Upload folder using huggingface_hub

README.md

@@ -12,18 +12,21 @@ library_name: pytorch
 pipeline_tag: image-feature-extraction
 ---
 
-# OpenPath — Pathology Foundation Model (training & evaluation code)
+# OpenPath: Public-Data Pathology Foundation Models and Leakage-Free Evaluation
+
+*Training, reproduction, and evaluation code.*
 
 **OpenPath** is a vision foundation model for computational pathology: a **ViT-g/14** encoder
 pre-trained with self-supervision (**DINOv2** + **gram anchoring**) on **public-only** whole-slide
 histopathology tiles. This repository contains the **training, reproduction, and evaluation code**.
 The corpus and checkpoints are hosted separately (see below).
 
-> **Headline result.** On a **contamination-free** in-house spatial-transcriptomics (ST) cohort — the
-> least leakage-prone benchmark, since no public foundation model was trained on it — OpenPath **ranks
-> #1 among seven foundation models** (mean Pearson: OpenPath **0.323** > UNI2-h 0.301 > OpenMidnight
-> 0.300 > Virchow2 0.292 > prov-gigapath 0.286 > Phikon-v2 0.274 > UNI 0.257). Released checkpoint:
-> **`training_316250`** (in `openpath-checkpoints`). See [Evaluation](#evaluation).
+> **Headline result.** On **AMC-HCC-ST** — a contamination-free in-house Asan Medical Center
+> hepatocellular-carcinoma spatial-transcriptomics cohort, the least leakage-prone benchmark since no
+> public foundation model was trained on it — OpenPath **ranks #1 among seven foundation models** (mean
+> Pearson: OpenPath **0.323** > UNI2-h 0.301 > OpenMidnight 0.300 > Virchow2 0.292 > prov-gigapath 0.286
+> > Phikon-v2 0.274 > UNI 0.257). Released checkpoint: **`training_316250`** (in `openpath-checkpoints`).
+> See [Evaluation](#evaluation).
 
 - **Encoder:** ViT-g/14 (reg4), 1536-dim CLS embedding
 - **Objective:** DINO + iBOT + KDE (DINOv2) with **gram anchoring** ported from DINOv3
@@ -47,7 +50,7 @@ scripts/
   run_hest_3way.py           # HEST evaluation (Meta DINOv2 / Phikon-v2 / OpenPath)
 eval/                                          # downstream benchmark / reference-FM comparison
   openpath_eva_backbone.py   # backbone factories: OpenPath + Phikon / OpenMidnight / UNI / UNI2-h / gigapath / Virchow2
-  st_bench.py                # in-house spatial-transcriptomics benchmark (LOPO ridge, headline)
+  st_bench.py                # AMC-HCC-ST benchmark (LOPO ridge, headline)
   run_patch_eval.sh          # PCam / CRC / BACH patch probing via kaiko-eva
   eva_configs/               # eva YAML configs (crc / bach / patch_camelyon)
 requirements.txt
@@ -110,15 +113,16 @@ cls = m.forward_features(x)["x_norm_clstoken"]   # (B, 1536)
 
 ## Evaluation
 
-Frozen-encoder linear/ridge probing. The headline benchmark is a **contamination-free** in-house
-Visium spatial-transcriptomics (ST) cohort (leave-one-patient-out, mean Pearson over top-50
-highly-variable genes) — **no public FM was trained on it**, so it is the least leakage-prone
-comparison. The reported OpenPath checkpoint is `training_316250`.
+Frozen-encoder linear/ridge probing. The headline benchmark is **AMC-HCC-ST** — a
+**contamination-free** in-house Asan Medical Center hepatocellular-carcinoma Visium
+spatial-transcriptomics cohort (leave-one-patient-out, mean Pearson over top-50 highly-variable
+genes) — **no public FM was trained on it**, so it is the least leakage-prone comparison. The
+reported OpenPath checkpoint is `training_316250`.
 
 **Comparison** — all 7 models loaded through one backbone factory and probed under an identical
-protocol; sorted by the clean ST benchmark:
+protocol; sorted by the clean AMC-HCC-ST benchmark:
 
-| Model | ST (in-house, clean) ↓ | HEST-1K (public) | NCT-CRC-HE (9-cls acc) | BACH (4-cls acc) |
+| Model | AMC-HCC-ST (clean) ↓ | HEST-1K (public) | NCT-CRC-HE (9-cls acc) | BACH (4-cls acc) |
 |---|---|---|---|---|
 | **OpenPath** | **0.323** | 0.372 | 0.954 | 0.761 |
 | UNI2-h | 0.301 | 0.414 | 0.966 | 0.908 |
@@ -128,12 +132,12 @@ protocol; sorted by the clean ST benchmark:
 | Phikon-v2 | 0.274 | 0.375 | 0.937 | 0.708 |
 | UNI | 0.257 | 0.386 | 0.946 | 0.777 |
 
-**On the contamination-free ST cohort OpenPath ranks #1** among all seven foundation models. The
-picture inverts on the **public** benchmarks (HEST-1K, CRC, BACH): there OpenPath is mid-pack to
+**On the contamination-free AMC-HCC-ST cohort OpenPath ranks #1** among all seven foundation models.
+The picture inverts on the **public** benchmarks (HEST-1K, CRC, BACH): there OpenPath is mid-pack to
 low, and the large FMs lead. Those benchmarks derive from public repositories (TCGA/GTEx/etc.) that
 these FMs were pre-trained on, so their apparent edge is confounded by **train/test leakage** — which
-is exactly why the leakage-free in-house ST cohort is our headline. (The reported checkpoint
-`training_316250` is selected by ST; OpenPath's HEST-1K peaks earlier in training at ~0.38.)
+is exactly why the leakage-free AMC-HCC-ST cohort is our headline. (The reported checkpoint
+`training_316250` is selected by AMC-HCC-ST; OpenPath's HEST-1K peaks earlier in training at ~0.38.)
 PCam / CAMELYON is excluded because it overlaps our own training corpus.
 
 ### Reproducing the comparison
@@ -144,7 +148,7 @@ UNI2-h, gigapath, Virchow2) are directly comparable.
 
 ```bash
 export PYTHONPATH="$PWD/OpenPath:$PWD/eval"
-# Headline: in-house spatial-transcriptomics (LOPO ridge; cohort is private, code is provided)
+# Headline: AMC-HCC-ST (LOPO ridge; cohort is private, code is provided)
 python eval/st_bench.py --backbone openpath --weights <teacher_checkpoint.pth>
 python eval/st_bench.py --backbone uni              # reference FM (also: uni2 / gigapath / virchow2 / phikon / openmidnight)
 
@@ -168,7 +172,7 @@ decision-making.
 - **Public-benchmark leakage.** Public benchmarks (HEST-1K, NCT-CRC-HE, BACH) derive from repositories
   (TCGA/GTEx/…) that many foundation models — and partly OpenPath — were pre-trained on. Absolute
   numbers and cross-model rankings on them are confounded; prefer leakage-controlled evaluation.
-- **Checkpoint trade-off.** The released `training_316250` is selected by the clean ST benchmark;
+- **Checkpoint trade-off.** The released `training_316250` is selected by the clean AMC-HCC-ST benchmark;
   earlier checkpoints score higher on HEST-1K (~0.38). Pick a checkpoint to match your downstream task.
 - **Domain.** Trained on H&E WSIs at native magnification. Behavior on IHC, cytology, frozen sections,
   non-0.5 µm-per-pixel inputs, or non-pathology images is untested.
@@ -181,7 +185,7 @@ A paper is in preparation. Until then, please cite the repository and the upstre
 
 ```bibtex
 @misc{openpath2026,
-  title  = {OpenPath: a public-data pathology foundation model},
+  title  = {OpenPath: Public-Data Pathology Foundation Models and Leakage-Free Evaluation},
   author = {OpenPath authors},
   year   = {2026},
   note   = {https://huggingface.co/taejoon89/openpath}

eval/st_bench.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-"""HEST-style spatial-transcriptomics(ST) 벤치마크 — in-house Visium 코호트.
+"""AMC-HCC-ST 벤치마크 — Asan Medical Center HCC Visium spatial-transcriptomics 코호트(비공개).
 각 spot에서 WSI 패치 추출 → FM 임베딩(CLS) → PCA → Ridge 회귀로 상위 HVG 발현 예측
 → Pearson 상관(유전자평균). Leave-one-patient-out CV.
 
@@ -20,7 +20,7 @@ from scipy.stats import pearsonr
 import torchvision.transforms as T
 
 ROOT = os.environ.get("OPENPATH_ROOT", os.path.dirname(os.path.dirname(os.path.abspath(__file__))))  # repo 루트(eval/의 상위)
-DATA = os.environ.get("ST_ROOT", f"{ROOT}/data/st_bench")  # in-house Visium ST 코호트(비공개; 코드만 공개)
+DATA = os.environ.get("ST_ROOT", f"{ROOT}/data/st_bench")  # AMC-HCC-ST 코호트(비공개; 코드만 공개)
 IMAGENET_MEAN = (0.485, 0.456, 0.406); IMAGENET_STD = (0.229, 0.224, 0.225)
 
 
@@ -169,7 +169,7 @@ def main():
 
     overall = float(np.mean(per_gene_corr))
     tag = args.tag or args.backbone
-    print(f"[ST RESULT] backbone={tag} | LOPO mean Pearson = {overall:.4f} (folds={len(pats)}, HVG={args.k_genes})", flush=True)
+    print(f"[AMC-HCC-ST RESULT] backbone={tag} | LOPO mean Pearson = {overall:.4f} (folds={len(pats)}, HVG={args.k_genes})", flush=True)
 
 
 if __name__ == "__main__":