
grid = torch.arange(height, device=logits.device, dtype=torch.float32)[
|
| 10 |
+
None, None, :, None
|
| 11 |
+
]
|
| 12 |
+
result = {}
|
| 13 |
+
if "mean" in names:
|
| 14 |
+
result["mean"] = (probability * grid).sum(-2)
|
| 15 |
+
if "median" in names:
|
| 16 |
+
cumulative = probability.cumsum(-2)
|
| 17 |
+
index = (cumulative < 0.5).sum(-2).clamp_max(height - 1)
|
| 18 |
+
mass = probability.gather(-2, index.unsqueeze(-2)).squeeze(-2)
|
| 19 |
+
before = cumulative.gather(-2, (index - 1).clamp_min(0).unsqueeze(-2)).squeeze(
|
| 20 |
+
-2
|
| 21 |
+
)
|
| 22 |
+
before = torch.where(index == 0, torch.zeros_like(before), before)
|
| 23 |
+
result["median"] = (
|
| 24 |
+
index.float() - 0.5 + (0.5 - before) / mass.clamp_min(1e-12)
|
| 25 |
+
).clamp(0, height - 1)
|
| 26 |
+
if "quadratic_mode" in names:
|
| 27 |
+
index = logits.argmax(-2)
|
| 28 |
+
score = logits.float()
|
| 29 |
+
center = score.gather(-2, index.unsqueeze(-2)).squeeze(-2)
|
| 30 |
+
left = score.gather(-2, (index - 1).clamp_min(0).unsqueeze(-2)).squeeze(-2)
|
| 31 |
+
right = score.gather(
|
| 32 |
+
-2, (index + 1).clamp_max(height - 1).unsqueeze(-2)
|
| 33 |
+
).squeeze(-2)
|
| 34 |
+
curvature = left - 2 * center + right
|
| 35 |
+
offset = torch.where(
|
| 36 |
+
(curvature < -1e-8) & (index > 0) & (index < height - 1),
|
| 37 |
+
0.5 * (left - right) / curvature.clamp_max(-1e-8),
|
| 38 |
+
torch.zeros_like(center),
|
| 39 |
+
).clamp(-0.5, 0.5)
|
| 40 |
+
result["quadratic_mode"] = (index.float() + offset).clamp(0, height - 1)
|
| 41 |
+
if set(result) != set(names):
|
| 42 |
+
raise ValueError("Unknown posterior estimator")
|
| 43 |
+
return result
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
def positions_from_logits(logits, config, device=None):
|
| 47 |
+
by_device = config.get("inference", {}).get("posterior_by_device")
|
| 48 |
+
if by_device is not None:
|
| 49 |
+
if device is None or device not in by_device:
|
| 50 |
+
raise ValueError("Configured head estimators require the device")
|
| 51 |
+
keys = config["device_keys"][device]
|
| 52 |
+
mapping = by_device[device]
|
| 53 |
+
if set(mapping) != set(keys) or logits.shape[1] != len(keys):
|
| 54 |
+
raise ValueError("Configured head estimators differ from output identities")
|
| 55 |
+
names = [mapping[key] for key in keys]
|
| 56 |
+
values = estimates(logits, sorted(set(names)))
|
| 57 |
+
return torch.stack(
|
| 58 |
+
[values[name][:, index] for index, name in enumerate(names)], dim=1
|
| 59 |
+
)
|
| 60 |
+
name = config.get("inference", {}).get("posterior", "mean")
|
| 61 |
+
if name not in ["mean", "median", "quadratic_mode"]:
|
| 62 |
+
raise ValueError("Unsupported configured posterior")
|
| 63 |
+
return estimates(logits, [name])[name]
|
src/inference/ensemble.py
ADDED
|
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Label-free mixed-resolution/context ensemble inference, one OCT decode pass."""
|
| 2 |
+
|
| 3 |
+
import json
|
| 4 |
+
import time
|
| 5 |
+
import numpy as np
|
| 6 |
+
import torch
|
| 7 |
+
from torch.nn import functional as F
|
| 8 |
+
from torch.utils.data import DataLoader
|
| 9 |
+
from src.models import build_model, output_indices
|
| 10 |
+
from src.inference.stream import OCTBatches
|
| 11 |
+
from src.inference.runtime import autocast_options
|
| 12 |
+
from src.inference.decoding import positions_from_logits
|
| 13 |
+
from src.inference.combination import finish_positions, combine_named_heads
|
| 14 |
+
from src.inference.writer import PredictionWriter
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
def stream_ensemble(
|
| 18 |
+
rows, root, checkpoint, output_dir, device, batch_size, workers, precision
|
| 19 |
+
):
|
| 20 |
+
config = checkpoint["config"]
|
| 21 |
+
members = []
|
| 22 |
+
for saved in checkpoint["members"]:
|
| 23 |
+
cfg = saved["config"]
|
| 24 |
+
model = build_model(cfg)
|
| 25 |
+
model.load_state_dict(saved["model"])
|
| 26 |
+
model.to(device).eval().requires_grad_(False)
|
| 27 |
+
members.append({"name": saved["name"], "config": cfg, "model": model})
|
| 28 |
+
if not members or len({m["name"] for m in members}) != len(members):
|
| 29 |
+
raise ValueError("Invalid ensemble members")
|
| 30 |
+
head_routes = config["combination"].get("head_source_by_device")
|
| 31 |
+
active_by_device = {}
|
| 32 |
+
if head_routes is not None:
|
| 33 |
+
if set(head_routes) != set(config["device_keys"]):
|
| 34 |
+
raise ValueError("Head-source device families differ")
|
| 35 |
+
available = {member["name"] for member in members}
|
| 36 |
+
for family, keys in config["device_keys"].items():
|
| 37 |
+
if set(head_routes[family]) != set(keys):
|
| 38 |
+
raise ValueError("Head-source anatomical identities differ")
|
| 39 |
+
active_by_device[family] = set(head_routes[family].values())
|
| 40 |
+
if not active_by_device[family] <= available:
|
| 41 |
+
raise ValueError("Unknown selected head source")
|
| 42 |
+
shapes = sorted(
|
| 43 |
+
{
|
| 44 |
+
(
|
| 45 |
+
m["config"]["height"],
|
| 46 |
+
m["config"]["width"],
|
| 47 |
+
m["config"].get("input_channels", 1),
|
| 48 |
+
)
|
| 49 |
+
for m in members
|
| 50 |
+
}
|
| 51 |
+
)
|
| 52 |
+
loader = DataLoader(
|
| 53 |
+
OCTBatches(rows, root, shapes, batch_size),
|
| 54 |
+
batch_size=None,
|
| 55 |
+
num_workers=workers,
|
| 56 |
+
pin_memory=device.startswith("cuda"),
|
| 57 |
+
**({"prefetch_factor": 2} if workers else {})
|
| 58 |
+
)
|
| 59 |
+
writer = PredictionWriter(output_dir, workers=2, maximum_pending_cases=2)
|
| 60 |
+
# PredictionWriter uses named subdirectories; final files belong at root.
|
| 61 |
+
pending = {}
|
| 62 |
+
done = 0
|
| 63 |
+
start = time.monotonic()
|
| 64 |
+
evaluated_frames = {}
|
| 65 |
+
for batch in loader:
|
| 66 |
+
index, offset = int(batch["index"]), int(batch["offset"])
|
| 67 |
+
b, h, a = map(int, batch["geometry"])
|
| 68 |
+
row = rows[index]
|
| 69 |
+
n = len(batch["images"][0])
|
| 70 |
+
keys = config["device_keys"][row["device"]]
|
| 71 |
+
if index not in pending:
|
| 72 |
+
buffers = []
|
| 73 |
+
for member in members:
|
| 74 |
+
if (
|
| 75 |
+
head_routes is not None
|
| 76 |
+
and member["name"] not in active_by_device[row["device"]]
|
| 77 |
+
):
|
| 78 |
+
continue
|
| 79 |
+
cfg = member["config"]
|
| 80 |
+
own_keys = cfg["device_keys"][row["device"]]
|
| 81 |
+
if set(own_keys) != set(keys) or len(own_keys) != len(keys):
|
| 82 |
+
raise ValueError("Ensemble boundary vocabulary differs")
|
| 83 |
+
shape = (cfg["height"], cfg["width"], cfg.get("input_channels", 1))
|
| 84 |
+
buffers.append(
|
| 85 |
+
{
|
| 86 |
+
"member": member,
|
| 87 |
+
"shape": shape,
|
| 88 |
+
"indices": output_indices(cfg, row["device"]),
|
| 89 |
+
"order": [own_keys.index(k) for k in keys],
|
| 90 |
+
"positions": np.empty((len(keys), b, a), np.float32),
|
| 91 |
+
}
|
| 92 |
+
)
|
| 93 |
+
pending[index] = {"seen": np.zeros(b, bool), "buffers": buffers}
|
| 94 |
+
state = pending[index]
|
| 95 |
+
if offset + n > b or state["seen"][offset : offset + n].any():
|
| 96 |
+
raise ValueError("Invalid frame coverage")
|
| 97 |
+
tensors = [image.to(device, non_blocking=True) for image in batch["images"]]
|
| 98 |
+
with torch.inference_mode(), torch.autocast(
|
| 99 |
+
**autocast_options(device, precision)
|
| 100 |
+
):
|
| 101 |
+
for buffer in state["buffers"]:
|
| 102 |
+
member = buffer["member"]
|
| 103 |
+
cfg = member["config"]
|
| 104 |
+
family_counts = evaluated_frames.setdefault(row["device"], {})
|
| 105 |
+
family_counts[member["name"]] = family_counts.get(member["name"], 0) + n
|
| 106 |
+
position = positions_from_logits(
|
| 107 |
+
member["model"](tensors[shapes.index(buffer["shape"])])[
|
| 108 |
+
:, buffer["indices"]
|
| 109 |
+
],
|
| 110 |
+
cfg,
|
| 111 |
+
row["device"],
|
| 112 |
+
)
|
| 113 |
+
position = F.interpolate(
|
| 114 |
+
position, size=a, mode="linear", align_corners=False
|
| 115 |
+
)
|
| 116 |
+
position = ((position + 0.5) * h / cfg["height"] - 0.5).clamp(0, h - 1)
|
| 117 |
+
values = position.float().cpu().numpy().transpose(1, 0, 2)
|
| 118 |
+
buffer["positions"][:, offset : offset + n] = values[buffer["order"]]
|
| 119 |
+
state["seen"][offset : offset + n] = True
|
| 120 |
+
if state["seen"].all():
|
| 121 |
+
combination = config["combination"]
|
| 122 |
+
components = [
|
| 123 |
+
finish_positions(
|
| 124 |
+
item["positions"],
|
| 125 |
+
row["device"],
|
| 126 |
+
h,
|
| 127 |
+
item["member"]["config"]
|
| 128 |
+
.get("inference", {})
|
| 129 |
+
.get("postprocess", {}),
|
| 130 |
+
)
|
| 131 |
+
for item in state["buffers"]
|
| 132 |
+
]
|
| 133 |
+
values = combine_named_heads(
|
| 134 |
+
components,
|
| 135 |
+
[item["member"]["name"] for item in state["buffers"]],
|
| 136 |
+
keys,
|
| 137 |
+
row["device"],
|
| 138 |
+
combination,
|
| 139 |
+
)
|
| 140 |
+
values = finish_positions(
|
| 141 |
+
values,
|
| 142 |
+
row["device"],
|
| 143 |
+
h,
|
| 144 |
+
config.get("inference", {}).get("postprocess", {}),
|
| 145 |
+
)
|
| 146 |
+
if not np.isfinite(values).all():
|
| 147 |
+
raise ValueError("Nonfinite ensemble output")
|
| 148 |
+
writer.submit(row["case_id"], [("", values, keys)])
|
| 149 |
+
del pending[index]
|
| 150 |
+
done += 1
|
| 151 |
+
if done % 10 == 0:
|
| 152 |
+
print(
|
| 153 |
+
json.dumps(
|
| 154 |
+
{
|
| 155 |
+
"completed_cases": done,
|
| 156 |
+
"elapsed_seconds": time.monotonic() - start,
|
| 157 |
+
}
|
| 158 |
+
),
|
| 159 |
+
flush=True,
|
| 160 |
+
)
|
| 161 |
+
writer.close()
|
| 162 |
+
if pending or done != len(rows):
|
| 163 |
+
raise ValueError("Incomplete ensemble input manifest")
|
| 164 |
+
summary = {
|
| 165 |
+
"completed_cases": done,
|
| 166 |
+
"members": len(members),
|
| 167 |
+
"elapsed_seconds": time.monotonic() - start,
|
| 168 |
+
"evaluated_member_frames_by_device": evaluated_frames,
|
| 169 |
+
"static_inactive_networks_skipped": head_routes is not None,
|
| 170 |
+
}
|
| 171 |
+
print(json.dumps(summary), flush=True)
|
| 172 |
+
return summary
|
src/inference/postprocess.py
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Prediction-only native-grid filters; no reference arrays or masks are inputs."""
|
| 2 |
+
|
| 3 |
+
import numpy as np
|
| 4 |
+
from scipy.ndimage import gaussian_filter, median_filter
|
| 5 |
+
|
| 6 |
+
INTEGER_DEVICES = ["topcon_maestro2", "topcon_triton", "zeiss_cirrus"]
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
def transform(positions, device, height, configuration):
|
| 10 |
+
if "by_device" in configuration:
|
| 11 |
+
overrides = configuration["by_device"].get(device, {})
|
| 12 |
+
configuration = {
|
| 13 |
+
**{k: v for k, v in configuration.items() if k != "by_device"},
|
| 14 |
+
**overrides,
|
| 15 |
+
}
|
| 16 |
+
values = np.asarray(positions, dtype=np.float32)
|
| 17 |
+
if "boundary_filters" in configuration:
|
| 18 |
+
rules = configuration["boundary_filters"]
|
| 19 |
+
if (
|
| 20 |
+
not isinstance(rules, list)
|
| 21 |
+
or len(rules) != values.shape[0]
|
| 22 |
+
or not all(isinstance(rule, dict) for rule in rules)
|
| 23 |
+
):
|
| 24 |
+
raise ValueError(
|
| 25 |
+
"One fixed filter configuration is required for every output boundary"
|
| 26 |
+
)
|
| 27 |
+
common = {
|
| 28 |
+
key: value
|
| 29 |
+
for key, value in configuration.items()
|
| 30 |
+
if key != "boundary_filters"
|
| 31 |
+
}
|
| 32 |
+
return np.concatenate(
|
| 33 |
+
[
|
| 34 |
+
transform(values[index : index + 1], device, height, {**common, **rule})
|
| 35 |
+
for index, rule in enumerate(rules)
|
| 36 |
+
],
|
| 37 |
+
axis=0,
|
| 38 |
+
)
|
| 39 |
+
kind = configuration.get("filter", "none")
|
| 40 |
+
if kind == "gaussian":
|
| 41 |
+
values = gaussian_filter(
|
| 42 |
+
values,
|
| 43 |
+
sigma=(
|
| 44 |
+
0,
|
| 45 |
+
float(configuration.get("sigma_b", 0)),
|
| 46 |
+
float(configuration.get("sigma_a", 0)),
|
| 47 |
+
),
|
| 48 |
+
mode="nearest",
|
| 49 |
+
truncate=3,
|
| 50 |
+
)
|
| 51 |
+
elif kind == "median":
|
| 52 |
+
values = median_filter(
|
| 53 |
+
values,
|
| 54 |
+
size=(
|
| 55 |
+
1,
|
| 56 |
+
int(configuration.get("size_b", 1)),
|
| 57 |
+
int(configuration.get("size_a", 1)),
|
| 58 |
+
),
|
| 59 |
+
mode="nearest",
|
| 60 |
+
)
|
| 61 |
+
elif kind != "none":
|
| 62 |
+
raise ValueError("Unknown prediction filter")
|
| 63 |
+
if device in configuration.get("round_devices", []):
|
| 64 |
+
values = np.rint(values)
|
| 65 |
+
return np.clip(values, 0, height - 1).astype(np.float32)
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
CONFIGURATIONS = {
|
| 69 |
+
"round_integer_devices": {"round_devices": INTEGER_DEVICES},
|
| 70 |
+
"gaussian_b05": {"filter": "gaussian", "sigma_b": 0.5},
|
| 71 |
+
"gaussian_b1": {"filter": "gaussian", "sigma_b": 1.0},
|
| 72 |
+
"median_b3": {"filter": "median", "size_b": 3},
|
| 73 |
+
"gaussian_b05_round": {
|
| 74 |
+
"filter": "gaussian",
|
| 75 |
+
"sigma_b": 0.5,
|
| 76 |
+
"round_devices": INTEGER_DEVICES,
|
| 77 |
+
},
|
| 78 |
+
"gaussian_b1_round": {
|
| 79 |
+
"filter": "gaussian",
|
| 80 |
+
"sigma_b": 1.0,
|
| 81 |
+
"round_devices": INTEGER_DEVICES,
|
| 82 |
+
},
|
| 83 |
+
"median_b3_round": {
|
| 84 |
+
"filter": "median",
|
| 85 |
+
"size_b": 3,
|
| 86 |
+
"round_devices": INTEGER_DEVICES,
|
| 87 |
+
},
|
| 88 |
+
}
|
src/inference/predict.py
ADDED
|
@@ -0,0 +1,182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Fresh-process, label-free OCT boundary inference. Network access is unnecessary."""
|
| 2 |
+
|
| 3 |
+
from pathlib import Path
|
| 4 |
+
import argparse
|
| 5 |
+
import json
|
| 6 |
+
import time
|
| 7 |
+
import numpy as np
|
| 8 |
+
import torch
|
| 9 |
+
from torch.nn import functional as F
|
| 10 |
+
from src.inference.decoding import positions_from_logits
|
| 11 |
+
from src.models import build_model, output_indices
|
| 12 |
+
from src.inference.runtime import configure_inference, autocast_options
|
| 13 |
+
from src.io import load_manifest, volume_headers
|
| 14 |
+
from src.inference.context import iter_normalized_contexts
|
| 15 |
+
from src.inference.combination import finish_positions
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
def predict_case(
|
| 19 |
+
row, data_root, model, config, device, batch_size=8, tta=False, precision="fp32"
|
| 20 |
+
):
|
| 21 |
+
headers, (b, h, a) = volume_headers(data_root, row["oct_paths"])
|
| 22 |
+
keys = config["device_keys"][row["device"]]
|
| 23 |
+
indices = output_indices(config, row["device"])
|
| 24 |
+
values = np.empty((len(keys), b, a), np.float32)
|
| 25 |
+
shape = (config["height"], config["width"])
|
| 26 |
+
batch = []
|
| 27 |
+
completed = 0
|
| 28 |
+
|
| 29 |
+
def consume(images):
|
| 30 |
+
nonlocal completed
|
| 31 |
+
x = torch.from_numpy(np.stack(images)).to(device)
|
| 32 |
+
with torch.inference_mode(), torch.autocast(
|
| 33 |
+
**autocast_options(device, precision)
|
| 34 |
+
):
|
| 35 |
+
pred = positions_from_logits(model(x)[:, indices], config, row["device"])
|
| 36 |
+
if tta:
|
| 37 |
+
pred = (
|
| 38 |
+
pred
|
| 39 |
+
+ positions_from_logits(
|
| 40 |
+
model(x.flip(-1))[:, indices], config, row["device"]
|
| 41 |
+
).flip(-1)
|
| 42 |
+
) * 0.5
|
| 43 |
+
pred = F.interpolate(pred, size=a, mode="linear", align_corners=False)
|
| 44 |
+
pred = (pred + 0.5) * h / shape[0] - 0.5
|
| 45 |
+
pred = pred.clamp(0, h - 1)
|
| 46 |
+
arr = pred.float().cpu().numpy().transpose(1, 0, 2)
|
| 47 |
+
values[:, completed : completed + len(images)] = arr
|
| 48 |
+
completed += len(images)
|
| 49 |
+
|
| 50 |
+
for images in iter_normalized_contexts(
|
| 51 |
+
headers, [(shape[0], shape[1], config.get("input_channels", 1))]
|
| 52 |
+
):
|
| 53 |
+
batch.append(images[0])
|
| 54 |
+
if len(batch) == batch_size:
|
| 55 |
+
consume(batch)
|
| 56 |
+
batch = []
|
| 57 |
+
if batch:
|
| 58 |
+
consume(batch)
|
| 59 |
+
if completed != b or not np.isfinite(values).all():
|
| 60 |
+
raise ValueError("Incomplete or nonfinite prediction")
|
| 61 |
+
return finish_positions(
|
| 62 |
+
values, row["device"], h, config.get("inference", {}).get("postprocess", {})
|
| 63 |
+
), np.asarray(keys)
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
def main():
|
| 67 |
+
ap = argparse.ArgumentParser()
|
| 68 |
+
ap.add_argument("--input-manifest", required=True)
|
| 69 |
+
ap.add_argument("--data-root", required=True)
|
| 70 |
+
ap.add_argument("--checkpoint", required=True)
|
| 71 |
+
ap.add_argument("--output-dir", required=True)
|
| 72 |
+
ap.add_argument("--batch-size", type=int, default=32)
|
| 73 |
+
ap.add_argument("--device", default="cuda" if torch.cuda.is_available() else "cpu")
|
| 74 |
+
ap.add_argument("--tta", action="store_true")
|
| 75 |
+
ap.add_argument("--workers", type=int, default=4)
|
| 76 |
+
ap.add_argument("--precision", choices=["fp32", "bf16", "tf32"], default=None)
|
| 77 |
+
ap.add_argument("--shard-index", type=int, default=0)
|
| 78 |
+
ap.add_argument("--num-shards", type=int, default=1)
|
| 79 |
+
args = ap.parse_args()
|
| 80 |
+
# Checkpoint contains model tensors and simple configuration; never labels,
|
| 81 |
+
# participant IDs, paths or a lookup table indexed by acquisition identifiers.
|
| 82 |
+
ck = torch.load(args.checkpoint, map_location="cpu", weights_only=True)
|
| 83 |
+
config = ck["config"]
|
| 84 |
+
args.precision = args.precision or config.get("inference", {}).get(
|
| 85 |
+
"precision", "fp32"
|
| 86 |
+
)
|
| 87 |
+
configure_inference(args.precision)
|
| 88 |
+
if config.get("architecture") == "BoundaryEnsemble":
|
| 89 |
+
from src.inference.ensemble import stream_ensemble
|
| 90 |
+
|
| 91 |
+
rows = [
|
| 92 |
+
{k: r[k] for k in ["case_id", "device", "oct_paths"]}
|
| 93 |
+
for r in load_manifest(args.input_manifest)
|
| 94 |
+
]
|
| 95 |
+
selected = [
|
| 96 |
+
r for i, r in enumerate(rows) if i % args.num_shards == args.shard_index
|
| 97 |
+
]
|
| 98 |
+
out = Path(args.output_dir)
|
| 99 |
+
out.mkdir(parents=True, exist_ok=True)
|
| 100 |
+
if args.tta:
|
| 101 |
+
raise ValueError("TTA must be explicitly validated before ensemble use")
|
| 102 |
+
stream_ensemble(
|
| 103 |
+
selected,
|
| 104 |
+
args.data_root,
|
| 105 |
+
ck,
|
| 106 |
+
out,
|
| 107 |
+
args.device,
|
| 108 |
+
args.batch_size,
|
| 109 |
+
args.workers,
|
| 110 |
+
args.precision,
|
| 111 |
+
)
|
| 112 |
+
return
|
| 113 |
+
model = build_model(config)
|
| 114 |
+
model.load_state_dict(ck["model"])
|
| 115 |
+
model.to(args.device).eval()
|
| 116 |
+
rows = load_manifest(args.input_manifest)
|
| 117 |
+
# Drop every field except the label-free contract, even if a caller passes more.
|
| 118 |
+
rows = [{k: r[k] for k in ["case_id", "device", "oct_paths"]} for r in rows]
|
| 119 |
+
out = Path(args.output_dir)
|
| 120 |
+
out.mkdir(parents=True, exist_ok=True)
|
| 121 |
+
t = time.monotonic()
|
| 122 |
+
count = 0
|
| 123 |
+
if args.workers:
|
| 124 |
+
from src.inference.stream import stream_predictions
|
| 125 |
+
|
| 126 |
+
selected = [
|
| 127 |
+
r for i, r in enumerate(rows) if i % args.num_shards == args.shard_index
|
| 128 |
+
]
|
| 129 |
+
stream_predictions(
|
| 130 |
+
selected,
|
| 131 |
+
args.data_root,
|
| 132 |
+
[{"model": model, "config": config, "destination": out}],
|
| 133 |
+
args.device,
|
| 134 |
+
args.batch_size,
|
| 135 |
+
args.workers,
|
| 136 |
+
args.tta,
|
| 137 |
+
args.precision,
|
| 138 |
+
)
|
| 139 |
+
return
|
| 140 |
+
for i, row in enumerate(rows):
|
| 141 |
+
if i % args.num_shards != args.shard_index:
|
| 142 |
+
continue
|
| 143 |
+
target = out / (row["case_id"] + ".npz")
|
| 144 |
+
positions, keys = predict_case(
|
| 145 |
+
row,
|
| 146 |
+
args.data_root,
|
| 147 |
+
model,
|
| 148 |
+
config,
|
| 149 |
+
args.device,
|
| 150 |
+
args.batch_size,
|
| 151 |
+
args.tta,
|
| 152 |
+
args.precision,
|
| 153 |
+
)
|
| 154 |
+
tmp = target.with_suffix(".tmp.npz")
|
| 155 |
+
np.savez_compressed(tmp, positions=positions, boundary_keys=keys)
|
| 156 |
+
tmp.replace(target)
|
| 157 |
+
count += 1
|
| 158 |
+
if count % 10 == 0:
|
| 159 |
+
print(
|
| 160 |
+
json.dumps(
|
| 161 |
+
{
|
| 162 |
+
"completed_cases": count,
|
| 163 |
+
"elapsed_seconds": time.monotonic() - t,
|
| 164 |
+
"shard": args.shard_index,
|
| 165 |
+
}
|
| 166 |
+
),
|
| 167 |
+
flush=True,
|
| 168 |
+
)
|
| 169 |
+
print(
|
| 170 |
+
json.dumps(
|
| 171 |
+
{
|
| 172 |
+
"completed_cases": count,
|
| 173 |
+
"elapsed_seconds": time.monotonic() - t,
|
| 174 |
+
"shard": args.shard_index,
|
| 175 |
+
}
|
| 176 |
+
),
|
| 177 |
+
flush=True,
|
| 178 |
+
)
|
| 179 |
+
|
| 180 |
+
|
| 181 |
+
if __name__ == "__main__":
|
| 182 |
+
main()
|
src/inference/runtime.py
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Explicit inference numerics, shared by single/multiple-checkpoint runners."""
|
| 2 |
+
|
| 3 |
+
import torch
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
def configure_inference(precision):
|
| 7 |
+
if precision not in ["fp32", "bf16", "tf32"]:
|
| 8 |
+
raise ValueError("Unknown inference precision")
|
| 9 |
+
torch.set_num_threads(4)
|
| 10 |
+
torch.backends.cudnn.benchmark = False
|
| 11 |
+
torch.backends.cudnn.deterministic = True
|
| 12 |
+
torch.backends.cudnn.allow_tf32 = precision == "tf32"
|
| 13 |
+
torch.backends.cuda.matmul.allow_tf32 = precision == "tf32"
|
| 14 |
+
torch.set_float32_matmul_precision("high" if precision == "tf32" else "highest")
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
def autocast_options(device, precision):
|
| 18 |
+
cuda = device.startswith("cuda")
|
| 19 |
+
enabled = cuda and precision == "bf16"
|
| 20 |
+
if enabled and not torch.cuda.is_bf16_supported():
|
| 21 |
+
raise ValueError("BF16 inference requested on an unsupported GPU")
|
| 22 |
+
return {
|
| 23 |
+
"device_type": "cuda" if cuda else "cpu",
|
| 24 |
+
"dtype": torch.bfloat16,
|
| 25 |
+
"enabled": enabled,
|
| 26 |
+
}
|
src/inference/stream.py
ADDED
|
@@ -0,0 +1,182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Bounded parallel, label-free OCT decoding for optional faster inference."""
|
| 2 |
+
|
| 3 |
+
from pathlib import Path
|
| 4 |
+
import json
|
| 5 |
+
import time
|
| 6 |
+
import numpy as np
|
| 7 |
+
import torch
|
| 8 |
+
from torch.nn import functional as F
|
| 9 |
+
from torch.utils.data import IterableDataset, DataLoader, get_worker_info
|
| 10 |
+
from src.inference.decoding import positions_from_logits
|
| 11 |
+
from src.inference.combination import finish_positions
|
| 12 |
+
from src.models import output_indices
|
| 13 |
+
from src.inference.runtime import autocast_options
|
| 14 |
+
from src.io import volume_headers
|
| 15 |
+
from src.inference.context import iter_normalized_contexts
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
class OCTBatches(IterableDataset):
|
| 19 |
+
def __init__(self, rows, root, shapes, batch_size):
|
| 20 |
+
self.rows, self.root = rows, root
|
| 21 |
+
self.shapes, self.batch_size = shapes, batch_size
|
| 22 |
+
|
| 23 |
+
def __iter__(self):
|
| 24 |
+
worker = get_worker_info()
|
| 25 |
+
worker_index, workers = (worker.id, worker.num_workers) if worker else (0, 1)
|
| 26 |
+
for index in range(worker_index, len(self.rows), workers):
|
| 27 |
+
row = self.rows[index]
|
| 28 |
+
headers, geometry = volume_headers(self.root, row["oct_paths"])
|
| 29 |
+
batches = [[] for _ in self.shapes]
|
| 30 |
+
completed = 0
|
| 31 |
+
|
| 32 |
+
def item():
|
| 33 |
+
nonlocal completed
|
| 34 |
+
n = len(batches[0])
|
| 35 |
+
if completed + n > geometry[0]:
|
| 36 |
+
raise ValueError(
|
| 37 |
+
"Decoded frames exceed declared structural geometry"
|
| 38 |
+
)
|
| 39 |
+
result = {
|
| 40 |
+
"index": index,
|
| 41 |
+
"offset": completed,
|
| 42 |
+
"geometry": geometry,
|
| 43 |
+
"images": [np.stack(batch) for batch in batches],
|
| 44 |
+
}
|
| 45 |
+
completed += n
|
| 46 |
+
for batch in batches:
|
| 47 |
+
batch.clear()
|
| 48 |
+
return result
|
| 49 |
+
|
| 50 |
+
for images in iter_normalized_contexts(headers, self.shapes):
|
| 51 |
+
for frame, batch in zip(images, batches):
|
| 52 |
+
batch.append(frame)
|
| 53 |
+
if len(batches[0]) == self.batch_size:
|
| 54 |
+
yield item()
|
| 55 |
+
if batches[0]:
|
| 56 |
+
yield item()
|
| 57 |
+
if completed != geometry[0]:
|
| 58 |
+
raise ValueError("Incomplete structural frame coverage")
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def stream_predictions(
|
| 62 |
+
rows, root, candidates, device, batch_size, workers, tta=False, precision="fp32"
|
| 63 |
+
):
|
| 64 |
+
"""Candidates contain loaded models/configs/destinations; no reference inputs."""
|
| 65 |
+
shapes = sorted(
|
| 66 |
+
{
|
| 67 |
+
(
|
| 68 |
+
c["config"]["height"],
|
| 69 |
+
c["config"]["width"],
|
| 70 |
+
c["config"].get("input_channels", 1),
|
| 71 |
+
)
|
| 72 |
+
for c in candidates
|
| 73 |
+
}
|
| 74 |
+
)
|
| 75 |
+
dataset = OCTBatches(rows, root, shapes, batch_size)
|
| 76 |
+
loader = DataLoader(
|
| 77 |
+
dataset,
|
| 78 |
+
batch_size=None,
|
| 79 |
+
num_workers=workers,
|
| 80 |
+
pin_memory=device.startswith("cuda"),
|
| 81 |
+
**({"prefetch_factor": 2} if workers else {})
|
| 82 |
+
)
|
| 83 |
+
pending, done = {}, 0
|
| 84 |
+
start = time.monotonic()
|
| 85 |
+
for batch in loader:
|
| 86 |
+
index, offset = int(batch["index"]), int(batch["offset"])
|
| 87 |
+
b, h, a = map(int, batch["geometry"])
|
| 88 |
+
row = rows[index]
|
| 89 |
+
n = len(batch["images"][0])
|
| 90 |
+
if index not in pending:
|
| 91 |
+
pending[index] = {"seen": np.zeros(b, bool), "buffers": []}
|
| 92 |
+
for candidate in candidates:
|
| 93 |
+
config = candidate["config"]
|
| 94 |
+
keys = config["device_keys"][row["device"]]
|
| 95 |
+
shape = (
|
| 96 |
+
config["height"],
|
| 97 |
+
config["width"],
|
| 98 |
+
config.get("input_channels", 1),
|
| 99 |
+
)
|
| 100 |
+
pending[index]["buffers"].append(
|
| 101 |
+
{
|
| 102 |
+
"candidate": candidate,
|
| 103 |
+
"shape_index": shapes.index(shape),
|
| 104 |
+
"height": shape[0],
|
| 105 |
+
"keys": keys,
|
| 106 |
+
"indices": output_indices(config, row["device"]),
|
| 107 |
+
"positions": np.empty((len(keys), b, a), np.float32),
|
| 108 |
+
}
|
| 109 |
+
)
|
| 110 |
+
state = pending[index]
|
| 111 |
+
if state["seen"][offset : offset + n].any() or offset + n > b:
|
| 112 |
+
raise ValueError("Duplicate or out-of-range structural frames")
|
| 113 |
+
tensors = [image.to(device, non_blocking=True) for image in batch["images"]]
|
| 114 |
+
with torch.inference_mode(), torch.autocast(
|
| 115 |
+
**autocast_options(device, precision)
|
| 116 |
+
):
|
| 117 |
+
for buffer in state["buffers"]:
|
| 118 |
+
x = tensors[buffer["shape_index"]]
|
| 119 |
+
model = buffer["candidate"]["model"]
|
| 120 |
+
pred = positions_from_logits(
|
| 121 |
+
model(x)[:, buffer["indices"]],
|
| 122 |
+
buffer["candidate"]["config"],
|
| 123 |
+
row["device"],
|
| 124 |
+
)
|
| 125 |
+
if tta:
|
| 126 |
+
pred = (
|
| 127 |
+
pred
|
| 128 |
+
+ positions_from_logits(
|
| 129 |
+
model(x.flip(-1))[:, buffer["indices"]],
|
| 130 |
+
buffer["candidate"]["config"],
|
| 131 |
+
row["device"],
|
| 132 |
+
).flip(-1)
|
| 133 |
+
) * 0.5
|
| 134 |
+
pred = F.interpolate(pred, size=a, mode="linear", align_corners=False)
|
| 135 |
+
pred = ((pred + 0.5) * h / buffer["height"] - 0.5).clamp(0, h - 1)
|
| 136 |
+
buffer["positions"][:, offset : offset + n] = (
|
| 137 |
+
pred.float().cpu().numpy().transpose(1, 0, 2)
|
| 138 |
+
)
|
| 139 |
+
state["seen"][offset : offset + n] = True
|
| 140 |
+
if state["seen"].all():
|
| 141 |
+
for buffer in state["buffers"]:
|
| 142 |
+
values = finish_positions(
|
| 143 |
+
buffer["positions"],
|
| 144 |
+
row["device"],
|
| 145 |
+
h,
|
| 146 |
+
buffer["candidate"]["config"]
|
| 147 |
+
.get("inference", {})
|
| 148 |
+
.get("postprocess", {}),
|
| 149 |
+
)
|
| 150 |
+
if not np.isfinite(values).all():
|
| 151 |
+
raise ValueError("Nonfinite candidate prediction")
|
| 152 |
+
destination = Path(buffer["candidate"]["destination"])
|
| 153 |
+
path = destination / (row["case_id"] + ".npz")
|
| 154 |
+
temporary = path.with_suffix(".tmp.npz")
|
| 155 |
+
np.savez_compressed(
|
| 156 |
+
temporary,
|
| 157 |
+
positions=values,
|
| 158 |
+
boundary_keys=np.asarray(buffer["keys"]),
|
| 159 |
+
)
|
| 160 |
+
temporary.replace(path)
|
| 161 |
+
del pending[index]
|
| 162 |
+
done += 1
|
| 163 |
+
if done % 10 == 0:
|
| 164 |
+
print(
|
| 165 |
+
json.dumps(
|
| 166 |
+
{
|
| 167 |
+
"completed_cases": done,
|
| 168 |
+
"elapsed_seconds": time.monotonic() - start,
|
| 169 |
+
"decode_workers": workers,
|
| 170 |
+
}
|
| 171 |
+
),
|
| 172 |
+
flush=True,
|
| 173 |
+
)
|
| 174 |
+
if pending or done != len(rows):
|
| 175 |
+
raise ValueError("Incomplete inference manifest coverage")
|
| 176 |
+
report = {
|
| 177 |
+
"completed_cases": done,
|
| 178 |
+
"elapsed_seconds": time.monotonic() - start,
|
| 179 |
+
"decode_workers": workers,
|
| 180 |
+
}
|
| 181 |
+
print(json.dumps(report), flush=True)
|
| 182 |
+
return report
|
src/inference/writer.py
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Bounded asynchronous NPZ serialization; values and dtypes are preserved."""
|
| 2 |
+
|
| 3 |
+
from collections import deque
|
| 4 |
+
from concurrent.futures import ThreadPoolExecutor
|
| 5 |
+
from pathlib import Path
|
| 6 |
+
import zipfile
|
| 7 |
+
import numpy as np
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
def save_npz(path, arrays, level=1):
|
| 11 |
+
path = Path(path)
|
| 12 |
+
temporary = path.with_suffix(".tmp.npz")
|
| 13 |
+
with zipfile.ZipFile(
|
| 14 |
+
temporary,
|
| 15 |
+
"w",
|
| 16 |
+
compression=zipfile.ZIP_DEFLATED,
|
| 17 |
+
compresslevel=level,
|
| 18 |
+
allowZip64=True,
|
| 19 |
+
) as archive:
|
| 20 |
+
for name, value in arrays.items():
|
| 21 |
+
with archive.open(name + ".npy", "w", force_zip64=True) as handle:
|
| 22 |
+
np.lib.format.write_array(handle, np.asarray(value), allow_pickle=False)
|
| 23 |
+
temporary.replace(path)
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
class PredictionWriter:
|
| 27 |
+
def __init__(self, output_dir, workers=2, maximum_pending_cases=2):
|
| 28 |
+
self.output_dir = Path(output_dir)
|
| 29 |
+
self.queue = deque()
|
| 30 |
+
self.maximum_pending_cases = maximum_pending_cases
|
| 31 |
+
self.executor = ThreadPoolExecutor(max_workers=workers)
|
| 32 |
+
|
| 33 |
+
def submit(self, case_id, items):
|
| 34 |
+
# Keep at most this many completed-volume arrays alive behind inference.
|
| 35 |
+
while len(self.queue) >= self.maximum_pending_cases:
|
| 36 |
+
self.queue.popleft().result()
|
| 37 |
+
|
| 38 |
+
def write_case():
|
| 39 |
+
for name, positions, keys in items:
|
| 40 |
+
save_npz(
|
| 41 |
+
self.output_dir / name / (case_id + ".npz"),
|
| 42 |
+
{"positions": positions, "boundary_keys": np.asarray(keys)},
|
| 43 |
+
)
|
| 44 |
+
|
| 45 |
+
self.queue.append(self.executor.submit(write_case))
|
| 46 |
+
|
| 47 |
+
def close(self):
|
| 48 |
+
try:
|
| 49 |
+
while self.queue:
|
| 50 |
+
self.queue.popleft().result()
|
| 51 |
+
finally:
|
| 52 |
+
self.executor.shutdown(wait=True, cancel_futures=True)
|
src/io.py
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Label-free structural OCT I/O; no segmentation dependency."""
|
| 2 |
+
from pathlib import Path
|
| 3 |
+
import json,re
|
| 4 |
+
import numpy as np
|
| 5 |
+
import pydicom
|
| 6 |
+
from pydicom.pixels import pixel_array,iter_pixels
|
| 7 |
+
from PIL import Image
|
| 8 |
+
|
| 9 |
+
def load_manifest(path):
|
| 10 |
+
rows=[json.loads(s) for s in Path(path).read_text().splitlines() if s.strip()]
|
| 11 |
+
seen=set()
|
| 12 |
+
for row in rows:
|
| 13 |
+
name=row['case_id']
|
| 14 |
+
if not isinstance(name,str) or not re.fullmatch(r'[A-Za-z0-9_-]{1,64}',name):raise ValueError('Unsafe case identifier')
|
| 15 |
+
if name in seen:raise ValueError('Duplicate case')
|
| 16 |
+
seen.add(name)
|
| 17 |
+
return rows
|
| 18 |
+
|
| 19 |
+
def safe_path(root,relative):
|
| 20 |
+
p=Path(relative)
|
| 21 |
+
if p.is_absolute() or '..' in p.parts:raise ValueError('Input path must be dataset-relative')
|
| 22 |
+
return Path(root)/p
|
| 23 |
+
|
| 24 |
+
def volume_headers(root,oct_paths,with_spacing=False):
|
| 25 |
+
tags=['SOPClassUID','Rows','Columns','NumberOfFrames','ConcatenationFrameOffsetNumber']
|
| 26 |
+
if with_spacing:tags+=['SharedFunctionalGroupsSequence','PerFrameFunctionalGroupsSequence']
|
| 27 |
+
# Inference asks for geometry, never participant identifiers or clinical tags.
|
| 28 |
+
headers=[(safe_path(root,p),pydicom.dcmread(safe_path(root,p),stop_before_pixels=True,specific_tags=tags)) for p in oct_paths]
|
| 29 |
+
headers.sort(key=lambda v:int(v[1].get('ConcatenationFrameOffsetNumber',0)))
|
| 30 |
+
offsets=[int(d.get('ConcatenationFrameOffsetNumber',0)) for p,d in headers]
|
| 31 |
+
n=0;h=int(headers[0][1].Rows);w=int(headers[0][1].Columns)
|
| 32 |
+
for off,(p,d) in zip(offsets,headers):
|
| 33 |
+
if off!=n:raise ValueError('Missing or overlapping concatenation frames')
|
| 34 |
+
if (int(d.Rows),int(d.Columns))!=(h,w):raise ValueError('Inconsistent structural geometry')
|
| 35 |
+
if str(d.SOPClassUID)!='1.2.840.10008.5.1.4.1.1.77.1.5.4':raise ValueError('Input is not structural OCT')
|
| 36 |
+
n+=int(d.get('NumberOfFrames',1))
|
| 37 |
+
return headers,(n,h,w)
|
| 38 |
+
|
| 39 |
+
def read_frame(headers,index):
|
| 40 |
+
for path,ds in headers:
|
| 41 |
+
off=int(ds.get('ConcatenationFrameOffsetNumber',0));n=int(ds.get('NumberOfFrames',1))
|
| 42 |
+
if off<=index<off+n:
|
| 43 |
+
plugin='pylibjpeg' if ds.file_meta.TransferSyntaxUID.is_compressed else ''
|
| 44 |
+
return pixel_array(path,index=index-off,decoding_plugin=plugin)
|
| 45 |
+
raise IndexError('Frame outside volume')
|
| 46 |
+
|
| 47 |
+
def read_frames(headers,indices):
|
| 48 |
+
"""Decode selected original frames with one file/decoder pass per source part."""
|
| 49 |
+
requested=[int(i) for i in indices];result={}
|
| 50 |
+
for path,ds in headers:
|
| 51 |
+
off=int(ds.get('ConcatenationFrameOffsetNumber',0));n=int(ds.get('NumberOfFrames',1))
|
| 52 |
+
local=[i-off for i in requested if off<=i<off+n]
|
| 53 |
+
if not local:continue
|
| 54 |
+
plugin='pylibjpeg' if ds.file_meta.TransferSyntaxUID.is_compressed else ''
|
| 55 |
+
for i,frame in zip(local,iter_pixels(path,indices=local,decoding_plugin=plugin)):
|
| 56 |
+
result[off+i]=frame
|
| 57 |
+
if set(result)!=set(requested):raise ValueError('Selected structural frame coverage is incomplete')
|
| 58 |
+
return result
|
| 59 |
+
|
| 60 |
+
def iter_volume_frames(headers):
|
| 61 |
+
for path,ds in headers:
|
| 62 |
+
plugin='pylibjpeg' if ds.file_meta.TransferSyntaxUID.is_compressed else ''
|
| 63 |
+
yield from iter_pixels(path,decoding_plugin=plugin)
|
| 64 |
+
|
| 65 |
+
def normalize_frame(image,shape):
|
| 66 |
+
"""Deterministic within-image percentiles; no cohort fitting or metadata features."""
|
| 67 |
+
image=np.asarray(image,dtype=np.float32)
|
| 68 |
+
finite=np.isfinite(image)
|
| 69 |
+
if not finite.any():return np.zeros(shape,dtype=np.float32)
|
| 70 |
+
lo,hi=np.quantile(image[finite],[.01,.995])
|
| 71 |
+
image=np.nan_to_num(image,nan=float(lo),posinf=float(hi),neginf=float(lo))
|
| 72 |
+
image=np.clip((image-lo)/max(float(hi-lo),1e-6),0,1)
|
| 73 |
+
# PIL float bilinear matches center-based coordinate conversion.
|
| 74 |
+
return np.asarray(Image.fromarray(image).resize((shape[1],shape[0]),Image.Resampling.BILINEAR),dtype=np.float32).copy()
|
src/models/__init__.py
ADDED
|
@@ -0,0 +1,174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Model construction and device-specific output selection.
|
| 2 |
+
|
| 3 |
+
Device is used only to select supervised/output heads. The convolutional network
|
| 4 |
+
receives OCT pixels, and its external boundary vocabulary stays anatomical.
|
| 5 |
+
Legacy checkpoints use one shared head per anatomical code.
|
| 6 |
+
"""
|
| 7 |
+
|
| 8 |
+
from src.models.unet import BoundaryNet
|
| 9 |
+
import torch
|
| 10 |
+
from torch.nn import functional as F
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
def output_indices(config, device):
|
| 14 |
+
keys = config["device_keys"][device]
|
| 15 |
+
if "device_output_indices" in config:
|
| 16 |
+
indices = config["device_output_indices"][device]
|
| 17 |
+
labels = config["model_head_keys"]
|
| 18 |
+
if len(indices) != len(keys) or len(set(indices)) != len(indices):
|
| 19 |
+
raise ValueError("Invalid device output index mapping")
|
| 20 |
+
if any(labels[i] != device + "::" + key for i, key in zip(indices, keys)):
|
| 21 |
+
raise ValueError("Device heads do not match the external vocabulary")
|
| 22 |
+
return indices
|
| 23 |
+
return [config["boundary_keys"].index(k) for k in keys]
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
def configure_heads(config, mode="shared"):
|
| 27 |
+
config["head_mode"] = mode
|
| 28 |
+
if mode == "device":
|
| 29 |
+
labels, indices = [], {}
|
| 30 |
+
for device, keys in sorted(config["device_keys"].items()):
|
| 31 |
+
indices[device] = list(range(len(labels), len(labels) + len(keys)))
|
| 32 |
+
labels.extend(device + "::" + key for key in keys)
|
| 33 |
+
config["model_head_keys"] = labels
|
| 34 |
+
config["device_output_indices"] = indices
|
| 35 |
+
elif mode != "shared":
|
| 36 |
+
raise ValueError("Unknown output head mode")
|
| 37 |
+
for device in config["device_keys"]:
|
| 38 |
+
output_indices(config, device)
|
| 39 |
+
return config
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
def build_model(config):
|
| 43 |
+
n = len(config.get("model_head_keys", config["boundary_keys"]))
|
| 44 |
+
if config.get("architecture") == "BoundaryNetWidePrior":
|
| 45 |
+
from src.models.wide import WideBoundaryNet
|
| 46 |
+
|
| 47 |
+
return WideBoundaryNet(n, config["base"], config["height"])
|
| 48 |
+
if config.get("architecture") == "BoundaryNetGlobalPrior":
|
| 49 |
+
from src.models.global_context import GlobalBoundaryNet
|
| 50 |
+
|
| 51 |
+
return GlobalBoundaryNet(n, config["base"], config["height"])
|
| 52 |
+
if config.get("architecture") == "BoundaryNetAuxiliaryPrior":
|
| 53 |
+
from src.models.auxiliary import AuxiliaryBoundaryNet
|
| 54 |
+
|
| 55 |
+
return AuxiliaryBoundaryNet(
|
| 56 |
+
n, config["base"], config["height"], len(config["auxiliary_region_names"])
|
| 57 |
+
)
|
| 58 |
+
if config.get("architecture") in ["BoundaryNetContext", "BoundaryNetContextPrior"]:
|
| 59 |
+
from src.models.context import ContextBoundaryNet
|
| 60 |
+
|
| 61 |
+
return ContextBoundaryNet(
|
| 62 |
+
n,
|
| 63 |
+
config["base"],
|
| 64 |
+
(
|
| 65 |
+
config["height"]
|
| 66 |
+
if config["architecture"] == "BoundaryNetContextPrior"
|
| 67 |
+
else None
|
| 68 |
+
),
|
| 69 |
+
)
|
| 70 |
+
if config.get("architecture") == "BoundaryNetAxialPrior":
|
| 71 |
+
from src.models.axial_prior import AxialPriorNet
|
| 72 |
+
|
| 73 |
+
return AxialPriorNet(n, config["base"], config["height"])
|
| 74 |
+
if config.get("architecture", "BoundaryNet") != "BoundaryNet":
|
| 75 |
+
raise ValueError("Unknown architecture")
|
| 76 |
+
return BoundaryNet(n, config["base"])
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
def remap_state(state, source_config, target_config):
|
| 80 |
+
"""Duplicate this researcher's shared trained heads for a device-head run.
|
| 81 |
+
|
| 82 |
+
Every backbone tensor is retained. No weights from external assets are used.
|
| 83 |
+
Returning a remapping flag lets training explicitly reset optimizer state.
|
| 84 |
+
"""
|
| 85 |
+
old = source_config.get("model_head_keys", source_config["boundary_keys"])
|
| 86 |
+
new = target_config.get("model_head_keys", target_config["boundary_keys"])
|
| 87 |
+
result = dict(state)
|
| 88 |
+
changed = False
|
| 89 |
+
indices = None
|
| 90 |
+
if old != new:
|
| 91 |
+
if "model_head_keys" in source_config or "model_head_keys" not in target_config:
|
| 92 |
+
raise ValueError(
|
| 93 |
+
"Only shared-to-device trained-head remapping is supported"
|
| 94 |
+
)
|
| 95 |
+
indices = [old.index(label.split("::", 1)[1]) for label in new]
|
| 96 |
+
for name in ["head.weight", "head.bias"]:
|
| 97 |
+
result[name] = state[name][indices].clone()
|
| 98 |
+
changed = True
|
| 99 |
+
target_prior = target_config.get("architecture") in [
|
| 100 |
+
"BoundaryNetAxialPrior",
|
| 101 |
+
"BoundaryNetContextPrior",
|
| 102 |
+
"BoundaryNetAuxiliaryPrior",
|
| 103 |
+
"BoundaryNetGlobalPrior",
|
| 104 |
+
"BoundaryNetWidePrior",
|
| 105 |
+
]
|
| 106 |
+
if target_prior:
|
| 107 |
+
if "axial_prior" not in state:
|
| 108 |
+
result["axial_prior"] = state["head.weight"].new_zeros(
|
| 109 |
+
1, len(new), target_config["height"], 1
|
| 110 |
+
)
|
| 111 |
+
changed = True
|
| 112 |
+
else:
|
| 113 |
+
prior = state["axial_prior"]
|
| 114 |
+
if indices is not None:
|
| 115 |
+
prior = prior[:, indices].clone()
|
| 116 |
+
if prior.shape[-2] != target_config["height"]:
|
| 117 |
+
prior = F.interpolate(
|
| 118 |
+
prior,
|
| 119 |
+
size=(target_config["height"], 1),
|
| 120 |
+
mode="bilinear",
|
| 121 |
+
align_corners=False,
|
| 122 |
+
)
|
| 123 |
+
changed = True
|
| 124 |
+
result["axial_prior"] = prior
|
| 125 |
+
elif "axial_prior" in state:
|
| 126 |
+
raise ValueError(
|
| 127 |
+
"Dropping a trained axial prior is not an implicit resume operation"
|
| 128 |
+
)
|
| 129 |
+
channels = (
|
| 130 |
+
3
|
| 131 |
+
if target_config.get("architecture")
|
| 132 |
+
in ["BoundaryNetGlobalPrior", "BoundaryNetWidePrior"]
|
| 133 |
+
else target_config.get("input_channels", 1)
|
| 134 |
+
)
|
| 135 |
+
weight = result["down.0.net.0.weight"]
|
| 136 |
+
if weight.shape[1] != channels:
|
| 137 |
+
if weight.shape[1] != 1 or channels != 3:
|
| 138 |
+
raise ValueError("Unsupported input-channel resume mapping")
|
| 139 |
+
result["down.0.net.0.weight"] = weight.repeat(1, 3, 1, 1) / 3
|
| 140 |
+
changed = True
|
| 141 |
+
if target_config.get("architecture") == "BoundaryNetAuxiliaryPrior":
|
| 142 |
+
regions = len(target_config["auxiliary_region_names"])
|
| 143 |
+
if "auxiliary_head.weight" not in state:
|
| 144 |
+
result["auxiliary_head.weight"] = state["head.weight"].new_zeros(
|
| 145 |
+
regions, target_config["base"], 1, 1
|
| 146 |
+
)
|
| 147 |
+
result["auxiliary_head.bias"] = state["head.weight"].new_zeros(regions)
|
| 148 |
+
changed = True
|
| 149 |
+
elif "auxiliary_head.weight" in state:
|
| 150 |
+
raise ValueError(
|
| 151 |
+
"Dropping an auxiliary head is not an implicit resume operation"
|
| 152 |
+
)
|
| 153 |
+
if target_config.get("architecture") == "BoundaryNetGlobalPrior":
|
| 154 |
+
with torch.random.fork_rng(devices=[]):
|
| 155 |
+
torch.manual_seed(target_config["global_context"]["initialization_seed"])
|
| 156 |
+
initial = build_model(target_config).state_dict()
|
| 157 |
+
for name, value in initial.items():
|
| 158 |
+
if (
|
| 159 |
+
name.startswith(("global_encoder.", "global_film."))
|
| 160 |
+
and name not in state
|
| 161 |
+
):
|
| 162 |
+
result[name] = value
|
| 163 |
+
changed = True
|
| 164 |
+
elif any(name.startswith(("global_encoder.", "global_film.")) for name in state):
|
| 165 |
+
raise ValueError("Dropping trained global context is not implicit")
|
| 166 |
+
if target_config.get("architecture") == "BoundaryNetWidePrior":
|
| 167 |
+
if "outer_conv.weight" not in state:
|
| 168 |
+
result["outer_conv.weight"] = state["head.weight"].new_zeros(
|
| 169 |
+
target_config["base"], 2, 3, 3
|
| 170 |
+
)
|
| 171 |
+
changed = True
|
| 172 |
+
elif "outer_conv.weight" in state:
|
| 173 |
+
raise ValueError("Dropping trained distant-view inputs is not implicit")
|
| 174 |
+
return result, changed
|
src/models/auxiliary.py
ADDED
|
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Optional training-only ordinal interval supervision from coded boundaries.
|
| 2 |
+
|
| 3 |
+
The boundary objective keeps every original valid source target. Auxiliary
|
| 4 |
+
intervals are defined only in columns whose necessary boundaries are valid and
|
| 5 |
+
ordered. This auxiliary support is never used by reference conversion/scoring.
|
| 6 |
+
"""
|
| 7 |
+
|
| 8 |
+
import torch
|
| 9 |
+
from torch import nn
|
| 10 |
+
from torch.nn import functional as F
|
| 11 |
+
from src.models.unet import BoundaryNet
|
| 12 |
+
|
| 13 |
+
ORDERS = {
|
| 14 |
+
"heidelberg_spectralis": [
|
| 15 |
+
"SCT_280677004",
|
| 16 |
+
"DCM_128289",
|
| 17 |
+
"DCM_128290",
|
| 18 |
+
"DCM_128291",
|
| 19 |
+
"DCM_128292",
|
| 20 |
+
"DCM_128293",
|
| 21 |
+
"SCT_76710003",
|
| 22 |
+
"DCM_128321",
|
| 23 |
+
"DCM_128323",
|
| 24 |
+
"DCM_128297",
|
| 25 |
+
"DCM_128300",
|
| 26 |
+
],
|
| 27 |
+
"topcon_maestro2": [
|
| 28 |
+
"SCT_280677004",
|
| 29 |
+
"DCM_128289",
|
| 30 |
+
"DCM_128290",
|
| 31 |
+
"DCM_128291",
|
| 32 |
+
"DCM_128293",
|
| 33 |
+
"SCT_76710003",
|
| 34 |
+
"DCM_128320",
|
| 35 |
+
"DCM_128297",
|
| 36 |
+
"DCM_128299",
|
| 37 |
+
],
|
| 38 |
+
"topcon_triton": [
|
| 39 |
+
"SCT_280677004",
|
| 40 |
+
"DCM_128289",
|
| 41 |
+
"DCM_128290",
|
| 42 |
+
"DCM_128291",
|
| 43 |
+
"DCM_128293",
|
| 44 |
+
"SCT_76710003",
|
| 45 |
+
"DCM_128320",
|
| 46 |
+
"DCM_128297",
|
| 47 |
+
"DCM_128299",
|
| 48 |
+
"DCM_128301",
|
| 49 |
+
],
|
| 50 |
+
"zeiss_cirrus": ["SCT_280677004", "DCM_128298"],
|
| 51 |
+
}
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
def configure_auxiliary(config):
|
| 55 |
+
from src.models import output_indices
|
| 56 |
+
|
| 57 |
+
if config.get("input_channels", 1) != 1 or config.get("head_mode") != "device":
|
| 58 |
+
raise ValueError(
|
| 59 |
+
"This auxiliary experiment requires single-channel device heads"
|
| 60 |
+
)
|
| 61 |
+
mapping = {}
|
| 62 |
+
names = []
|
| 63 |
+
for device, keys in sorted(config["device_keys"].items()):
|
| 64 |
+
order = ORDERS[device]
|
| 65 |
+
if set(keys) != set(order):
|
| 66 |
+
raise ValueError("Unreviewed auxiliary boundary vocabulary")
|
| 67 |
+
indices = output_indices(config, device)
|
| 68 |
+
ordered = [indices[keys.index(key)] for key in order]
|
| 69 |
+
regions = list(range(len(names), len(names) + len(order) + 1))
|
| 70 |
+
intervals = (
|
| 71 |
+
["above_" + order[0]]
|
| 72 |
+
+ [a + "__to__" + b for a, b in zip(order[:-1], order[1:])]
|
| 73 |
+
+ ["below_" + order[-1]]
|
| 74 |
+
)
|
| 75 |
+
names.extend(device + "::" + interval for interval in intervals)
|
| 76 |
+
mapping[device] = {"boundary_indices": ordered, "region_indices": regions}
|
| 77 |
+
config["auxiliary_mapping"] = mapping
|
| 78 |
+
config["auxiliary_region_names"] = names
|
| 79 |
+
return config
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
class AuxiliaryBoundaryNet(BoundaryNet):
|
| 83 |
+
def __init__(self, n_boundaries, base, height, n_regions):
|
| 84 |
+
super().__init__(n_boundaries, base)
|
| 85 |
+
self.axial_prior = nn.Parameter(torch.zeros(1, n_boundaries, height, 1))
|
| 86 |
+
self.auxiliary_head = nn.Conv2d(base, n_regions, 1)
|
| 87 |
+
nn.init.zeros_(self.auxiliary_head.weight)
|
| 88 |
+
nn.init.zeros_(self.auxiliary_head.bias)
|
| 89 |
+
|
| 90 |
+
def forward(self, image, return_aux=False):
|
| 91 |
+
x = image
|
| 92 |
+
skips = []
|
| 93 |
+
for index, layer in enumerate(self.down):
|
| 94 |
+
if index:
|
| 95 |
+
x = F.avg_pool2d(x, 2)
|
| 96 |
+
x = layer(x)
|
| 97 |
+
skips.append(x)
|
| 98 |
+
for index, layer in enumerate(self.up):
|
| 99 |
+
skip = skips[-2 - index]
|
| 100 |
+
x = F.interpolate(
|
| 101 |
+
x, size=skip.shape[-2:], mode="bilinear", align_corners=False
|
| 102 |
+
)
|
| 103 |
+
x = layer(torch.cat([x, skip], 1))
|
| 104 |
+
prior = self.axial_prior
|
| 105 |
+
if prior.shape[-2] != x.shape[-2]:
|
| 106 |
+
prior = F.interpolate(
|
| 107 |
+
prior, size=(x.shape[-2], 1), mode="bilinear", align_corners=False
|
| 108 |
+
)
|
| 109 |
+
boundary = self.head(x) + prior
|
| 110 |
+
return (boundary, self.auxiliary_head(x)) if return_aux else boundary
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
def interval_targets(positions, valid, height):
|
| 114 |
+
"""Integer ordinal interval labels plus an independent auxiliary-column mask."""
|
| 115 |
+
support = valid.all(1) & (positions[:, 1:] >= positions[:, :-1]).all(1)
|
| 116 |
+
rows = torch.arange(height, device=positions.device, dtype=positions.dtype)[
|
| 117 |
+
None, None, :, None
|
| 118 |
+
]
|
| 119 |
+
target = (rows >= positions[:, :, None, :]).sum(1)
|
| 120 |
+
return target, support
|
| 121 |
+
|
| 122 |
+
|
| 123 |
+
def auxiliary_loss(logits, positions, valid, config):
|
| 124 |
+
n, _, height, width = logits.shape
|
| 125 |
+
per_image = logits.float().flatten(1).sum(1) * 0
|
| 126 |
+
for mapping in config["auxiliary_mapping"].values():
|
| 127 |
+
indices = mapping["boundary_indices"]
|
| 128 |
+
regions = mapping["region_indices"]
|
| 129 |
+
target, columns = interval_targets(
|
| 130 |
+
positions[:, indices], valid[:, indices], height
|
| 131 |
+
)
|
| 132 |
+
support = columns[:, None, :].expand(-1, height, -1).float()
|
| 133 |
+
ce = F.cross_entropy(logits[:, regions].float(), target, reduction="none")
|
| 134 |
+
count = logits.new_zeros((n, len(regions)), dtype=torch.float32)
|
| 135 |
+
count.scatter_add_(1, target.flatten(1), support.flatten(1))
|
| 136 |
+
denominator = (
|
| 137 |
+
count.gather(1, target.flatten(1)).reshape(n, height, width).clamp_min(1)
|
| 138 |
+
)
|
| 139 |
+
per_image = per_image + (ce * support / denominator).sum((1, 2)) / (
|
| 140 |
+
count > 0
|
| 141 |
+
).sum(1).clamp_min(1)
|
| 142 |
+
return per_image.mean()
|
src/models/axial_prior.py
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Image-only boundary network with a learned, zero-initialized axial logit bias.
|
| 2 |
+
|
| 3 |
+
The spatial parameters are trained jointly with the CNN on training targets. No
|
| 4 |
+
segmentation or acquisition identifier is an inference input. Device-specific
|
| 5 |
+
output selection is unchanged. A zero bias preserves the parent model exactly.
|
| 6 |
+
"""
|
| 7 |
+
|
| 8 |
+
import torch
|
| 9 |
+
from torch import nn
|
| 10 |
+
from torch.nn import functional as F
|
| 11 |
+
from src.models.unet import BoundaryNet
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
class AxialPriorNet(BoundaryNet):
|
| 15 |
+
def __init__(self, n_boundaries, base, height):
|
| 16 |
+
super().__init__(n_boundaries, base)
|
| 17 |
+
self.axial_prior = nn.Parameter(torch.zeros(1, n_boundaries, height, 1))
|
| 18 |
+
|
| 19 |
+
def forward(self, image):
|
| 20 |
+
logits = super().forward(image)
|
| 21 |
+
prior = self.axial_prior
|
| 22 |
+
if prior.shape[-2] != logits.shape[-2]:
|
| 23 |
+
prior = F.interpolate(
|
| 24 |
+
prior, size=(logits.shape[-2], 1), mode="bilinear", align_corners=False
|
| 25 |
+
)
|
| 26 |
+
return logits + prior
|
src/models/context.py
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Three adjacent OCT B-scans as image channels, with center-frame outputs."""
|
| 2 |
+
|
| 3 |
+
import torch
|
| 4 |
+
from torch import nn
|
| 5 |
+
from torch.nn import functional as F
|
| 6 |
+
from src.models.unet import BoundaryNet, Block
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
class ContextBoundaryNet(BoundaryNet):
|
| 10 |
+
def __init__(self, n_boundaries, base, prior_height=None):
|
| 11 |
+
super().__init__(n_boundaries, base)
|
| 12 |
+
self.down[0] = Block(3, base)
|
| 13 |
+
if prior_height is None:
|
| 14 |
+
self.register_parameter("axial_prior", None)
|
| 15 |
+
else:
|
| 16 |
+
self.axial_prior = nn.Parameter(
|
| 17 |
+
torch.zeros(1, n_boundaries, prior_height, 1)
|
| 18 |
+
)
|
| 19 |
+
|
| 20 |
+
def forward(self, image):
|
| 21 |
+
logits = super().forward(image)
|
| 22 |
+
if self.axial_prior is None:
|
| 23 |
+
return logits
|
| 24 |
+
prior = self.axial_prior
|
| 25 |
+
if prior.shape[-2] != logits.shape[-2]:
|
| 26 |
+
prior = F.interpolate(
|
| 27 |
+
prior, size=(logits.shape[-2], 1), mode="bilinear", align_corners=False
|
| 28 |
+
)
|
| 29 |
+
return logits + prior
|
src/models/global_context.py
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Local adjacent slices conditioned on three whole-volume OCT views."""
|
| 2 |
+
|
| 3 |
+
import torch
|
| 4 |
+
from torch import nn
|
| 5 |
+
from torch.nn import functional as F
|
| 6 |
+
from src.models.context import ContextBoundaryNet
|
| 7 |
+
from src.models.unet import Block
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
class GlobalBoundaryNet(ContextBoundaryNet):
|
| 11 |
+
def __init__(self, n_boundaries, base, prior_height):
|
| 12 |
+
super().__init__(n_boundaries, base, prior_height)
|
| 13 |
+
self.global_encoder = nn.Sequential(
|
| 14 |
+
nn.Conv2d(3, base, 5, stride=2, padding=2, bias=False),
|
| 15 |
+
nn.GroupNorm(min(8, base), base),
|
| 16 |
+
nn.SiLU(),
|
| 17 |
+
Block(base, base * 2),
|
| 18 |
+
nn.AvgPool2d(2),
|
| 19 |
+
Block(base * 2, base * 4),
|
| 20 |
+
nn.AdaptiveAvgPool2d(1),
|
| 21 |
+
nn.Flatten(),
|
| 22 |
+
)
|
| 23 |
+
self.global_film = nn.Linear(base * 4, base * 12 * 2)
|
| 24 |
+
nn.init.zeros_(self.global_film.weight)
|
| 25 |
+
nn.init.zeros_(self.global_film.bias)
|
| 26 |
+
|
| 27 |
+
def forward(self, image):
|
| 28 |
+
if image.shape[1] != 6:
|
| 29 |
+
raise ValueError("Expected local3 plus global3 OCT channels")
|
| 30 |
+
global_image = F.interpolate(
|
| 31 |
+
image[:, 3:], size=(96, 128), mode="bilinear", align_corners=False
|
| 32 |
+
)
|
| 33 |
+
embedding = self.global_encoder(global_image)
|
| 34 |
+
scale, bias = self.global_film(embedding).chunk(2, dim=1)
|
| 35 |
+
x = image[:, :3].contiguous()
|
| 36 |
+
skips = []
|
| 37 |
+
for index, layer in enumerate(self.down):
|
| 38 |
+
if index:
|
| 39 |
+
x = F.avg_pool2d(x, 2)
|
| 40 |
+
x = layer(x)
|
| 41 |
+
if index == len(self.down) - 1:
|
| 42 |
+
x = x * (1 + scale[:, :, None, None]) + bias[:, :, None, None]
|
| 43 |
+
skips.append(x)
|
| 44 |
+
for index, layer in enumerate(self.up):
|
| 45 |
+
skip = skips[-2 - index]
|
| 46 |
+
x = F.interpolate(
|
| 47 |
+
x, size=skip.shape[-2:], mode="bilinear", align_corners=False
|
| 48 |
+
)
|
| 49 |
+
x = layer(torch.cat([x, skip], 1))
|
| 50 |
+
logits = self.head(x)
|
| 51 |
+
prior = self.axial_prior
|
| 52 |
+
if prior.shape[-2] != logits.shape[-2]:
|
| 53 |
+
prior = F.interpolate(
|
| 54 |
+
prior, size=(logits.shape[-2], 1), mode="bilinear", align_corners=False
|
| 55 |
+
)
|
| 56 |
+
return logits + prior
|
src/models/unet.py
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Randomly initialized U-Net with per-boundary axial distributions."""
|
| 2 |
+
|
| 3 |
+
import torch
|
| 4 |
+
from torch import nn
|
| 5 |
+
from torch.nn import functional as F
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
class Block(nn.Module):
|
| 9 |
+
def __init__(self, a, b):
|
| 10 |
+
super().__init__()
|
| 11 |
+
g = min(8, b)
|
| 12 |
+
self.net = nn.Sequential(
|
| 13 |
+
nn.Conv2d(a, b, 3, padding=1, bias=False),
|
| 14 |
+
nn.GroupNorm(g, b),
|
| 15 |
+
nn.SiLU(),
|
| 16 |
+
nn.Conv2d(b, b, 3, padding=1, bias=False),
|
| 17 |
+
nn.GroupNorm(g, b),
|
| 18 |
+
nn.SiLU(),
|
| 19 |
+
)
|
| 20 |
+
|
| 21 |
+
def forward(self, x):
|
| 22 |
+
return self.net(x)
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
class BoundaryNet(nn.Module):
|
| 26 |
+
def __init__(self, n_boundaries, base=24):
|
| 27 |
+
super().__init__()
|
| 28 |
+
c = [base, base * 2, base * 4, base * 8, base * 12]
|
| 29 |
+
self.down = nn.ModuleList(
|
| 30 |
+
[Block(1, c[0])] + [Block(c[i - 1], c[i]) for i in range(1, 5)]
|
| 31 |
+
)
|
| 32 |
+
self.up = nn.ModuleList(
|
| 33 |
+
[Block(c[i] + c[i - 1], c[i - 1]) for i in range(4, 0, -1)]
|
| 34 |
+
)
|
| 35 |
+
self.head = nn.Conv2d(c[0], n_boundaries, 1)
|
| 36 |
+
|
| 37 |
+
def forward(self, x):
|
| 38 |
+
skips = []
|
| 39 |
+
for i, layer in enumerate(self.down):
|
| 40 |
+
if i:
|
| 41 |
+
x = F.avg_pool2d(x, 2)
|
| 42 |
+
x = layer(x)
|
| 43 |
+
skips.append(x)
|
| 44 |
+
for i, layer in enumerate(self.up):
|
| 45 |
+
skip = skips[-2 - i]
|
| 46 |
+
x = F.interpolate(
|
| 47 |
+
x, size=skip.shape[-2:], mode="bilinear", align_corners=False
|
| 48 |
+
)
|
| 49 |
+
x = layer(torch.cat([x, skip], 1))
|
| 50 |
+
return self.head(x)
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
def expected_positions(logits):
|
| 54 |
+
p = logits.float().softmax(dim=-2)
|
| 55 |
+
y = torch.arange(logits.shape[-2], device=logits.device, dtype=torch.float32)
|
| 56 |
+
return (p * y[None, None, :, None]).sum(-2)
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def boundary_loss(
|
| 60 |
+
logits,
|
| 61 |
+
positions,
|
| 62 |
+
valid,
|
| 63 |
+
sigma=1.5,
|
| 64 |
+
regression_weight=0.1,
|
| 65 |
+
coordinate_scale=None,
|
| 66 |
+
regression_loss="smooth_l1",
|
| 67 |
+
active_head_packing=False,
|
| 68 |
+
):
|
| 69 |
+
"""Gaussian cross entropy plus a configured native-scaled position penalty."""
|
| 70 |
+
if active_head_packing:
|
| 71 |
+
n, k, h, w = logits.shape
|
| 72 |
+
support = valid.any(-1)
|
| 73 |
+
count = max(1, int(support.sum(-1).max().item()))
|
| 74 |
+
index = (
|
| 75 |
+
torch.arange(k, device=logits.device)[None]
|
| 76 |
+
.expand(n, -1)
|
| 77 |
+
.masked_fill(~support, k)
|
| 78 |
+
.sort(-1)
|
| 79 |
+
.values[:, :count]
|
| 80 |
+
)
|
| 81 |
+
keep = index < k
|
| 82 |
+
index = index.clamp_max(k - 1)
|
| 83 |
+
logits = logits.gather(1, index[:, :, None, None].expand(-1, -1, h, w))
|
| 84 |
+
positions = positions.gather(1, index[:, :, None].expand(-1, -1, w))
|
| 85 |
+
valid = valid.gather(1, index[:, :, None].expand(-1, -1, w)) & keep[:, :, None]
|
| 86 |
+
h = logits.shape[-2]
|
| 87 |
+
rows = torch.arange(h, device=logits.device, dtype=torch.float32)[
|
| 88 |
+
None, None, :, None
|
| 89 |
+
]
|
| 90 |
+
target = torch.exp(-0.5 * ((rows - positions[:, :, None, :]) / sigma) ** 2)
|
| 91 |
+
target = target / target.sum(-2, keepdim=True).clamp_min(1e-8)
|
| 92 |
+
ce = -(target * logits.float().log_softmax(-2)).sum(-2)
|
| 93 |
+
if regression_loss == "smooth_l1":
|
| 94 |
+
reg = F.smooth_l1_loss(
|
| 95 |
+
expected_positions(logits), positions, reduction="none", beta=2
|
| 96 |
+
)
|
| 97 |
+
elif regression_loss == "l1":
|
| 98 |
+
reg = (expected_positions(logits) - positions).abs()
|
| 99 |
+
elif regression_loss == "expected_l1":
|
| 100 |
+
reg = (
|
| 101 |
+
logits.float().softmax(-2) * (rows - positions[:, :, None, :]).abs()
|
| 102 |
+
).sum(-2)
|
| 103 |
+
else:
|
| 104 |
+
raise ValueError("Unknown position regression loss")
|
| 105 |
+
if coordinate_scale is not None:
|
| 106 |
+
reg = reg * coordinate_scale[:, None, None]
|
| 107 |
+
m = valid.float()
|
| 108 |
+
count = m.sum(-1)
|
| 109 |
+
loss = ((ce + regression_weight * reg) * m).sum(-1) / count.clamp_min(1)
|
| 110 |
+
included = count > 0
|
| 111 |
+
per_image = (loss * included).sum(1) / included.sum(1).clamp_min(1)
|
| 112 |
+
return per_image.mean()
|
src/models/wide.py
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Own C3 body plus zero-initialized distant OCT inputs; no metadata features."""
|
| 2 |
+
|
| 3 |
+
import torch
|
| 4 |
+
from torch import nn
|
| 5 |
+
from torch.nn import functional as F
|
| 6 |
+
from src.models.context import ContextBoundaryNet
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
class WideBoundaryNet(ContextBoundaryNet):
|
| 10 |
+
def __init__(self, n_boundaries, base, prior_height):
|
| 11 |
+
super().__init__(n_boundaries, base, prior_height)
|
| 12 |
+
self.outer_conv = nn.Conv2d(2, base, 3, padding=1, bias=False)
|
| 13 |
+
nn.init.zeros_(self.outer_conv.weight)
|
| 14 |
+
|
| 15 |
+
def forward(self, image):
|
| 16 |
+
if image.ndim != 4 or image.shape[1] != 5:
|
| 17 |
+
raise ValueError("Five OCT input views required")
|
| 18 |
+
local = image[:, 1:4].contiguous()
|
| 19 |
+
outer = image[:, [0, 4]].contiguous()
|
| 20 |
+
first = self.down[0].net
|
| 21 |
+
x = first[0](local) + self.outer_conv(outer)
|
| 22 |
+
for layer in list(first)[1:]:
|
| 23 |
+
x = layer(x)
|
| 24 |
+
skips = [x]
|
| 25 |
+
for layer in self.down[1:]:
|
| 26 |
+
x = layer(F.avg_pool2d(x, 2))
|
| 27 |
+
skips.append(x)
|
| 28 |
+
for index, layer in enumerate(self.up):
|
| 29 |
+
skip = skips[-2 - index]
|
| 30 |
+
x = F.interpolate(
|
| 31 |
+
x, size=skip.shape[-2:], mode="bilinear", align_corners=False
|
| 32 |
+
)
|
| 33 |
+
x = layer(torch.cat([x, skip], 1))
|
| 34 |
+
logits = self.head(x)
|
| 35 |
+
prior = self.axial_prior
|
| 36 |
+
if prior.shape[-2] != logits.shape[-2]:
|
| 37 |
+
prior = F.interpolate(
|
| 38 |
+
prior, size=(logits.shape[-2], 1), mode="bilinear", align_corners=False
|
| 39 |
+
)
|
| 40 |
+
return logits + prior
|
src/paths.py
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Project paths shared by commands and the local viewer."""
|
| 2 |
+
|
| 3 |
+
from pathlib import Path
|
| 4 |
+
|
| 5 |
+
PROJECT_ROOT = Path(__file__).resolve().parents[1]
|
src/protocol.py
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Public split and canonical-boundary checks; does not decode or pair DICOMs."""
|
| 2 |
+
from __future__ import annotations
|
| 3 |
+
|
| 4 |
+
import argparse
|
| 5 |
+
from collections import defaultdict
|
| 6 |
+
import hashlib
|
| 7 |
+
import json
|
| 8 |
+
from pathlib import Path, PurePosixPath
|
| 9 |
+
import re
|
| 10 |
+
from statistics import fmean
|
| 11 |
+
|
| 12 |
+
DEVICES = {'heidelberg_spectralis', 'topcon_maestro2', 'topcon_triton', 'zeiss_cirrus'}
|
| 13 |
+
SEED = 20261105
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
def digest(path):
|
| 17 |
+
return hashlib.sha256(Path(path).read_bytes()).hexdigest()
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
def relative_path(value):
|
| 21 |
+
if not isinstance(value, str) or not value or '\\' in value or '\x00' in value or re.match(r'^[A-Za-z]:', value):
|
| 22 |
+
raise ValueError('Dataset paths must be relative POSIX paths')
|
| 23 |
+
path = PurePosixPath(value)
|
| 24 |
+
if path.is_absolute() or '..' in path.parts or value == '.':
|
| 25 |
+
raise ValueError('Dataset paths must stay beneath the supplied data root')
|
| 26 |
+
return value
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
def load_pairs(path):
|
| 30 |
+
rows, identities, inputs = [], set(), set()
|
| 31 |
+
for line in Path(path).read_text().splitlines():
|
| 32 |
+
if not line.strip():
|
| 33 |
+
continue
|
| 34 |
+
row = json.loads(line)
|
| 35 |
+
if not isinstance(row, dict):
|
| 36 |
+
raise ValueError('Manifest rows must be objects')
|
| 37 |
+
name = row.get('case_id')
|
| 38 |
+
if not isinstance(name, str) or not re.fullmatch(r'[A-Za-z0-9_-]{1,64}', name) or name in identities:
|
| 39 |
+
raise ValueError('Case IDs must be unique safe filename stems')
|
| 40 |
+
if (not isinstance(row.get('participant_id'), str) or not row['participant_id'].strip()
|
| 41 |
+
or row['participant_id'] != row['participant_id'].strip()):
|
| 42 |
+
raise ValueError('Each case needs a nonempty participant identity')
|
| 43 |
+
if row.get('device') not in DEVICES:
|
| 44 |
+
raise ValueError('Device family must match the declared AI-READI cohort')
|
| 45 |
+
for field in ('oct_paths', 'segmentation_paths'):
|
| 46 |
+
values = row.get(field)
|
| 47 |
+
if not isinstance(values, list) or not values:
|
| 48 |
+
raise ValueError('Each case needs structural input and segmentation paths')
|
| 49 |
+
checked = [relative_path(item) for item in values]
|
| 50 |
+
if len(set(checked)) != len(checked):
|
| 51 |
+
raise ValueError('Duplicate paths within a case')
|
| 52 |
+
if inputs.intersection(row['oct_paths']):
|
| 53 |
+
raise ValueError('A structural input cannot be duplicated across cases')
|
| 54 |
+
inputs.update(row['oct_paths'])
|
| 55 |
+
identities.add(name)
|
| 56 |
+
rows.append(row)
|
| 57 |
+
if not rows:
|
| 58 |
+
raise ValueError('The manifest is empty')
|
| 59 |
+
return rows
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
def split_for(participant):
|
| 63 |
+
# Integer buckets avoid floating-point or Python-hash dependence.
|
| 64 |
+
key = f'aireadi-oct-v1:{SEED}:{participant}'.encode('utf-8')
|
| 65 |
+
bucket = int.from_bytes(hashlib.sha256(key).digest(), 'big') % 100
|
| 66 |
+
return 'train' if bucket < 80 else 'validation' if bucket < 90 else 'test'
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
def write_splits(pairs, output):
|
| 70 |
+
rows = load_pairs(pairs)
|
| 71 |
+
groups = {name: [] for name in ('train', 'validation', 'test')}
|
| 72 |
+
for row in sorted(rows, key=lambda item: item['case_id']):
|
| 73 |
+
groups[split_for(row['participant_id'])].append(row)
|
| 74 |
+
if any(not group for group in groups.values()):
|
| 75 |
+
raise ValueError('A split is empty; report this rather than rerolling the seed')
|
| 76 |
+
output = Path(output)
|
| 77 |
+
output.mkdir(parents=True, exist_ok=False, mode=0o700)
|
| 78 |
+
report = {'seed': SEED, 'algorithm': 'sha256-mod100-v1', 'ratios': [80, 10, 10],
|
| 79 |
+
'source_manifest_sha256': digest(pairs), 'splits': {}}
|
| 80 |
+
for name, group in groups.items():
|
| 81 |
+
destination = output / (name + '.jsonl')
|
| 82 |
+
destination.write_text(''.join(json.dumps(row, sort_keys=True) + '\n' for row in group))
|
| 83 |
+
public = [{key: row[key] for key in ('case_id', 'device', 'oct_paths')} for row in group]
|
| 84 |
+
(output / (name + '-inputs.jsonl')).write_text(''.join(json.dumps(row) + '\n' for row in public))
|
| 85 |
+
report['splits'][name] = {'cases': len(group), 'participants': len({row['participant_id'] for row in group}),
|
| 86 |
+
'devices': sorted({row['device'] for row in group}), 'manifest_sha256': digest(destination)}
|
| 87 |
+
(output / 'split-summary.json').write_text(json.dumps(report, indent=2) + '\n')
|
| 88 |
+
return report
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
def read_arrays(path, reference=False):
|
| 92 |
+
import numpy as np
|
| 93 |
+
with np.load(path, allow_pickle=False) as data:
|
| 94 |
+
required = {'positions', 'boundary_keys', 'valid', 'height'} if reference else {'positions', 'boundary_keys'}
|
| 95 |
+
allowed = required | ({'axial_spacing_um'} if reference else set())
|
| 96 |
+
if not required <= set(data.files) or set(data.files) - allowed:
|
| 97 |
+
raise ValueError('Unexpected or missing canonical array fields')
|
| 98 |
+
positions = data['positions']
|
| 99 |
+
keys = data['boundary_keys']
|
| 100 |
+
if positions.ndim != 3 or any(n == 0 for n in positions.shape) or positions.dtype.kind not in 'fiu':
|
| 101 |
+
raise ValueError('positions must be a nonempty real [boundary, B-scan, A-scan] array')
|
| 102 |
+
if keys.ndim != 1 or keys.dtype.kind not in 'US' or len(keys) != positions.shape[0]:
|
| 103 |
+
raise ValueError('boundary_keys must be a one-dimensional Unicode/byte-string array')
|
| 104 |
+
names = [x.decode('utf-8') if isinstance(x, bytes) else str(x) for x in keys.tolist()]
|
| 105 |
+
if any(not x or x != x.strip() for x in names) or len(set(names)) != len(names):
|
| 106 |
+
raise ValueError('Boundary keys must be nonempty and unique')
|
| 107 |
+
result = {'positions': positions.astype('float64'), 'keys': names}
|
| 108 |
+
if reference:
|
| 109 |
+
valid, height = data['valid'], data['height']
|
| 110 |
+
if valid.dtype.kind != 'b' or valid.shape != positions.shape:
|
| 111 |
+
raise ValueError('Reference valid must be a matching Boolean mask')
|
| 112 |
+
if height.shape != () or height.dtype.kind not in 'iu' or int(height) < 2:
|
| 113 |
+
raise ValueError('Reference height must be the original axial size')
|
| 114 |
+
if not valid.any() or not np.isfinite(positions[valid]).all():
|
| 115 |
+
raise ValueError('Reference needs finite valid annotation support')
|
| 116 |
+
if ((positions[valid] < 0) | (positions[valid] > int(height) - 1)).any():
|
| 117 |
+
raise ValueError('Reference coordinates are outside original geometry')
|
| 118 |
+
result.update(valid=valid.copy(), height=int(height), spacing=None)
|
| 119 |
+
if 'axial_spacing_um' in data:
|
| 120 |
+
spacing = data['axial_spacing_um']
|
| 121 |
+
if spacing.shape != () or spacing.dtype.kind not in 'fiu' or not np.isfinite(spacing) or float(spacing) <= 0:
|
| 122 |
+
raise ValueError('Axial spacing must be a positive finite scalar in micrometres')
|
| 123 |
+
result['spacing'] = float(spacing)
|
| 124 |
+
return result
|
| 125 |
+
|
| 126 |
+
|
| 127 |
+
def score(manifest, references, predictions, expected_manifest_sha256=None):
|
| 128 |
+
import numpy as np
|
| 129 |
+
fingerprint = digest(manifest)
|
| 130 |
+
if expected_manifest_sha256 is not None and fingerprint != expected_manifest_sha256:
|
| 131 |
+
raise ValueError('The frozen manifest changed')
|
| 132 |
+
rows = load_pairs(manifest)
|
| 133 |
+
expected = {row['case_id'] for row in rows}
|
| 134 |
+
if {path.stem for path in Path(predictions).glob('*.npz')} != expected:
|
| 135 |
+
raise ValueError('Prediction cases do not exactly cover the manifest')
|
| 136 |
+
grouped = defaultdict(lambda: defaultdict(list))
|
| 137 |
+
boundaries = defaultdict(lambda: defaultdict(lambda: defaultdict(list)))
|
| 138 |
+
boundary_counts = defaultdict(lambda: defaultdict(int))
|
| 139 |
+
physical = defaultdict(lambda: defaultdict(list))
|
| 140 |
+
spacing_cases = defaultdict(int)
|
| 141 |
+
for row in rows:
|
| 142 |
+
name = row['case_id'] + '.npz'
|
| 143 |
+
ref = read_arrays(Path(references) / name, reference=True)
|
| 144 |
+
pred = read_arrays(Path(predictions) / name)
|
| 145 |
+
if set(ref['keys']) != set(pred['keys']) or ref['positions'].shape != pred['positions'].shape:
|
| 146 |
+
raise ValueError('Prediction boundary identities or geometry do not match')
|
| 147 |
+
values = pred['positions'][[pred['keys'].index(key) for key in ref['keys']]]
|
| 148 |
+
if not np.isfinite(values).all() or ((values < 0) | (values > ref['height'] - 1)).any():
|
| 149 |
+
raise ValueError('All predicted coordinates must be finite and in original bounds')
|
| 150 |
+
device, participant = row['device'], row['participant_id']
|
| 151 |
+
errors = []
|
| 152 |
+
for index, key in enumerate(ref['keys']):
|
| 153 |
+
mask = ref['valid'][index]
|
| 154 |
+
boundary_counts[device][key] += int(mask.sum())
|
| 155 |
+
if mask.any():
|
| 156 |
+
error = float(np.abs(values[index][mask] - ref['positions'][index][mask]).mean())
|
| 157 |
+
errors.append(error)
|
| 158 |
+
boundaries[device][key][participant].append(error)
|
| 159 |
+
case_error = fmean(errors)
|
| 160 |
+
grouped[device][participant].append(case_error)
|
| 161 |
+
if ref['spacing'] is not None:
|
| 162 |
+
physical[device][participant].append(case_error * ref['spacing'])
|
| 163 |
+
spacing_cases[device] += 1
|
| 164 |
+
average = lambda participants: fmean(fmean(cases) for cases in participants.values())
|
| 165 |
+
devices = {}
|
| 166 |
+
for device, participants in sorted(grouped.items()):
|
| 167 |
+
count = sum(map(len, participants.values()))
|
| 168 |
+
devices[device] = {'cases': count, 'participants': len(participants), 'mae_pixels': average(participants),
|
| 169 |
+
'spacing_cases': spacing_cases[device],
|
| 170 |
+
'mae_um': average(physical[device]) if spacing_cases[device] == count else None,
|
| 171 |
+
'boundaries': {key: {'mae_pixels': average(groups) if groups else None, 'participants': len(groups),
|
| 172 |
+
'valid_points': boundary_counts[device][key]}
|
| 173 |
+
for key, groups in ((key, boundaries[device][key]) for key in sorted(boundary_counts[device]))}}
|
| 174 |
+
return {'measurement': 'informal_canonical_boundary_agreement', 'manifest_sha256': fingerprint,
|
| 175 |
+
'cases': len(rows), 'participants': len({row['participant_id'] for row in rows}),
|
| 176 |
+
'mae_pixels': fmean(item['mae_pixels'] for item in devices.values()),
|
| 177 |
+
'mae_um': fmean(item['mae_um'] for item in devices.values()) if all(item['mae_um'] is not None for item in devices.values()) else None,
|
| 178 |
+
'aggregation': 'valid points -> boundaries -> volume -> participant/device -> device -> macro device',
|
| 179 |
+
'devices': devices}
|
| 180 |
+
|
| 181 |
+
|
| 182 |
+
def main():
|
| 183 |
+
parser = argparse.ArgumentParser(description=__doc__)
|
| 184 |
+
commands = parser.add_subparsers(dest='command', required=True)
|
| 185 |
+
split = commands.add_parser('split')
|
| 186 |
+
split.add_argument('--pairs', required=True, type=Path)
|
| 187 |
+
split.add_argument('--output-dir', required=True, type=Path)
|
| 188 |
+
measure = commands.add_parser('score')
|
| 189 |
+
measure.add_argument('--manifest', required=True, type=Path)
|
| 190 |
+
measure.add_argument('--reference-dir', required=True, type=Path)
|
| 191 |
+
measure.add_argument('--predictions-dir', required=True, type=Path)
|
| 192 |
+
measure.add_argument('--expected-manifest-sha256')
|
| 193 |
+
measure.add_argument('--output', required=True, type=Path)
|
| 194 |
+
args = parser.parse_args()
|
| 195 |
+
if args.command == 'split':
|
| 196 |
+
result = write_splits(args.pairs, args.output_dir)
|
| 197 |
+
else:
|
| 198 |
+
if args.output.exists():
|
| 199 |
+
raise FileExistsError('Choose a fresh metric report path')
|
| 200 |
+
result = score(args.manifest, args.reference_dir, args.predictions_dir, args.expected_manifest_sha256)
|
| 201 |
+
with args.output.open('x') as stream:
|
| 202 |
+
json.dump(result, stream, indent=2, allow_nan=False)
|
| 203 |
+
stream.write('\n')
|
| 204 |
+
print(json.dumps(result, allow_nan=False))
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
if __name__ == '__main__':
|
| 208 |
+
main()
|
src/training/__init__.py
ADDED
|
File without changes
|
src/training/guard.py
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Metadata-only split checks before development payload access.
|
| 2 |
+
|
| 3 |
+
The frozen discovery audit establishes pairing. These checks independently reject
|
| 4 |
+
a mislabeled manifest participant before reading any image/segmentation payload.
|
| 5 |
+
This module is never imported by label-free inference.
|
| 6 |
+
"""
|
| 7 |
+
|
| 8 |
+
import pydicom
|
| 9 |
+
from src.io import safe_path
|
| 10 |
+
from src.protocol import split_for
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
def check_development_identity(row, root, expected_split):
|
| 14 |
+
participant = str(row["participant_id"])
|
| 15 |
+
if (
|
| 16 |
+
expected_split not in ["train", "validation"]
|
| 17 |
+
or split_for(participant) != expected_split
|
| 18 |
+
):
|
| 19 |
+
raise ValueError("Development manifest split violation")
|
| 20 |
+
classes = [
|
| 21 |
+
("oct_paths", "1.2.840.10008.5.1.4.1.1.77.1.5.4"),
|
| 22 |
+
("segmentation_paths", "1.2.840.10008.5.1.4.1.1.66.8"),
|
| 23 |
+
]
|
| 24 |
+
for field, sop_class in classes:
|
| 25 |
+
for relative in row[field]:
|
| 26 |
+
header = pydicom.dcmread(
|
| 27 |
+
safe_path(root, relative),
|
| 28 |
+
stop_before_pixels=True,
|
| 29 |
+
specific_tags=["PatientID", "SOPClassUID"],
|
| 30 |
+
)
|
| 31 |
+
actual = str(header.get("PatientID", ""))
|
| 32 |
+
if actual != participant or split_for(actual) != expected_split:
|
| 33 |
+
raise ValueError(
|
| 34 |
+
"DICOM participant identity/split differs from frozen manifest"
|
| 35 |
+
)
|
| 36 |
+
if str(header.get("SOPClassUID", "")) != sop_class:
|
| 37 |
+
raise ValueError("Unexpected development source object class")
|
src/training/unet.py
ADDED
|
@@ -0,0 +1,790 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Original boundary model training. Run only through managed compute.
|
| 2 |
+
|
| 3 |
+
Canonical references and sampled training OCT caches are produced by prepare.py.
|
| 4 |
+
All checkpoints begin randomly unless --resume supplies this researcher's weights.
|
| 5 |
+
"""
|
| 6 |
+
|
| 7 |
+
from src.paths import PROJECT_ROOT
|
| 8 |
+
from pathlib import Path
|
| 9 |
+
from collections import defaultdict, OrderedDict
|
| 10 |
+
import argparse
|
| 11 |
+
import json
|
| 12 |
+
import random
|
| 13 |
+
import time
|
| 14 |
+
import math
|
| 15 |
+
import subprocess
|
| 16 |
+
import sys
|
| 17 |
+
import os
|
| 18 |
+
|
| 19 |
+
SCRIPT_STARTED = time.time()
|
| 20 |
+
SCRIPT_TIMER = time.monotonic()
|
| 21 |
+
print(
|
| 22 |
+
json.dumps({"stage": "scientific_imports", "process_started_unix": SCRIPT_STARTED}),
|
| 23 |
+
flush=True,
|
| 24 |
+
)
|
| 25 |
+
import numpy as np
|
| 26 |
+
import torch
|
| 27 |
+
from torch.utils.data import Dataset, DataLoader
|
| 28 |
+
from src.models.unet import boundary_loss
|
| 29 |
+
from src.models import build_model, configure_heads, output_indices, remap_state
|
| 30 |
+
from src.io import load_manifest
|
| 31 |
+
from src.protocol import split_for, digest
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
class CachedFrames(Dataset):
|
| 35 |
+
def __init__(self, rows, cache, keys, packed=None, config=None, global_cache=None):
|
| 36 |
+
self.config = config
|
| 37 |
+
self.global_images = None
|
| 38 |
+
self.global_cases = {}
|
| 39 |
+
if global_cache:
|
| 40 |
+
global_root = Path(global_cache)
|
| 41 |
+
meta = json.loads((global_root / "global-meta.json").read_text())
|
| 42 |
+
self.global_cases = {r["case_id"]: int(r["index"]) for r in meta["cases"]}
|
| 43 |
+
if set(self.global_cases) != {r["case_id"] for r in rows}:
|
| 44 |
+
raise ValueError("Global cache cases differ")
|
| 45 |
+
if sorted(self.global_cases.values()) != list(range(len(rows))):
|
| 46 |
+
raise ValueError("Global cache indices differ")
|
| 47 |
+
self.global_images = np.load(
|
| 48 |
+
global_root / "global-images.npy", mmap_mode="r", allow_pickle=False
|
| 49 |
+
)
|
| 50 |
+
if self.global_images.shape != (
|
| 51 |
+
len(rows),
|
| 52 |
+
3,
|
| 53 |
+
config["height"],
|
| 54 |
+
config["width"],
|
| 55 |
+
):
|
| 56 |
+
raise ValueError("Global image geometry differs")
|
| 57 |
+
self.rows = rows
|
| 58 |
+
self.cache = Path(cache) / "frames-train"
|
| 59 |
+
self.keys = keys
|
| 60 |
+
self.memo = OrderedDict()
|
| 61 |
+
self.samples = []
|
| 62 |
+
self.weights = []
|
| 63 |
+
self.packed = None
|
| 64 |
+
self.packed_cases = {}
|
| 65 |
+
if packed:
|
| 66 |
+
packed = Path(packed)
|
| 67 |
+
meta = json.loads((packed / "packed.json").read_text())
|
| 68 |
+
if meta["boundary_keys"] != keys:
|
| 69 |
+
raise ValueError("Packed vocabulary differs")
|
| 70 |
+
self.packed_cases = {r["case_id"]: r for r in meta["cases"]}
|
| 71 |
+
self.packed = {
|
| 72 |
+
k: np.load(packed / (k + ".npy"), mmap_mode="r", allow_pickle=False)
|
| 73 |
+
for k in ["images", "positions", "valid", "original_height"]
|
| 74 |
+
}
|
| 75 |
+
sampling = Path(cache) / "sampling.jsonl"
|
| 76 |
+
counts = {}
|
| 77 |
+
if sampling.is_file():
|
| 78 |
+
for line in sampling.read_text().splitlines():
|
| 79 |
+
r = json.loads(line)
|
| 80 |
+
if r.get("split") == "train" and "error" not in r:
|
| 81 |
+
counts[r["case_id"]] = len(r["frames"])
|
| 82 |
+
devices = defaultdict(lambda: defaultdict(list))
|
| 83 |
+
for i, r in enumerate(rows):
|
| 84 |
+
devices[r["device"]][r["participant_id"]].append(i)
|
| 85 |
+
for i, row in enumerate(rows):
|
| 86 |
+
if self.packed is not None and row["case_id"] not in self.packed_cases:
|
| 87 |
+
raise ValueError("Packed case missing")
|
| 88 |
+
if row["case_id"] in counts:
|
| 89 |
+
n = counts[row["case_id"]]
|
| 90 |
+
else:
|
| 91 |
+
with np.load(
|
| 92 |
+
self.cache / (row["case_id"] + ".npz"), allow_pickle=False
|
| 93 |
+
) as f:
|
| 94 |
+
n = len(f["images"])
|
| 95 |
+
if n < 1:
|
| 96 |
+
raise ValueError(
|
| 97 |
+
"A training case has no cached source-annotated frames"
|
| 98 |
+
)
|
| 99 |
+
if (
|
| 100 |
+
self.packed is not None
|
| 101 |
+
and self.packed_cases[row["case_id"]]["count"] != n
|
| 102 |
+
):
|
| 103 |
+
raise ValueError("Packed frame sampling differs")
|
| 104 |
+
group = devices[row["device"]]
|
| 105 |
+
for j in range(n):
|
| 106 |
+
self.samples.append((i, j))
|
| 107 |
+
self.weights.append(
|
| 108 |
+
1 / (len(group) * len(group[row["participant_id"]]) * n)
|
| 109 |
+
)
|
| 110 |
+
|
| 111 |
+
def __len__(self):
|
| 112 |
+
return len(self.samples)
|
| 113 |
+
|
| 114 |
+
def __getitem__(self, index):
|
| 115 |
+
i, j = self.samples[index]
|
| 116 |
+
row = self.rows[i]
|
| 117 |
+
name = row["case_id"]
|
| 118 |
+
if self.packed is not None:
|
| 119 |
+
index = self.packed_cases[name]["offset"] + j
|
| 120 |
+
data = self.packed
|
| 121 |
+
pos, valid = self.project(
|
| 122 |
+
row, data["positions"][index].copy(), data["valid"][index].copy()
|
| 123 |
+
)
|
| 124 |
+
image = data["images"][index].astype(np.float32) / 255
|
| 125 |
+
if image.ndim == 2:
|
| 126 |
+
image = image[None]
|
| 127 |
+
image = self.join_global(image, name)
|
| 128 |
+
return (
|
| 129 |
+
torch.from_numpy(image),
|
| 130 |
+
torch.from_numpy(pos),
|
| 131 |
+
torch.from_numpy(valid),
|
| 132 |
+
np.float32(data["original_height"][index]),
|
| 133 |
+
)
|
| 134 |
+
if name in self.memo:
|
| 135 |
+
data = self.memo.pop(name)
|
| 136 |
+
else:
|
| 137 |
+
with np.load(self.cache / (name + ".npz"), allow_pickle=False) as f:
|
| 138 |
+
data = {k: f[k] for k in f.files}
|
| 139 |
+
self.memo[name] = data
|
| 140 |
+
while len(self.memo) > 16:
|
| 141 |
+
self.memo.popitem(last=False)
|
| 142 |
+
image = data["images"][j].astype(np.float32) / 255
|
| 143 |
+
if image.ndim == 2:
|
| 144 |
+
image = image[None]
|
| 145 |
+
pos = np.zeros((len(self.keys), image.shape[-1]), np.float32)
|
| 146 |
+
valid = np.zeros_like(pos, dtype=bool)
|
| 147 |
+
for k, key in enumerate(data["boundary_keys"].tolist()):
|
| 148 |
+
global_index = self.keys.index(key)
|
| 149 |
+
pos[global_index] = data["positions"][k, j]
|
| 150 |
+
valid[global_index] = data["valid"][k, j]
|
| 151 |
+
pos, valid = self.project(row, pos, valid)
|
| 152 |
+
image = self.join_global(image, name)
|
| 153 |
+
return (
|
| 154 |
+
torch.from_numpy(image),
|
| 155 |
+
torch.from_numpy(pos),
|
| 156 |
+
torch.from_numpy(valid),
|
| 157 |
+
np.float32(data["original_height"]),
|
| 158 |
+
)
|
| 159 |
+
|
| 160 |
+
def join_global(self, image, name):
|
| 161 |
+
if self.global_images is None:
|
| 162 |
+
return image
|
| 163 |
+
if image.shape[0] != 3:
|
| 164 |
+
raise ValueError("Local context must contain three channels")
|
| 165 |
+
return np.concatenate(
|
| 166 |
+
[
|
| 167 |
+
image,
|
| 168 |
+
self.global_images[self.global_cases[name]].astype(np.float32) / 255,
|
| 169 |
+
],
|
| 170 |
+
axis=0,
|
| 171 |
+
)
|
| 172 |
+
|
| 173 |
+
def project(self, row, pos, valid):
|
| 174 |
+
if self.config is None or "device_output_indices" not in self.config:
|
| 175 |
+
return pos, valid
|
| 176 |
+
target = np.zeros(
|
| 177 |
+
(len(self.config["model_head_keys"]), pos.shape[-1]), np.float32
|
| 178 |
+
)
|
| 179 |
+
support = np.zeros_like(target, dtype=bool)
|
| 180 |
+
for key, index in zip(
|
| 181 |
+
self.config["device_keys"][row["device"]],
|
| 182 |
+
output_indices(self.config, row["device"]),
|
| 183 |
+
):
|
| 184 |
+
source = self.keys.index(key)
|
| 185 |
+
target[index] = pos[source]
|
| 186 |
+
support[index] = valid[source]
|
| 187 |
+
return target, support
|
| 188 |
+
|
| 189 |
+
|
| 190 |
+
def seed_worker(worker_id):
|
| 191 |
+
seed = torch.initial_seed() % 2**32
|
| 192 |
+
np.random.seed(seed)
|
| 193 |
+
random.seed(seed)
|
| 194 |
+
|
| 195 |
+
|
| 196 |
+
def augment(image, pos, valid):
|
| 197 |
+
n, _, h, w = image.shape
|
| 198 |
+
flip = torch.rand(n, device=image.device) < 0.5
|
| 199 |
+
image[flip] = image[flip].flip(-1)
|
| 200 |
+
pos[flip] = pos[flip].flip(-1)
|
| 201 |
+
valid[flip] = valid[flip].flip(-1)
|
| 202 |
+
# Axial shifts preserve the coordinate contract; locations shifted outside the
|
| 203 |
+
# augmented image are not training support, with the original masks unchanged.
|
| 204 |
+
shifts = torch.randint(-(h // 12), h // 12 + 1, (n,), device=image.device)
|
| 205 |
+
# Preserve native image-edge targets; translating only their visible support
|
| 206 |
+
# would systematically turn valid zero-depth annotations into positive depths.
|
| 207 |
+
touches_edge = (valid & ((pos <= 0) | (pos >= h - 1))).flatten(1).any(1)
|
| 208 |
+
shifts[touches_edge] = 0
|
| 209 |
+
for i, shift in enumerate(shifts.tolist()):
|
| 210 |
+
image[i] = torch.roll(image[i], shift, -2)
|
| 211 |
+
if shift > 0:
|
| 212 |
+
image[i, :, :shift] = 0
|
| 213 |
+
elif shift < 0:
|
| 214 |
+
image[i, :, shift:] = 0
|
| 215 |
+
pos[i] += shift
|
| 216 |
+
valid &= (pos >= 0) & (pos <= h - 1)
|
| 217 |
+
pos = pos.clamp(0, h - 1)
|
| 218 |
+
gamma = torch.empty(n, 1, 1, 1, device=image.device).uniform_(0.75, 1.4)
|
| 219 |
+
gain = torch.empty(n, 1, 1, 1, device=image.device).uniform_(0.8, 1.2)
|
| 220 |
+
image = (
|
| 221 |
+
image.clamp_min(0).pow(gamma) * gain + torch.randn_like(image) * 0.015
|
| 222 |
+
).clamp(0, 1)
|
| 223 |
+
return image, pos, valid
|
| 224 |
+
|
| 225 |
+
|
| 226 |
+
def source_hashes():
|
| 227 |
+
return {
|
| 228 |
+
p.relative_to(PROJECT_ROOT).as_posix(): digest(p)
|
| 229 |
+
for folder in [PROJECT_ROOT, PROJECT_ROOT / "src", PROJECT_ROOT / "tools"]
|
| 230 |
+
for p in sorted(
|
| 231 |
+
folder.glob("*.py") if folder == PROJECT_ROOT else folder.rglob("*.py")
|
| 232 |
+
)
|
| 233 |
+
}
|
| 234 |
+
|
| 235 |
+
|
| 236 |
+
def main():
|
| 237 |
+
ap = argparse.ArgumentParser()
|
| 238 |
+
ap.add_argument("--train-manifest", required=True)
|
| 239 |
+
ap.add_argument("--validation-manifest", required=True)
|
| 240 |
+
ap.add_argument("--data-root", required=True)
|
| 241 |
+
ap.add_argument("--output-dir", required=True)
|
| 242 |
+
ap.add_argument("--seed", type=int, required=True)
|
| 243 |
+
ap.add_argument("--cache-dir")
|
| 244 |
+
ap.add_argument("--global-cache")
|
| 245 |
+
ap.add_argument("--packed-cache")
|
| 246 |
+
ap.add_argument("--steps", type=int, default=30000)
|
| 247 |
+
ap.add_argument("--batch-size", type=int, default=8)
|
| 248 |
+
ap.add_argument("--workers", type=int, default=4)
|
| 249 |
+
ap.add_argument("--base", type=int, default=24)
|
| 250 |
+
ap.add_argument("--height", type=int, default=384)
|
| 251 |
+
ap.add_argument("--width", type=int, default=256)
|
| 252 |
+
ap.add_argument("--learning-rate", type=float, default=0.0005)
|
| 253 |
+
ap.add_argument("--save-every", type=int, default=2000)
|
| 254 |
+
ap.add_argument("--sigma", type=float, default=1.5)
|
| 255 |
+
ap.add_argument("--regression-weight", type=float, default=0.1)
|
| 256 |
+
ap.add_argument(
|
| 257 |
+
"--regression-loss",
|
| 258 |
+
choices=["smooth_l1", "l1", "expected_l1"],
|
| 259 |
+
default="smooth_l1",
|
| 260 |
+
)
|
| 261 |
+
ap.add_argument("--input-channels", type=int, choices=[1, 3, 5, 6], default=1)
|
| 262 |
+
ap.add_argument("--pack-active-heads", action="store_true")
|
| 263 |
+
ap.add_argument("--axial-prior", action="store_true")
|
| 264 |
+
ap.add_argument("--auxiliary-region-weight", type=float, default=0)
|
| 265 |
+
ap.add_argument("--resume")
|
| 266 |
+
ap.add_argument("--reset-optimizer", action="store_true")
|
| 267 |
+
ap.add_argument("--head-mode", choices=["shared", "device"], default="shared")
|
| 268 |
+
ap.add_argument("--device", default="cuda")
|
| 269 |
+
args = ap.parse_args()
|
| 270 |
+
torch.set_num_threads(4)
|
| 271 |
+
random.seed(args.seed)
|
| 272 |
+
np.random.seed(args.seed)
|
| 273 |
+
torch.manual_seed(args.seed)
|
| 274 |
+
torch.cuda.manual_seed_all(args.seed)
|
| 275 |
+
torch.backends.cudnn.benchmark = True
|
| 276 |
+
rows = load_manifest(args.train_manifest)
|
| 277 |
+
val = load_manifest(args.validation_manifest)
|
| 278 |
+
if any(split_for(r["participant_id"]) != "train" for r in rows) or any(
|
| 279 |
+
split_for(r["participant_id"]) != "validation" for r in val
|
| 280 |
+
):
|
| 281 |
+
raise ValueError("Fixed split violation")
|
| 282 |
+
out = Path(args.output_dir).resolve()
|
| 283 |
+
out.mkdir(parents=True, exist_ok=True)
|
| 284 |
+
print("training_output", str(out), flush=True)
|
| 285 |
+
if args.input_channels in [5, 6] and not args.axial_prior:
|
| 286 |
+
raise ValueError("Six-channel global training requires --axial-prior")
|
| 287 |
+
if args.global_cache and args.input_channels != 6:
|
| 288 |
+
raise ValueError("Global cache requires six-channel configuration")
|
| 289 |
+
if args.auxiliary_region_weight and args.input_channels != 1:
|
| 290 |
+
raise ValueError("This auxiliary architecture uses one local OCT channel")
|
| 291 |
+
local_channels = 3 if args.input_channels == 6 else args.input_channels
|
| 292 |
+
cache = args.cache_dir or str(out / "cache")
|
| 293 |
+
if args.cache_dir is None:
|
| 294 |
+
subprocess.run(
|
| 295 |
+
[
|
| 296 |
+
sys.executable,
|
| 297 |
+
str(PROJECT_ROOT / "tools/prepare.py"),
|
| 298 |
+
"--train-manifest",
|
| 299 |
+
args.train_manifest,
|
| 300 |
+
"--validation-manifest",
|
| 301 |
+
args.validation_manifest,
|
| 302 |
+
"--data-root",
|
| 303 |
+
args.data_root,
|
| 304 |
+
"--output-dir",
|
| 305 |
+
cache,
|
| 306 |
+
"--height",
|
| 307 |
+
str(args.height),
|
| 308 |
+
"--width",
|
| 309 |
+
str(args.width),
|
| 310 |
+
"--seed",
|
| 311 |
+
str(args.seed),
|
| 312 |
+
"--input-channels",
|
| 313 |
+
str(local_channels),
|
| 314 |
+
"--workers",
|
| 315 |
+
str(max(1, args.workers)),
|
| 316 |
+
],
|
| 317 |
+
check=True,
|
| 318 |
+
)
|
| 319 |
+
if args.input_channels == 6 and args.global_cache is None:
|
| 320 |
+
args.global_cache = str(out / "global-cache")
|
| 321 |
+
subprocess.run(
|
| 322 |
+
[
|
| 323 |
+
sys.executable,
|
| 324 |
+
str(PROJECT_ROOT / "tools/prepare_global.py"),
|
| 325 |
+
"--train-manifest",
|
| 326 |
+
args.train_manifest,
|
| 327 |
+
"--data-root",
|
| 328 |
+
args.data_root,
|
| 329 |
+
"--output-dir",
|
| 330 |
+
args.global_cache,
|
| 331 |
+
"--height",
|
| 332 |
+
str(args.height),
|
| 333 |
+
"--width",
|
| 334 |
+
str(args.width),
|
| 335 |
+
"--workers",
|
| 336 |
+
str(max(1, args.workers)),
|
| 337 |
+
],
|
| 338 |
+
check=True,
|
| 339 |
+
)
|
| 340 |
+
preparation = json.loads((Path(cache) / "preparation-summary.json").read_text())
|
| 341 |
+
if preparation["failures"] or preparation["manifest_hashes"] != {
|
| 342 |
+
"train": digest(args.train_manifest),
|
| 343 |
+
"validation": digest(args.validation_manifest),
|
| 344 |
+
}:
|
| 345 |
+
raise ValueError("Complete cache must match the frozen manifests")
|
| 346 |
+
if preparation["decoder_sha256"] != digest(PROJECT_ROOT / "src/annotations.py"):
|
| 347 |
+
raise ValueError("Canonical decoder changed after preparation")
|
| 348 |
+
local_channels = 3 if args.global_cache else args.input_channels
|
| 349 |
+
if preparation["arguments"].get("input_channels", 1) != local_channels:
|
| 350 |
+
raise ValueError("Cached input channels differ")
|
| 351 |
+
if (preparation["arguments"]["height"], preparation["arguments"]["width"]) != (
|
| 352 |
+
args.height,
|
| 353 |
+
args.width,
|
| 354 |
+
):
|
| 355 |
+
raise ValueError("Cached image resolution differs from training configuration")
|
| 356 |
+
if args.packed_cache:
|
| 357 |
+
packed_meta = json.loads((Path(args.packed_cache) / "packed.json").read_text())
|
| 358 |
+
if (
|
| 359 |
+
packed_meta["training_manifest_sha256"] != digest(args.train_manifest)
|
| 360 |
+
or packed_meta["decoder_sha256"] != preparation["decoder_sha256"]
|
| 361 |
+
or packed_meta["source_sampling_sha256"]
|
| 362 |
+
!= digest(Path(cache) / "sampling.jsonl")
|
| 363 |
+
or packed_meta["source_preparation_sha256"]
|
| 364 |
+
!= digest(Path(cache) / "preparation-summary.json")
|
| 365 |
+
):
|
| 366 |
+
raise ValueError("Packed cache provenance differs")
|
| 367 |
+
if packed_meta.get("input_channels", 1) != local_channels:
|
| 368 |
+
raise ValueError("Packed input channels differ")
|
| 369 |
+
if (packed_meta["height"], packed_meta["width"]) != (args.height, args.width):
|
| 370 |
+
raise ValueError("Packed resolution differs")
|
| 371 |
+
device_keys = {}
|
| 372 |
+
for r in rows:
|
| 373 |
+
if r["device"] not in device_keys:
|
| 374 |
+
with np.load(
|
| 375 |
+
Path(cache) / "frames-train" / (r["case_id"] + ".npz"),
|
| 376 |
+
allow_pickle=False,
|
| 377 |
+
) as f:
|
| 378 |
+
device_keys[r["device"]] = f["boundary_keys"].tolist()
|
| 379 |
+
keys = sorted(set(k for v in device_keys.values() for k in v))
|
| 380 |
+
config = {
|
| 381 |
+
"architecture": "BoundaryNet",
|
| 382 |
+
"base": args.base,
|
| 383 |
+
"height": args.height,
|
| 384 |
+
"width": args.width,
|
| 385 |
+
"boundary_keys": keys,
|
| 386 |
+
"device_keys": device_keys,
|
| 387 |
+
"normalization": "within-frame-percentile-1-99.5-bilinear-v1",
|
| 388 |
+
"initialization": "random",
|
| 389 |
+
"seed": args.seed,
|
| 390 |
+
"frame_sampling_seed": preparation["arguments"]["seed"],
|
| 391 |
+
"cache_sampling_sha256": digest(Path(cache) / "sampling.jsonl"),
|
| 392 |
+
"sampling_balance": "device -> participant -> volume -> cached frame",
|
| 393 |
+
"augmentation": {
|
| 394 |
+
"horizontal_flip_probability": 0.5,
|
| 395 |
+
"vertical_shift_fraction": 1 / 12,
|
| 396 |
+
"vertical_shift_on_edge_touching_labels": False,
|
| 397 |
+
"gamma": [0.75, 1.4],
|
| 398 |
+
"gain": [0.8, 1.2],
|
| 399 |
+
"noise_std": 0.015,
|
| 400 |
+
},
|
| 401 |
+
"optimizer": {
|
| 402 |
+
"name": "AdamW",
|
| 403 |
+
"weight_decay": 1e-4,
|
| 404 |
+
"gradient_clip_norm": 5,
|
| 405 |
+
"warmup_steps": 500,
|
| 406 |
+
"cosine_floor": 0.05,
|
| 407 |
+
"ema_max_decay": 0.9995,
|
| 408 |
+
},
|
| 409 |
+
"numerics": {
|
| 410 |
+
"threads": 4,
|
| 411 |
+
"active_head_packing": args.pack_active_heads,
|
| 412 |
+
"cudnn_benchmark": True,
|
| 413 |
+
"deterministic_algorithms": False,
|
| 414 |
+
"allow_tf32_matmul": torch.backends.cuda.matmul.allow_tf32,
|
| 415 |
+
"allow_tf32_cudnn": torch.backends.cudnn.allow_tf32,
|
| 416 |
+
"mixed_precision": "bfloat16_if_supported_otherwise_float16_on_cuda",
|
| 417 |
+
},
|
| 418 |
+
"loss": {
|
| 419 |
+
"gaussian_sigma": args.sigma,
|
| 420 |
+
"regression_weight": args.regression_weight,
|
| 421 |
+
"regression_units": "original axial pixels",
|
| 422 |
+
"regression_loss": args.regression_loss,
|
| 423 |
+
"smooth_l1_beta_model_pixels": (
|
| 424 |
+
2 if args.regression_loss == "smooth_l1" else None
|
| 425 |
+
),
|
| 426 |
+
},
|
| 427 |
+
"decoder_sha256": preparation["decoder_sha256"],
|
| 428 |
+
"training_manifest_sha256": digest(args.train_manifest),
|
| 429 |
+
"validation_manifest_sha256": digest(args.validation_manifest),
|
| 430 |
+
}
|
| 431 |
+
config["training_schedule"] = {
|
| 432 |
+
"total_final_step": args.steps,
|
| 433 |
+
"batch_size": args.batch_size,
|
| 434 |
+
"maximum_learning_rate": args.learning_rate,
|
| 435 |
+
"save_every_steps": args.save_every,
|
| 436 |
+
}
|
| 437 |
+
configure_heads(config, args.head_mode)
|
| 438 |
+
if args.axial_prior:
|
| 439 |
+
config["architecture"] = "BoundaryNetAxialPrior"
|
| 440 |
+
config["axial_prior"] = {
|
| 441 |
+
"initialization": "zero for a new prior; restore or interpolate an existing own-trained prior on resume",
|
| 442 |
+
"shape": [1, len(config.get("model_head_keys", keys)), args.height, 1],
|
| 443 |
+
"training": "joint supervised training only; no label inputs at inference",
|
| 444 |
+
}
|
| 445 |
+
config["input_channels"] = args.input_channels
|
| 446 |
+
if args.input_channels == 3:
|
| 447 |
+
config["architecture"] = (
|
| 448 |
+
"BoundaryNetContextPrior" if args.axial_prior else "BoundaryNetContext"
|
| 449 |
+
)
|
| 450 |
+
config["input_context"] = {
|
| 451 |
+
"frame_offsets": [-1, 0, 1],
|
| 452 |
+
"endpoints": "replicated",
|
| 453 |
+
"supervised_frame": "center",
|
| 454 |
+
}
|
| 455 |
+
if args.input_channels == 5:
|
| 456 |
+
config["architecture"] = "BoundaryNetWidePrior"
|
| 457 |
+
config["input_context"] = {
|
| 458 |
+
"frame_offsets": [-8, -1, 0, 1, 8],
|
| 459 |
+
"endpoints": "replicated",
|
| 460 |
+
"supervised_frame": "center",
|
| 461 |
+
"initialization": "own C3 body unchanged plus zero distant-view convolution before first normalization",
|
| 462 |
+
}
|
| 463 |
+
if args.global_cache:
|
| 464 |
+
if args.input_channels != 6 or not args.axial_prior:
|
| 465 |
+
raise ValueError("Global context requires six channels and axial prior")
|
| 466 |
+
global_meta = json.loads(
|
| 467 |
+
(Path(args.global_cache) / "global-meta.json").read_text()
|
| 468 |
+
)
|
| 469 |
+
if global_meta["failures"] or global_meta["manifest_sha256"] != digest(
|
| 470 |
+
args.train_manifest
|
| 471 |
+
):
|
| 472 |
+
raise ValueError("Global cache must match full training manifest")
|
| 473 |
+
if (global_meta["height"], global_meta["width"]) != (args.height, args.width):
|
| 474 |
+
raise ValueError("Global context resolution differs")
|
| 475 |
+
if global_meta["normalization_source_sha256"] != digest(
|
| 476 |
+
PROJECT_ROOT / "src/io.py"
|
| 477 |
+
):
|
| 478 |
+
raise ValueError("Global normalization differs")
|
| 479 |
+
config["architecture"] = "BoundaryNetGlobalPrior"
|
| 480 |
+
config["global_context"] = {
|
| 481 |
+
"local_channels": 3,
|
| 482 |
+
"local_frame_offsets": [-1, 0, 1],
|
| 483 |
+
"global_frame_rule": "[0, floor(B/2), B-1]",
|
| 484 |
+
"encoder_input_shape": [96, 128],
|
| 485 |
+
"conditioning": "zero-initialized bottleneck channel scale and bias",
|
| 486 |
+
"initialization_seed": args.seed + 19991,
|
| 487 |
+
"global_cache_meta_sha256": digest(
|
| 488 |
+
Path(args.global_cache) / "global-meta.json"
|
| 489 |
+
),
|
| 490 |
+
}
|
| 491 |
+
elif args.input_channels == 6:
|
| 492 |
+
raise ValueError("Six-channel training requires a global image cache")
|
| 493 |
+
if args.auxiliary_region_weight:
|
| 494 |
+
if not args.axial_prior or args.auxiliary_region_weight < 0:
|
| 495 |
+
raise ValueError("Positive auxiliary weight with axial prior required")
|
| 496 |
+
from src.models.auxiliary import configure_auxiliary
|
| 497 |
+
|
| 498 |
+
configure_auxiliary(config)
|
| 499 |
+
config["architecture"] = "BoundaryNetAuxiliaryPrior"
|
| 500 |
+
config["loss"]["auxiliary_region"] = {
|
| 501 |
+
"weight": args.auxiliary_region_weight,
|
| 502 |
+
"normalization": "per image and present ordinal interval class",
|
| 503 |
+
"support": "all required boundaries source-valid and nondecreasing; boundary objective unchanged",
|
| 504 |
+
"initialization": "zero auxiliary head; own trained backbone/prior retained",
|
| 505 |
+
}
|
| 506 |
+
if args.resume:
|
| 507 |
+
config["initialization"] = "own-trained-checkpoint"
|
| 508 |
+
config["resume_checkpoint_sha256"] = digest(args.resume)
|
| 509 |
+
(out / "config.json").write_text(json.dumps(config, indent=2))
|
| 510 |
+
(out / "provenance.json").write_text(
|
| 511 |
+
json.dumps(
|
| 512 |
+
{
|
| 513 |
+
"arguments": vars(args),
|
| 514 |
+
"source_hashes": source_hashes(),
|
| 515 |
+
"config_sha256": digest(out / "config.json"),
|
| 516 |
+
"approved_weights_manifest_sha256": (
|
| 517 |
+
digest(os.environ["AI_READI_WEIGHTS_MANIFEST"])
|
| 518 |
+
if os.environ.get("AI_READI_WEIGHTS_MANIFEST")
|
| 519 |
+
else None
|
| 520 |
+
),
|
| 521 |
+
"environment_lock_sha256": (
|
| 522 |
+
digest(os.environ["AI_READI_ENVIRONMENT_LOCK"])
|
| 523 |
+
if os.environ.get("AI_READI_ENVIRONMENT_LOCK")
|
| 524 |
+
else None
|
| 525 |
+
),
|
| 526 |
+
"resume_checkpoint_sha256": (
|
| 527 |
+
digest(args.resume) if args.resume else None
|
| 528 |
+
),
|
| 529 |
+
"process_started_unix": SCRIPT_STARTED,
|
| 530 |
+
"import_and_cache_setup_seconds": time.monotonic() - SCRIPT_TIMER,
|
| 531 |
+
"torch_version": str(torch.__version__),
|
| 532 |
+
"numpy_version": np.__version__,
|
| 533 |
+
"data_source": "AI-READI v3.0.0 external read-only",
|
| 534 |
+
"pretrained_weights": [],
|
| 535 |
+
},
|
| 536 |
+
indent=2,
|
| 537 |
+
)
|
| 538 |
+
)
|
| 539 |
+
dataset = CachedFrames(
|
| 540 |
+
rows, cache, keys, args.packed_cache, config, args.global_cache
|
| 541 |
+
)
|
| 542 |
+
g = torch.Generator().manual_seed(args.seed)
|
| 543 |
+
model = build_model(config).to(args.device)
|
| 544 |
+
ema = build_model(config).to(args.device)
|
| 545 |
+
ema.load_state_dict(model.state_dict())
|
| 546 |
+
ema.requires_grad_(False)
|
| 547 |
+
optimizer = torch.optim.AdamW(
|
| 548 |
+
model.parameters(), lr=args.learning_rate, weight_decay=1e-4
|
| 549 |
+
)
|
| 550 |
+
start_step = 0
|
| 551 |
+
if args.resume:
|
| 552 |
+
ck = torch.load(args.resume, map_location=args.device, weights_only=False)
|
| 553 |
+
if ck["config"]["boundary_keys"] != keys:
|
| 554 |
+
raise ValueError("Checkpoint vocabulary changed")
|
| 555 |
+
state, remapped = remap_state(
|
| 556 |
+
ck.get("raw_model", ck["model"]), ck["config"], config
|
| 557 |
+
)
|
| 558 |
+
ema_state, _ = remap_state(ck["model"], ck["config"], config)
|
| 559 |
+
model.load_state_dict(state)
|
| 560 |
+
ema.load_state_dict(ema_state)
|
| 561 |
+
start_step = ck["step"]
|
| 562 |
+
optimizer_restored = (
|
| 563 |
+
"optimizer" in ck and not remapped and not args.reset_optimizer
|
| 564 |
+
)
|
| 565 |
+
if optimizer_restored:
|
| 566 |
+
optimizer.load_state_dict(ck["optimizer"])
|
| 567 |
+
(out / "resume-mapping.json").write_text(
|
| 568 |
+
json.dumps(
|
| 569 |
+
{
|
| 570 |
+
"source_step": start_step,
|
| 571 |
+
"state_shape_adapted": remapped,
|
| 572 |
+
"head_weights_duplicated": ck["config"].get("model_head_keys", keys)
|
| 573 |
+
!= config.get("model_head_keys", keys),
|
| 574 |
+
"axial_prior_added": args.axial_prior
|
| 575 |
+
and "axial_prior" not in ck["model"],
|
| 576 |
+
"input_channel_mapping": (
|
| 577 |
+
"repeat_parent_filter_and_divide_by_three"
|
| 578 |
+
if ck["config"].get("input_channels", 1) == 1
|
| 579 |
+
and args.input_channels == 3
|
| 580 |
+
else "unchanged"
|
| 581 |
+
),
|
| 582 |
+
"optimizer_restored": optimizer_restored,
|
| 583 |
+
"optimizer_reset_requested": args.reset_optimizer,
|
| 584 |
+
"source_checkpoint_sha256": digest(args.resume),
|
| 585 |
+
},
|
| 586 |
+
indent=2,
|
| 587 |
+
)
|
| 588 |
+
)
|
| 589 |
+
if start_step >= args.steps:
|
| 590 |
+
raise ValueError(
|
| 591 |
+
"--steps is the total final step and must exceed the resumed step"
|
| 592 |
+
)
|
| 593 |
+
draws = torch.multinomial(
|
| 594 |
+
torch.as_tensor(dataset.weights, dtype=torch.double),
|
| 595 |
+
num_samples=(args.steps - start_step) * args.batch_size,
|
| 596 |
+
replacement=True,
|
| 597 |
+
generator=g,
|
| 598 |
+
).numpy()
|
| 599 |
+
loader = DataLoader(
|
| 600 |
+
dataset,
|
| 601 |
+
batch_size=args.batch_size,
|
| 602 |
+
sampler=draws.tolist(),
|
| 603 |
+
num_workers=args.workers,
|
| 604 |
+
pin_memory=args.device.startswith("cuda"),
|
| 605 |
+
worker_init_fn=seed_worker,
|
| 606 |
+
persistent_workers=args.workers > 0,
|
| 607 |
+
)
|
| 608 |
+
use_amp = args.device.startswith("cuda")
|
| 609 |
+
dtype = (
|
| 610 |
+
torch.bfloat16 if use_amp and torch.cuda.is_bf16_supported() else torch.float16
|
| 611 |
+
)
|
| 612 |
+
scaler = torch.amp.GradScaler("cuda", enabled=use_amp and dtype == torch.float16)
|
| 613 |
+
t = time.monotonic()
|
| 614 |
+
running = 0
|
| 615 |
+
step = start_step
|
| 616 |
+
|
| 617 |
+
def save(step, full=False):
|
| 618 |
+
state = {
|
| 619 |
+
"model": {k: v.detach().cpu() for k, v in ema.state_dict().items()},
|
| 620 |
+
"config": config,
|
| 621 |
+
"step": step,
|
| 622 |
+
"seed": args.seed,
|
| 623 |
+
"elapsed_seconds": time.monotonic() - t,
|
| 624 |
+
"start_step": start_step,
|
| 625 |
+
"frame_presentations_this_run": (step - start_step) * args.batch_size,
|
| 626 |
+
}
|
| 627 |
+
path = out / ("resume.pt" if full else f"candidate-{step:06d}.pt")
|
| 628 |
+
if full:
|
| 629 |
+
state.update(raw_model=model.state_dict(), optimizer=optimizer.state_dict())
|
| 630 |
+
consumed = (step - start_step) * args.batch_size
|
| 631 |
+
counts = np.bincount(draws[:consumed], minlength=len(dataset))
|
| 632 |
+
sample_cases = np.asarray([i for i, j in dataset.samples], dtype=np.int32)
|
| 633 |
+
np.savez_compressed(
|
| 634 |
+
out / "training-sample-counts.npz",
|
| 635 |
+
draw_indices=draws[:consumed].astype(np.int32),
|
| 636 |
+
sample_counts=counts,
|
| 637 |
+
case_ids=np.asarray([r["case_id"] for r in rows]),
|
| 638 |
+
case_index=sample_cases,
|
| 639 |
+
cached_frame_index=np.asarray(
|
| 640 |
+
[j for i, j in dataset.samples], dtype=np.int16
|
| 641 |
+
),
|
| 642 |
+
)
|
| 643 |
+
device_usage = {}
|
| 644 |
+
for device in sorted(device_keys):
|
| 645 |
+
used = {
|
| 646 |
+
int(i)
|
| 647 |
+
for i in sample_cases[counts > 0]
|
| 648 |
+
if rows[int(i)]["device"] == device
|
| 649 |
+
}
|
| 650 |
+
device_usage[device] = {
|
| 651 |
+
"volumes_used": len(used),
|
| 652 |
+
"participants_used": len({rows[i]["participant_id"] for i in used}),
|
| 653 |
+
"distinct_cached_frames_used": int(
|
| 654 |
+
sum(
|
| 655 |
+
counts[n] > 0
|
| 656 |
+
for n, (i, j) in enumerate(dataset.samples)
|
| 657 |
+
if rows[i]["device"] == device
|
| 658 |
+
)
|
| 659 |
+
),
|
| 660 |
+
"frame_presentations": int(
|
| 661 |
+
sum(
|
| 662 |
+
counts[n]
|
| 663 |
+
for n, (i, j) in enumerate(dataset.samples)
|
| 664 |
+
if rows[i]["device"] == device
|
| 665 |
+
)
|
| 666 |
+
),
|
| 667 |
+
}
|
| 668 |
+
(out / "trained-cohort-summary.json").write_text(
|
| 669 |
+
json.dumps(
|
| 670 |
+
{
|
| 671 |
+
"step": step,
|
| 672 |
+
"start_step": start_step,
|
| 673 |
+
"presentations_in_this_run": consumed,
|
| 674 |
+
"cache_sampling_sha256": config["cache_sampling_sha256"],
|
| 675 |
+
"seed": args.seed,
|
| 676 |
+
"devices": device_usage,
|
| 677 |
+
},
|
| 678 |
+
indent=2,
|
| 679 |
+
)
|
| 680 |
+
)
|
| 681 |
+
tmp = path.with_suffix(".tmp")
|
| 682 |
+
torch.save(state, tmp)
|
| 683 |
+
tmp.replace(path)
|
| 684 |
+
|
| 685 |
+
model.train()
|
| 686 |
+
with (out / "training.jsonl").open("a") as log:
|
| 687 |
+
for index, (image, pos, valid, original_height) in enumerate(loader):
|
| 688 |
+
next_step = start_step + index + 1
|
| 689 |
+
if next_step > args.steps:
|
| 690 |
+
break
|
| 691 |
+
step = next_step
|
| 692 |
+
image = image.to(args.device, non_blocking=True)
|
| 693 |
+
pos = pos.to(args.device, non_blocking=True)
|
| 694 |
+
valid = valid.to(args.device, non_blocking=True)
|
| 695 |
+
image, pos, valid = augment(image, pos, valid)
|
| 696 |
+
coordinate_scale = (
|
| 697 |
+
original_height.to(args.device, non_blocking=True).float()
|
| 698 |
+
/ image.shape[-2]
|
| 699 |
+
)
|
| 700 |
+
lr = (
|
| 701 |
+
args.learning_rate
|
| 702 |
+
* min(1, step / 500)
|
| 703 |
+
* (0.05 + 0.95 * 0.5 * (1 + math.cos(math.pi * step / args.steps)))
|
| 704 |
+
)
|
| 705 |
+
for group in optimizer.param_groups:
|
| 706 |
+
group["lr"] = lr
|
| 707 |
+
optimizer.zero_grad(set_to_none=True)
|
| 708 |
+
with torch.autocast(
|
| 709 |
+
device_type="cuda" if use_amp else "cpu", dtype=dtype, enabled=use_amp
|
| 710 |
+
):
|
| 711 |
+
if args.auxiliary_region_weight:
|
| 712 |
+
from src.models.auxiliary import auxiliary_loss
|
| 713 |
+
|
| 714 |
+
boundary, regions = model(image, return_aux=True)
|
| 715 |
+
loss = boundary_loss(
|
| 716 |
+
boundary,
|
| 717 |
+
pos,
|
| 718 |
+
valid,
|
| 719 |
+
sigma=args.sigma,
|
| 720 |
+
regression_weight=args.regression_weight,
|
| 721 |
+
coordinate_scale=coordinate_scale,
|
| 722 |
+
regression_loss=args.regression_loss,
|
| 723 |
+
active_head_packing=args.pack_active_heads,
|
| 724 |
+
)
|
| 725 |
+
loss = loss + args.auxiliary_region_weight * auxiliary_loss(
|
| 726 |
+
regions, pos, valid, config
|
| 727 |
+
)
|
| 728 |
+
else:
|
| 729 |
+
loss = boundary_loss(
|
| 730 |
+
model(image),
|
| 731 |
+
pos,
|
| 732 |
+
valid,
|
| 733 |
+
sigma=args.sigma,
|
| 734 |
+
regression_weight=args.regression_weight,
|
| 735 |
+
coordinate_scale=coordinate_scale,
|
| 736 |
+
regression_loss=args.regression_loss,
|
| 737 |
+
active_head_packing=args.pack_active_heads,
|
| 738 |
+
)
|
| 739 |
+
if not torch.isfinite(loss):
|
| 740 |
+
raise FloatingPointError("Nonfinite training loss")
|
| 741 |
+
scaler.scale(loss).backward()
|
| 742 |
+
scaler.unscale_(optimizer)
|
| 743 |
+
torch.nn.utils.clip_grad_norm_(model.parameters(), 5)
|
| 744 |
+
scaler.step(optimizer)
|
| 745 |
+
scaler.update()
|
| 746 |
+
decay = min(0.9995, 1 - 1 / (step + 1))
|
| 747 |
+
with torch.no_grad():
|
| 748 |
+
for e, p in zip(ema.parameters(), model.parameters()):
|
| 749 |
+
e.lerp_(p, 1 - decay)
|
| 750 |
+
running += float(loss.detach())
|
| 751 |
+
if step % 50 == 0:
|
| 752 |
+
record = {
|
| 753 |
+
"step": step,
|
| 754 |
+
"loss": running / 50,
|
| 755 |
+
"learning_rate": lr,
|
| 756 |
+
"elapsed_seconds": time.monotonic() - t,
|
| 757 |
+
"frame_presentations_in_this_run": (step - start_step)
|
| 758 |
+
* args.batch_size,
|
| 759 |
+
}
|
| 760 |
+
log.write(json.dumps(record) + "\n")
|
| 761 |
+
log.flush()
|
| 762 |
+
print(json.dumps(record), flush=True)
|
| 763 |
+
running = 0
|
| 764 |
+
if step % args.save_every == 0:
|
| 765 |
+
save(step)
|
| 766 |
+
save(step, full=True)
|
| 767 |
+
save(step)
|
| 768 |
+
save(step, full=True)
|
| 769 |
+
summary = {
|
| 770 |
+
"step": step,
|
| 771 |
+
"seed": args.seed,
|
| 772 |
+
"training_loop_seconds": time.monotonic() - t,
|
| 773 |
+
"process_seconds": time.monotonic() - SCRIPT_TIMER,
|
| 774 |
+
"process_started_unix": SCRIPT_STARTED,
|
| 775 |
+
"device": args.device,
|
| 776 |
+
"cuda_version": torch.version.cuda,
|
| 777 |
+
"gpu_name": torch.cuda.get_device_name() if use_amp else None,
|
| 778 |
+
"peak_cuda_allocated_bytes": (
|
| 779 |
+
torch.cuda.max_memory_allocated() if use_amp else None
|
| 780 |
+
),
|
| 781 |
+
"autocast_dtype": str(dtype) if use_amp else None,
|
| 782 |
+
"batch_size": args.batch_size,
|
| 783 |
+
"source_hashes": source_hashes(),
|
| 784 |
+
}
|
| 785 |
+
(out / "run-summary.json").write_text(json.dumps(summary, indent=2))
|
| 786 |
+
print(json.dumps(summary), flush=True)
|
| 787 |
+
|
| 788 |
+
|
| 789 |
+
if __name__ == "__main__":
|
| 790 |
+
main()
|
src/viewer.js
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
(id, action) => {
|
| 2 |
+
const image = document.getElementById(id)?.querySelector(".image-frame img");
|
| 3 |
+
if (!image?.naturalWidth) return;
|
| 4 |
+
const viewport = image.closest("button");
|
| 5 |
+
const fresh = !image.octZoom;
|
| 6 |
+
const state = image.octZoom ??= { scale: 1, x: 0, y: 0, drag: null };
|
| 7 |
+
const paint = () => {
|
| 8 |
+
const bounds = viewport.getBoundingClientRect();
|
| 9 |
+
if (!bounds.width || !bounds.height) return;
|
| 10 |
+
const fit = Math.min(
|
| 11 |
+
image.clientWidth / image.naturalWidth,
|
| 12 |
+
image.clientHeight / image.naturalHeight,
|
| 13 |
+
1
|
| 14 |
+
);
|
| 15 |
+
const limitX = Math.max(0, (image.naturalWidth * fit * state.scale - bounds.width) / 2);
|
| 16 |
+
const limitY = Math.max(0, (image.naturalHeight * fit * state.scale - bounds.height) / 2);
|
| 17 |
+
state.x = Math.max(-limitX, Math.min(limitX, state.x));
|
| 18 |
+
state.y = Math.max(-limitY, Math.min(limitY, state.y));
|
| 19 |
+
image.style.transformOrigin = "center";
|
| 20 |
+
image.style.transform = `translate(${state.x}px, ${state.y}px) scale(${state.scale})`;
|
| 21 |
+
viewport.style.overflow = "hidden";
|
| 22 |
+
viewport.style.cursor = state.scale > 1 ? "grab" : "";
|
| 23 |
+
viewport.style.touchAction = state.scale > 1 ? "none" : "";
|
| 24 |
+
};
|
| 25 |
+
if (fresh) {
|
| 26 |
+
image.draggable = false;
|
| 27 |
+
viewport.addEventListener("pointerdown", (event) => {
|
| 28 |
+
if (state.scale === 1 || event.button !== 0) return;
|
| 29 |
+
event.preventDefault();
|
| 30 |
+
viewport.setPointerCapture(event.pointerId);
|
| 31 |
+
state.drag = { id: event.pointerId, x: event.clientX, y: event.clientY };
|
| 32 |
+
});
|
| 33 |
+
viewport.addEventListener("pointermove", (event) => {
|
| 34 |
+
if (state.drag?.id !== event.pointerId) return;
|
| 35 |
+
state.x += event.clientX - state.drag.x;
|
| 36 |
+
state.y += event.clientY - state.drag.y;
|
| 37 |
+
state.drag.x = event.clientX;
|
| 38 |
+
state.drag.y = event.clientY;
|
| 39 |
+
paint();
|
| 40 |
+
});
|
| 41 |
+
for (const event of ["pointerup", "pointercancel", "lostpointercapture"]) {
|
| 42 |
+
viewport.addEventListener(event, () => { state.drag = null; });
|
| 43 |
+
}
|
| 44 |
+
image.addEventListener("load", paint);
|
| 45 |
+
}
|
| 46 |
+
state.scale = action === "fit" ? 1 : Math.max(
|
| 47 |
+
1, Math.min(16, state.scale * (action === "in" ? 1.5 : 1 / 1.5))
|
| 48 |
+
);
|
| 49 |
+
paint();
|
| 50 |
+
}
|
src/viewer.py
ADDED
|
@@ -0,0 +1,637 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Local DICOM viewing and inference adapter for the retained OCT submission.
|
| 2 |
+
|
| 3 |
+
The scientific model, normalization, head combinations and saved postprocessing
|
| 4 |
+
are imported from the researcher's original files. This module adds upload,
|
| 5 |
+
session and display handling; it does not retrain or alter the checkpoint.
|
| 6 |
+
"""
|
| 7 |
+
|
| 8 |
+
from __future__ import annotations
|
| 9 |
+
|
| 10 |
+
from src.paths import PROJECT_ROOT
|
| 11 |
+
|
| 12 |
+
from collections import OrderedDict
|
| 13 |
+
from dataclasses import dataclass, field
|
| 14 |
+
from pathlib import Path
|
| 15 |
+
from threading import Lock, RLock
|
| 16 |
+
from typing import Iterator
|
| 17 |
+
import hashlib
|
| 18 |
+
import html
|
| 19 |
+
import json
|
| 20 |
+
import math
|
| 21 |
+
import os
|
| 22 |
+
import shutil
|
| 23 |
+
import tempfile
|
| 24 |
+
import time
|
| 25 |
+
import uuid
|
| 26 |
+
|
| 27 |
+
import numpy as np
|
| 28 |
+
from PIL import Image, ImageDraw
|
| 29 |
+
import pydicom
|
| 30 |
+
import torch
|
| 31 |
+
from torch.nn import functional as F
|
| 32 |
+
|
| 33 |
+
from src.models import build_model, output_indices
|
| 34 |
+
from src.inference.context import OFFSETS, iter_normalized_contexts
|
| 35 |
+
from src.inference.runtime import configure_inference, autocast_options
|
| 36 |
+
from src.io import volume_headers, read_frame, read_frames, normalize_frame
|
| 37 |
+
from src.inference.decoding import positions_from_logits
|
| 38 |
+
from src.inference.combination import combine_named_heads, finish_positions
|
| 39 |
+
|
| 40 |
+
ROOT = PROJECT_ROOT
|
| 41 |
+
CHECKPOINT = ROOT / "artifacts/checkpoint.pt"
|
| 42 |
+
STRUCTURAL_OCT = "1.2.840.10008.5.1.4.1.1.77.1.5.4"
|
| 43 |
+
FAMILIES = {
|
| 44 |
+
"heidelberg_spectralis": "Heidelberg Spectralis",
|
| 45 |
+
"topcon_maestro2": "Topcon Maestro2",
|
| 46 |
+
"topcon_triton": "Topcon Triton",
|
| 47 |
+
"zeiss_cirrus": "Zeiss Cirrus",
|
| 48 |
+
}
|
| 49 |
+
AUTO = "auto"
|
| 50 |
+
NAMES = {
|
| 51 |
+
"SCT_280677004": "ILM",
|
| 52 |
+
"DCM_128289": "RNFL · outer",
|
| 53 |
+
"DCM_128290": "GCL · outer",
|
| 54 |
+
"DCM_128291": "IPL · outer",
|
| 55 |
+
"DCM_128292": "INL · outer",
|
| 56 |
+
"DCM_128293": "OPL · outer",
|
| 57 |
+
"SCT_76710003": "ELM",
|
| 58 |
+
"DCM_128320": "EZ · inner",
|
| 59 |
+
"DCM_128321": "EZ · midline",
|
| 60 |
+
"DCM_128323": "Interdigitation zone · inner",
|
| 61 |
+
"DCM_128297": "RPE · inner",
|
| 62 |
+
"DCM_128299": "RPE · outer",
|
| 63 |
+
"DCM_128300": "Bruch’s membrane · outer",
|
| 64 |
+
"DCM_128298": "RPE · centre",
|
| 65 |
+
"DCM_128301": "Choroid–sclera interface",
|
| 66 |
+
}
|
| 67 |
+
PALETTE = [
|
| 68 |
+
"#22d3ee",
|
| 69 |
+
"#a3e635",
|
| 70 |
+
"#fbbf24",
|
| 71 |
+
"#fb7185",
|
| 72 |
+
"#c084fc",
|
| 73 |
+
"#34d399",
|
| 74 |
+
"#f472b6",
|
| 75 |
+
"#60a5fa",
|
| 76 |
+
"#f97316",
|
| 77 |
+
"#e879f9",
|
| 78 |
+
"#2dd4bf",
|
| 79 |
+
"#fde047",
|
| 80 |
+
"#a5b4fc",
|
| 81 |
+
"#fda4af",
|
| 82 |
+
"#d9f99d",
|
| 83 |
+
]
|
| 84 |
+
COLORS = {key: PALETTE[i % len(PALETTE)] for i, key in enumerate(NAMES)}
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
class ViewerError(ValueError):
|
| 88 |
+
"""A recoverable error suitable for displaying in the viewer."""
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
@dataclass
|
| 92 |
+
class Prediction:
|
| 93 |
+
positions: np.ndarray # K, number of predicted B-scans, original A
|
| 94 |
+
keys: list[str]
|
| 95 |
+
frames: list[int]
|
| 96 |
+
family: str
|
| 97 |
+
compute: str
|
| 98 |
+
complete_volume: bool
|
| 99 |
+
seconds: float
|
| 100 |
+
export: Path
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
@dataclass
|
| 104 |
+
class Volume:
|
| 105 |
+
identity: str
|
| 106 |
+
directory: Path
|
| 107 |
+
paths: list[Path]
|
| 108 |
+
headers: list
|
| 109 |
+
shape: tuple[int, int, int]
|
| 110 |
+
detected_family: str | None
|
| 111 |
+
axial_mm: float | None
|
| 112 |
+
lateral_mm: float | None
|
| 113 |
+
filename: str
|
| 114 |
+
prediction: Prediction | None = None
|
| 115 |
+
view_frame: int = 0
|
| 116 |
+
view_settings: tuple | None = None
|
| 117 |
+
frames: OrderedDict = field(default_factory=OrderedDict)
|
| 118 |
+
cancelled: bool = False
|
| 119 |
+
updated: float = field(default_factory=time.monotonic)
|
| 120 |
+
|
| 121 |
+
def frame(self, index: int) -> np.ndarray:
|
| 122 |
+
index = max(0, min(int(index), self.shape[0] - 1))
|
| 123 |
+
self.updated = time.monotonic()
|
| 124 |
+
if index not in self.frames:
|
| 125 |
+
try:
|
| 126 |
+
pixels = np.asarray(read_frame(self.headers, index))
|
| 127 |
+
except Exception as exc:
|
| 128 |
+
raise ViewerError(
|
| 129 |
+
"Could not decode this DICOM. Install requirements.txt "
|
| 130 |
+
"for JPEG2000 and lossless JPEG support. " + str(exc)
|
| 131 |
+
) from exc
|
| 132 |
+
if pixels.shape != self.shape[1:]:
|
| 133 |
+
raise ViewerError(
|
| 134 |
+
"Decoded image dimensions do not match the DICOM header."
|
| 135 |
+
)
|
| 136 |
+
self.frames[index] = pixels
|
| 137 |
+
while len(self.frames) > 8:
|
| 138 |
+
self.frames.popitem(last=False)
|
| 139 |
+
self.frames.move_to_end(index)
|
| 140 |
+
return self.frames[index]
|
| 141 |
+
|
| 142 |
+
|
| 143 |
+
class SessionStore:
|
| 144 |
+
def __init__(self):
|
| 145 |
+
self.volumes: dict[str, Volume] = {}
|
| 146 |
+
self.lock = RLock()
|
| 147 |
+
|
| 148 |
+
def add(self, volume: Volume) -> str:
|
| 149 |
+
with self.lock:
|
| 150 |
+
self.reap()
|
| 151 |
+
self.volumes[volume.identity] = volume
|
| 152 |
+
return volume.identity
|
| 153 |
+
|
| 154 |
+
def get(self, identity: str | None) -> Volume:
|
| 155 |
+
with self.lock:
|
| 156 |
+
if not identity or identity not in self.volumes:
|
| 157 |
+
raise ViewerError("Upload a structural OCT DICOM first.")
|
| 158 |
+
volume = self.volumes[identity]
|
| 159 |
+
volume.updated = time.monotonic()
|
| 160 |
+
return volume
|
| 161 |
+
|
| 162 |
+
def remove(self, identity: str | None):
|
| 163 |
+
with self.lock:
|
| 164 |
+
volume = self.volumes.pop(identity, None)
|
| 165 |
+
if volume:
|
| 166 |
+
volume.cancelled = True
|
| 167 |
+
shutil.rmtree(volume.directory, ignore_errors=True)
|
| 168 |
+
|
| 169 |
+
def reap(self):
|
| 170 |
+
for identity, volume in list(self.volumes.items()):
|
| 171 |
+
if time.monotonic() - volume.updated > 7200:
|
| 172 |
+
self.remove(identity)
|
| 173 |
+
|
| 174 |
+
|
| 175 |
+
STORE = SessionStore()
|
| 176 |
+
|
| 177 |
+
|
| 178 |
+
def detect_family(header) -> str | None:
|
| 179 |
+
description = " ".join(
|
| 180 |
+
str(header.get(tag, ""))
|
| 181 |
+
for tag in ("Manufacturer", "ManufacturerModelName", "SeriesDescription")
|
| 182 |
+
).lower()
|
| 183 |
+
if "spectralis" in description or "heidelberg" in description:
|
| 184 |
+
return "heidelberg_spectralis"
|
| 185 |
+
if "maestro" in description:
|
| 186 |
+
return "topcon_maestro2"
|
| 187 |
+
if "triton" in description:
|
| 188 |
+
return "topcon_triton"
|
| 189 |
+
if "cirrus" in description or "zeiss" in description:
|
| 190 |
+
return "zeiss_cirrus"
|
| 191 |
+
return None
|
| 192 |
+
|
| 193 |
+
|
| 194 |
+
def pixel_spacing(header) -> tuple[float | None, float | None]:
|
| 195 |
+
candidates = []
|
| 196 |
+
for key in ("SharedFunctionalGroupsSequence", "PerFrameFunctionalGroupsSequence"):
|
| 197 |
+
sequence = header.get(key, [])
|
| 198 |
+
if sequence:
|
| 199 |
+
measures = sequence[0].get("PixelMeasuresSequence", [])
|
| 200 |
+
if measures:
|
| 201 |
+
candidates.append(measures[0].get("PixelSpacing"))
|
| 202 |
+
candidates.append(header.get("PixelSpacing"))
|
| 203 |
+
for values in candidates:
|
| 204 |
+
if values is not None and len(values) == 2:
|
| 205 |
+
row, col = map(float, values)
|
| 206 |
+
if math.isfinite(row) and math.isfinite(col) and row > 0 and col > 0:
|
| 207 |
+
return row, col
|
| 208 |
+
return None, None
|
| 209 |
+
|
| 210 |
+
|
| 211 |
+
def load_upload(files: list[str] | str) -> Volume:
|
| 212 |
+
if isinstance(files, str):
|
| 213 |
+
files = [files]
|
| 214 |
+
if not files:
|
| 215 |
+
raise ViewerError("Choose a .dcm file to begin.")
|
| 216 |
+
directory = Path(tempfile.mkdtemp(prefix="myxos-oct-viewer-"))
|
| 217 |
+
os.chmod(directory, 0o700)
|
| 218 |
+
try:
|
| 219 |
+
paths = []
|
| 220 |
+
all_headers = []
|
| 221 |
+
for index, uploaded in enumerate(files):
|
| 222 |
+
source = Path(uploaded)
|
| 223 |
+
if not source.is_file():
|
| 224 |
+
raise ViewerError(
|
| 225 |
+
"An uploaded DICOM is no longer available. Upload it again."
|
| 226 |
+
)
|
| 227 |
+
# A private copy decouples inference from Gradio's upload-cache lifetime.
|
| 228 |
+
path = directory / f"part-{index:03d}.dcm"
|
| 229 |
+
shutil.copyfile(source, path)
|
| 230 |
+
os.chmod(path, 0o600)
|
| 231 |
+
header = pydicom.dcmread(path, stop_before_pixels=True)
|
| 232 |
+
if str(header.get("SOPClassUID", "")) != STRUCTURAL_OCT:
|
| 233 |
+
raise ViewerError(
|
| 234 |
+
"This is not a structural OCT DICOM. Upload the OCT volume, rather than an OCTA or segmentation export."
|
| 235 |
+
)
|
| 236 |
+
if int(header.get("SamplesPerPixel", 1)) != 1:
|
| 237 |
+
raise ViewerError(
|
| 238 |
+
"The selected checkpoint expects grayscale structural OCT."
|
| 239 |
+
)
|
| 240 |
+
all_headers.append(header)
|
| 241 |
+
paths.append(path)
|
| 242 |
+
for tag in ("StudyInstanceUID", "SeriesInstanceUID", "ConcatenationUID"):
|
| 243 |
+
identifiers = {str(h.get(tag)) for h in all_headers if h.get(tag)}
|
| 244 |
+
if len(identifiers) > 1:
|
| 245 |
+
raise ViewerError(
|
| 246 |
+
"Upload one OCT volume, or the contiguous DICOM parts of that same volume."
|
| 247 |
+
)
|
| 248 |
+
headers, shape = volume_headers(directory, [p.name for p in paths])
|
| 249 |
+
if not all(int(n) > 0 for n in shape):
|
| 250 |
+
raise ViewerError("The DICOM contains an empty volume.")
|
| 251 |
+
axial, lateral = pixel_spacing(all_headers[0])
|
| 252 |
+
volume = Volume(
|
| 253 |
+
uuid.uuid4().hex,
|
| 254 |
+
directory,
|
| 255 |
+
paths,
|
| 256 |
+
headers,
|
| 257 |
+
tuple(shape),
|
| 258 |
+
detect_family(all_headers[0]),
|
| 259 |
+
axial,
|
| 260 |
+
lateral,
|
| 261 |
+
Path(files[0]).name,
|
| 262 |
+
)
|
| 263 |
+
# Fail early when a required codec is missing.
|
| 264 |
+
volume.frame((shape[0] - 1) // 2)
|
| 265 |
+
return volume
|
| 266 |
+
except ViewerError:
|
| 267 |
+
shutil.rmtree(directory, ignore_errors=True)
|
| 268 |
+
raise
|
| 269 |
+
except Exception as exc:
|
| 270 |
+
shutil.rmtree(directory, ignore_errors=True)
|
| 271 |
+
raise ViewerError("Unable to load this OCT volume: " + str(exc)) from exc
|
| 272 |
+
|
| 273 |
+
|
| 274 |
+
def resolve_family(volume: Volume, selected: str) -> str:
|
| 275 |
+
family = volume.detected_family if selected == AUTO else selected
|
| 276 |
+
if family not in FAMILIES:
|
| 277 |
+
raise ViewerError(
|
| 278 |
+
"The scanner could not be identified. Select its scanner family below."
|
| 279 |
+
)
|
| 280 |
+
return family
|
| 281 |
+
|
| 282 |
+
|
| 283 |
+
def boundary_choices(family: str | None) -> list[tuple[str, str]]:
|
| 284 |
+
cfg = json.loads((ROOT / "artifacts/config.json").read_text())
|
| 285 |
+
keys = cfg["device_keys"].get(family, [])
|
| 286 |
+
return [(NAMES.get(key, key), key) for key in keys]
|
| 287 |
+
|
| 288 |
+
|
| 289 |
+
def compute_choices() -> list[tuple[str, str]]:
|
| 290 |
+
choices = [("Automatic", "auto"), ("CPU", "cpu")]
|
| 291 |
+
if torch.cuda.is_available():
|
| 292 |
+
choices.append(("NVIDIA GPU · CUDA", "cuda"))
|
| 293 |
+
if torch.backends.mps.is_available():
|
| 294 |
+
choices.append(("Apple GPU · MPS", "mps"))
|
| 295 |
+
return choices
|
| 296 |
+
|
| 297 |
+
|
| 298 |
+
def resolve_compute(selected: str) -> str:
|
| 299 |
+
if selected == "auto":
|
| 300 |
+
return (
|
| 301 |
+
"cuda"
|
| 302 |
+
if torch.cuda.is_available()
|
| 303 |
+
else ("mps" if torch.backends.mps.is_available() else "cpu")
|
| 304 |
+
)
|
| 305 |
+
if selected not in {value for _, value in compute_choices()}:
|
| 306 |
+
raise ViewerError("That compute device is not available on this machine.")
|
| 307 |
+
return selected
|
| 308 |
+
|
| 309 |
+
|
| 310 |
+
def selected_contexts(headers, frames: list[int], shapes: list[tuple]):
|
| 311 |
+
total = sum(int(ds.get("NumberOfFrames", 1)) for _, ds in headers)
|
| 312 |
+
indices = set()
|
| 313 |
+
for frame in frames:
|
| 314 |
+
for shape in shapes:
|
| 315 |
+
indices.update(
|
| 316 |
+
max(0, min(total - 1, frame + offset)) for offset in OFFSETS[shape[2]]
|
| 317 |
+
)
|
| 318 |
+
if shape[2] == 6:
|
| 319 |
+
indices.update([0, total // 2, total - 1])
|
| 320 |
+
raw = read_frames(headers, sorted(indices))
|
| 321 |
+
normalized = {}
|
| 322 |
+
for frame in frames:
|
| 323 |
+
images = []
|
| 324 |
+
for h, a, channels in shapes:
|
| 325 |
+
context = [
|
| 326 |
+
max(0, min(total - 1, frame + offset)) for offset in OFFSETS[channels]
|
| 327 |
+
]
|
| 328 |
+
if channels == 6:
|
| 329 |
+
context += [0, total // 2, total - 1]
|
| 330 |
+
channels_out = []
|
| 331 |
+
for index in context:
|
| 332 |
+
key = index, h, a
|
| 333 |
+
if key not in normalized:
|
| 334 |
+
normalized[key] = normalize_frame(raw[index], (h, a))
|
| 335 |
+
channels_out.append(normalized[key])
|
| 336 |
+
images.append(np.stack(channels_out))
|
| 337 |
+
yield images
|
| 338 |
+
|
| 339 |
+
|
| 340 |
+
class InferenceEngine:
|
| 341 |
+
def __init__(self):
|
| 342 |
+
# A plain Lock can span generator yields, unlike thread-owned RLock.
|
| 343 |
+
self.lock = Lock()
|
| 344 |
+
self.checkpoint = None
|
| 345 |
+
self.models = {}
|
| 346 |
+
self.device = None
|
| 347 |
+
|
| 348 |
+
def load(self, device: str):
|
| 349 |
+
if self.checkpoint is None:
|
| 350 |
+
self.checkpoint = torch.load(
|
| 351 |
+
CHECKPOINT, map_location="cpu", weights_only=True
|
| 352 |
+
)
|
| 353 |
+
if self.checkpoint["config"]["architecture"] != "BoundaryEnsemble":
|
| 354 |
+
raise ViewerError(
|
| 355 |
+
"This viewer expects the retained Researcher 1 ensemble checkpoint."
|
| 356 |
+
)
|
| 357 |
+
if self.device != device:
|
| 358 |
+
self.models.clear()
|
| 359 |
+
self.device = device
|
| 360 |
+
if torch.cuda.is_available():
|
| 361 |
+
torch.cuda.empty_cache()
|
| 362 |
+
if torch.backends.mps.is_available():
|
| 363 |
+
torch.mps.empty_cache()
|
| 364 |
+
return self.checkpoint
|
| 365 |
+
|
| 366 |
+
def members(self, checkpoint, family):
|
| 367 |
+
cfg = checkpoint["config"]
|
| 368 |
+
combination = cfg["combination"]
|
| 369 |
+
active = None
|
| 370 |
+
if "head_weights_by_device" in combination:
|
| 371 |
+
active = {
|
| 372 |
+
name
|
| 373 |
+
for rule in combination["head_weights_by_device"][family].values()
|
| 374 |
+
for name in rule
|
| 375 |
+
}
|
| 376 |
+
elif "head_source_by_device" in combination:
|
| 377 |
+
active = set(combination["head_source_by_device"][family].values())
|
| 378 |
+
result = []
|
| 379 |
+
for saved in checkpoint["members"]:
|
| 380 |
+
if active is not None and saved["name"] not in active:
|
| 381 |
+
continue
|
| 382 |
+
if saved["name"] not in self.models:
|
| 383 |
+
model = build_model(saved["config"])
|
| 384 |
+
model.load_state_dict(saved["model"], strict=True)
|
| 385 |
+
self.models[saved["name"]] = (
|
| 386 |
+
model.to(self.device).eval().requires_grad_(False)
|
| 387 |
+
)
|
| 388 |
+
result.append(
|
| 389 |
+
{
|
| 390 |
+
"name": saved["name"],
|
| 391 |
+
"config": saved["config"],
|
| 392 |
+
"model": self.models[saved["name"]],
|
| 393 |
+
}
|
| 394 |
+
)
|
| 395 |
+
return result
|
| 396 |
+
|
| 397 |
+
def predict(
|
| 398 |
+
self,
|
| 399 |
+
volume: Volume,
|
| 400 |
+
family: str,
|
| 401 |
+
compute: str,
|
| 402 |
+
batch_size: int,
|
| 403 |
+
full_volume: bool,
|
| 404 |
+
frame_index: int,
|
| 405 |
+
) -> Iterator[dict]:
|
| 406 |
+
device = resolve_compute(compute)
|
| 407 |
+
batch_size = max(1, min(32, int(batch_size)))
|
| 408 |
+
b, h, a = volume.shape
|
| 409 |
+
frames = (
|
| 410 |
+
list(range(b)) if full_volume else [max(0, min(b - 1, int(frame_index)))]
|
| 411 |
+
)
|
| 412 |
+
started = time.monotonic()
|
| 413 |
+
volume.cancelled = False
|
| 414 |
+
with self.lock:
|
| 415 |
+
configure_inference("fp32")
|
| 416 |
+
checkpoint = self.load(device)
|
| 417 |
+
members = self.members(checkpoint, family)
|
| 418 |
+
cfg = checkpoint["config"]
|
| 419 |
+
keys = cfg["device_keys"][family]
|
| 420 |
+
shapes = sorted(
|
| 421 |
+
{
|
| 422 |
+
(
|
| 423 |
+
m["config"]["height"],
|
| 424 |
+
m["config"]["width"],
|
| 425 |
+
m["config"].get("input_channels", 1),
|
| 426 |
+
)
|
| 427 |
+
for m in members
|
| 428 |
+
}
|
| 429 |
+
)
|
| 430 |
+
buffers = [
|
| 431 |
+
np.empty((len(keys), len(frames), a), np.float32) for _ in members
|
| 432 |
+
]
|
| 433 |
+
iterator = (
|
| 434 |
+
iter_normalized_contexts(volume.headers, shapes)
|
| 435 |
+
if full_volume
|
| 436 |
+
else selected_contexts(volume.headers, frames, shapes)
|
| 437 |
+
)
|
| 438 |
+
batch = []
|
| 439 |
+
completed = 0
|
| 440 |
+
for images in iterator:
|
| 441 |
+
if volume.cancelled:
|
| 442 |
+
raise ViewerError("Segmentation cancelled.")
|
| 443 |
+
batch.append(images)
|
| 444 |
+
if len(batch) < batch_size and completed + len(batch) < len(frames):
|
| 445 |
+
continue
|
| 446 |
+
# Do not keep thread-local inference contexts open across yields.
|
| 447 |
+
with torch.inference_mode(), torch.autocast(
|
| 448 |
+
**autocast_options(device, "fp32")
|
| 449 |
+
):
|
| 450 |
+
tensors = [
|
| 451 |
+
torch.from_numpy(np.stack([item[i] for item in batch])).to(
|
| 452 |
+
device
|
| 453 |
+
)
|
| 454 |
+
for i in range(len(shapes))
|
| 455 |
+
]
|
| 456 |
+
for member, buffer in zip(members, buffers):
|
| 457 |
+
own = member["config"]
|
| 458 |
+
shape = (
|
| 459 |
+
own["height"],
|
| 460 |
+
own["width"],
|
| 461 |
+
own.get("input_channels", 1),
|
| 462 |
+
)
|
| 463 |
+
indices = output_indices(own, family)
|
| 464 |
+
logits = member["model"](tensors[shapes.index(shape)])[
|
| 465 |
+
:, indices
|
| 466 |
+
]
|
| 467 |
+
positions = positions_from_logits(logits, own, family)
|
| 468 |
+
positions = F.interpolate(
|
| 469 |
+
positions, size=a, mode="linear", align_corners=False
|
| 470 |
+
)
|
| 471 |
+
positions = ((positions + 0.5) * h / own["height"] - 0.5).clamp(
|
| 472 |
+
0, h - 1
|
| 473 |
+
)
|
| 474 |
+
order = [own["device_keys"][family].index(key) for key in keys]
|
| 475 |
+
values = (
|
| 476 |
+
positions.float().cpu().numpy().transpose(1, 0, 2)[order]
|
| 477 |
+
)
|
| 478 |
+
buffer[:, completed : completed + len(batch)] = values
|
| 479 |
+
del logits, positions
|
| 480 |
+
completed += len(batch)
|
| 481 |
+
batch = []
|
| 482 |
+
volume.updated = time.monotonic()
|
| 483 |
+
yield {
|
| 484 |
+
"completed": completed,
|
| 485 |
+
"total": len(frames),
|
| 486 |
+
"device": device,
|
| 487 |
+
"seconds": time.monotonic() - started,
|
| 488 |
+
}
|
| 489 |
+
if volume.cancelled:
|
| 490 |
+
raise ViewerError("Segmentation cancelled.")
|
| 491 |
+
components = [
|
| 492 |
+
finish_positions(
|
| 493 |
+
values,
|
| 494 |
+
family,
|
| 495 |
+
h,
|
| 496 |
+
member["config"].get("inference", {}).get("postprocess", {}),
|
| 497 |
+
)
|
| 498 |
+
for values, member in zip(buffers, members)
|
| 499 |
+
]
|
| 500 |
+
positions = combine_named_heads(
|
| 501 |
+
components,
|
| 502 |
+
[m["name"] for m in members],
|
| 503 |
+
keys,
|
| 504 |
+
family,
|
| 505 |
+
cfg["combination"],
|
| 506 |
+
)
|
| 507 |
+
positions = finish_positions(
|
| 508 |
+
positions, family, h, cfg.get("inference", {}).get("postprocess", {})
|
| 509 |
+
)
|
| 510 |
+
if completed != len(frames) or not np.isfinite(positions).all():
|
| 511 |
+
raise ViewerError(
|
| 512 |
+
"Inference did not produce complete finite boundary predictions."
|
| 513 |
+
)
|
| 514 |
+
suffix = "volume" if full_volume else f"preview-bscan-{frames[0] + 1:04d}"
|
| 515 |
+
output = volume.directory / f"boundaries-{suffix}.npz"
|
| 516 |
+
arrays = {"positions": positions, "boundary_keys": np.asarray(keys)}
|
| 517 |
+
if not full_volume:
|
| 518 |
+
arrays["frame_indices"] = np.asarray(frames, dtype=np.int32)
|
| 519 |
+
np.savez_compressed(output, **arrays)
|
| 520 |
+
prediction = Prediction(
|
| 521 |
+
positions,
|
| 522 |
+
list(keys),
|
| 523 |
+
frames,
|
| 524 |
+
family,
|
| 525 |
+
device,
|
| 526 |
+
full_volume,
|
| 527 |
+
time.monotonic() - started,
|
| 528 |
+
output,
|
| 529 |
+
)
|
| 530 |
+
volume.prediction = prediction
|
| 531 |
+
yield {"result": prediction}
|
| 532 |
+
|
| 533 |
+
|
| 534 |
+
ENGINE = InferenceEngine()
|
| 535 |
+
|
| 536 |
+
|
| 537 |
+
def display_dimensions(volume: Volume, physical: bool) -> tuple[int, int]:
|
| 538 |
+
_, h, a = volume.shape
|
| 539 |
+
ratio = h / a
|
| 540 |
+
if physical and volume.axial_mm and volume.lateral_mm:
|
| 541 |
+
ratio *= volume.axial_mm / volume.lateral_mm
|
| 542 |
+
width = 1000
|
| 543 |
+
height = max(1, round(width * ratio))
|
| 544 |
+
scale = min(1.0, 1400 / max(width, height))
|
| 545 |
+
return max(1, round(width * scale)), max(1, round(height * scale))
|
| 546 |
+
|
| 547 |
+
|
| 548 |
+
def render(
|
| 549 |
+
volume: Volume,
|
| 550 |
+
index: int,
|
| 551 |
+
selected_keys: list[str] | None = None,
|
| 552 |
+
overlay: bool = True,
|
| 553 |
+
opacity: float = 0.9,
|
| 554 |
+
line_width: int = 2,
|
| 555 |
+
labels: bool = False,
|
| 556 |
+
contrast: float = 1.0,
|
| 557 |
+
brightness: float = 0.0,
|
| 558 |
+
physical: bool = True,
|
| 559 |
+
) -> tuple[np.ndarray, np.ndarray | None]:
|
| 560 |
+
index = max(0, min(volume.shape[0] - 1, int(index)))
|
| 561 |
+
image = np.asarray(volume.frame(index), dtype=np.float32)
|
| 562 |
+
finite = image[np.isfinite(image)]
|
| 563 |
+
lo, hi = np.quantile(finite, [0.01, 0.995]) if finite.size else (0, 1)
|
| 564 |
+
gray = np.nan_to_num((image - lo) / max(float(hi - lo), 1e-6))
|
| 565 |
+
gray = np.clip((gray - 0.5) * float(contrast) + 0.5 + float(brightness), 0, 1)
|
| 566 |
+
width, height = display_dimensions(volume, physical)
|
| 567 |
+
base = (
|
| 568 |
+
Image.fromarray(np.uint8(np.round(gray * 255)))
|
| 569 |
+
.convert("RGB")
|
| 570 |
+
.resize((width, height), Image.Resampling.BILINEAR)
|
| 571 |
+
)
|
| 572 |
+
raw = np.asarray(base)
|
| 573 |
+
prediction = volume.prediction
|
| 574 |
+
if prediction is None or index not in prediction.frames:
|
| 575 |
+
return raw, None
|
| 576 |
+
if not overlay:
|
| 577 |
+
return raw, raw.copy()
|
| 578 |
+
frame = prediction.frames.index(index)
|
| 579 |
+
selected = set(prediction.keys if selected_keys is None else selected_keys)
|
| 580 |
+
layer = base.convert("RGBA")
|
| 581 |
+
annotation = Image.new("RGBA", base.size)
|
| 582 |
+
draw = ImageDraw.Draw(annotation)
|
| 583 |
+
_, native_h, native_a = volume.shape
|
| 584 |
+
x = np.linspace(0, width - 1, native_a)
|
| 585 |
+
for key, values in zip(prediction.keys, prediction.positions[:, frame]):
|
| 586 |
+
if key not in selected:
|
| 587 |
+
continue
|
| 588 |
+
y = np.clip(values, 0, native_h - 1) * (height - 1) / max(1, native_h - 1)
|
| 589 |
+
color = COLORS.get(key, "#ffffff")
|
| 590 |
+
rgb = tuple(int(color[i : i + 2], 16) for i in (1, 3, 5))
|
| 591 |
+
points = list(zip(x.tolist(), y.tolist()))
|
| 592 |
+
if len(points) > 1:
|
| 593 |
+
draw.line(
|
| 594 |
+
points,
|
| 595 |
+
fill=(*rgb, round(255 * float(opacity))),
|
| 596 |
+
width=max(1, int(line_width)),
|
| 597 |
+
joint="curve",
|
| 598 |
+
)
|
| 599 |
+
if labels:
|
| 600 |
+
text = NAMES.get(key, key)
|
| 601 |
+
anchor = max(
|
| 602 |
+
0,
|
| 603 |
+
min(
|
| 604 |
+
height - 14,
|
| 605 |
+
round(float(np.median(y[: max(1, native_a // 8)])) - 13),
|
| 606 |
+
),
|
| 607 |
+
)
|
| 608 |
+
box = draw.textbbox((8, anchor), text)
|
| 609 |
+
draw.rectangle(
|
| 610 |
+
(box[0] - 3, box[1] - 2, box[2] + 3, box[3] + 2), fill=(8, 15, 26, 210)
|
| 611 |
+
)
|
| 612 |
+
draw.text((8, anchor), text, fill=(*rgb, 255))
|
| 613 |
+
return raw, np.asarray(Image.alpha_composite(layer, annotation).convert("RGB"))
|
| 614 |
+
|
| 615 |
+
|
| 616 |
+
def legend(keys: list[str]) -> str:
|
| 617 |
+
if not keys:
|
| 618 |
+
return "Boundary colours appear after a scan is loaded."
|
| 619 |
+
items = []
|
| 620 |
+
for key in keys:
|
| 621 |
+
items.append(
|
| 622 |
+
f'<span style="color:{COLORS.get(key, "#94a3b8")}">●</span> {html.escape(NAMES.get(key, key))}'
|
| 623 |
+
)
|
| 624 |
+
return " · ".join(items)
|
| 625 |
+
|
| 626 |
+
|
| 627 |
+
def volume_info(volume: Volume, family: str | None) -> str:
|
| 628 |
+
b, h, a = volume.shape
|
| 629 |
+
scanner = FAMILIES.get(family, "Select scanner family")
|
| 630 |
+
spacing = f" · axial {volume.axial_mm * 1000:.2f} µm" if volume.axial_mm else ""
|
| 631 |
+
return (
|
| 632 |
+
f"**{html.escape(scanner)}** \n{b:,} B-scans · {h:,} × {a:,} pixels{spacing}"
|
| 633 |
+
)
|
| 634 |
+
|
| 635 |
+
|
| 636 |
+
def checkpoint_identity() -> str:
|
| 637 |
+
return hashlib.sha256(CHECKPOINT.read_bytes()).hexdigest()
|