docs/AMOS_SHARED13_EXPERIMENTS.md

# AMOS22 CT->MRI shared-13 experiment plan

This is the first SACFlow-FM implementation/evaluation protocol.

## Label protocol

AMOS22 labeled data contains 500 CT and 100 MRI cases. In the local AMOS split, MRI validation labels may only contain labels `0..13`; labels `14` and `15` are absent in `target_val`. For a clean CT->MRI protocol we use a shared-label setting:

- keep labels `0..13`;
- map labels `14` and `15` to background `0`;
- set `num_classes: 14`;
- use `target_val` for evaluation because `target_test` labels are not available.

## 0. Create manifests

From repo root:

```bash
AMOS_ROOT=datasets/amos22 bash scripts/amos/create_manifests_shared13.sh
```

This creates:

```text
data_json/amos_ct2mr.json
data_json/amos_ct2mr_shared13.json
data_json/amos_ct2mr_shared13_sfda.json
```

Use `amos_ct2mr_shared13_sfda.json` for all source-free adaptation runs. It removes labels from `target_train` to avoid target-label leakage.

## 1. Smoke test

```bash
NPROC=1 bash scripts/amos/train_source_ct_smoke.sh
```

## 2. Source CT model

```bash
NPROC=8 bash scripts/amos/train_source_ct_shared13.sh
bash scripts/amos/eval_source_ct2mri_shared13.sh
```

## 3. Export compact source memory

```bash
NUM_PASSES=3 bash scripts/amos/export_memory_ct_shared13.sh
```

## 4. MRI oracle upper bound

```bash
NPROC=8 bash scripts/amos/train_oracle_mri_shared13.sh
python tools/eval.py \
  --config configs/experiments/amos_oracle_mri_shared13.yaml \
  --checkpoint outputs/amos/oracle_mri_shared13/checkpoints/best.pt \
  --split target_val
```

## 5. Internal SFDA baselines

```bash
NPROC=8 bash scripts/amos/run_selftrain_ct2mri_shared13.sh
NPROC=8 bash scripts/amos/run_peft_ct2mri_shared13.sh
NPROC=8 bash scripts/amos/run_proto_align_ct2mri_shared13.sh
```

Evaluate:

```bash
python tools/eval.py --config configs/experiments/amos_selftrain_ct2mri_shared13.yaml --checkpoint outputs/amos/selftrain_ct2mri_shared13/checkpoints/best.pt --split target_val
python tools/eval.py --config configs/experiments/amos_peft_ct2mri_shared13.yaml --checkpoint outputs/amos/peft_ct2mri_shared13/checkpoints/best.pt --split target_val
python tools/eval.py --config configs/experiments/amos_proto_align_ct2mri_shared13.yaml --checkpoint outputs/amos/proto_align_ct2mri_shared13/checkpoints/best.pt --split target_val
```

## 6. SACFlow-FM

```bash
NPROC=8 bash scripts/amos/run_sacflow_ct2mri_shared13.sh
bash scripts/amos/eval_sacflow_ct2mri_shared13.sh
```

## 7. First ablations

Run these after the main SACFlow-FM run works:

```bash
NPROC=8 bash scripts/amos/run_sacflow_linear_ct2mri_shared13.sh
NPROC=8 bash scripts/amos/run_sacflow_whole_feature_ct2mri_shared13.sh
NPROC=8 bash scripts/amos/run_sacflow_random_subspace_ct2mri_shared13.sh
```

Evaluate:

```bash
python tools/eval.py --config configs/experiments/amos_sacflow_linear_ct2mri_shared13.yaml --checkpoint outputs/amos/sacflow_linear_ct2mri_shared13/checkpoints/best.pt --split target_val
python tools/eval.py --config configs/experiments/amos_sacflow_whole_feature_ct2mri_shared13.yaml --checkpoint outputs/amos/sacflow_whole_feature_ct2mri_shared13/checkpoints/best.pt --split target_val
python tools/eval.py --config configs/experiments/amos_sacflow_random_subspace_ct2mri_shared13.yaml --checkpoint outputs/amos/sacflow_random_subspace_ct2mri_shared13/checkpoints/best.pt --split target_val
```

## First results table

Report:

| Method | Target labels for training? | Source images during adaptation? | Mean Dice | Mean HD95 |
|---|---:|---:|---:|---:|
| Source-only CT->MRI | No | No | | |
| MRI oracle | Yes | N/A | | |
| Self-training | No | No | | |
| PEFT-only | No | No | | |
| Proto-align internal | No | No | | |
| SACFlow-linear | No | No | | |
| SACFlow-FM | No | No | | |