ModelAufgelistetExtern

CVPR2026 PanCancerSeg Baseline

Binary lesion segmentation from CT using vanilla nnU-Net v2 (ResEncM). Reference baseline for CVPR 2026: Foundation Models for Pan-cancer Segmentation in CT Images Task 1.

Quellehuggingface.co/KS987/CVPR2026-PanCancerSeg-baseline/tree/b9c65ae155292d4d90416185422714898186f8c3

ArtOtherVersionRevision b9c65ae

Modellquelle

Art: Other
Dateigröße: 778–779 MB
Version: vRevision b9c65ae
Aktualisiert: 15. Sept. 2026
Downloads: 0
Quelle: Hugging Face

Quellenbeschreibung

Vanilla nnUNet v2 Baseline — CVPR 2026 Task 1: Pan-Cancer Segmentation

Binary lesion segmentation from CT using vanilla nnU-Net v2 (ResEncM). Reference baseline for CVPR 2026: Foundation Models for Pan-cancer Segmentation in CT Images Task 1.

Code + failure analysis: GitHub — Kappapapa123/CVPR2026-PanCancerSeg-baseline

Model Details

Parameter	Value
Framework	nnU-Net v2.6.4
Architecture	Residual Encoder U-Net Medium (`nnUNetResEncUNetMPlans`)
Configuration	3d_fullres
Task	Binary segmentation (0=background, 1=tumor)
Epochs	2000
Fold	0 (official competition split via `splits_final.json`)
Trainer class	`nnUNetTrainerWandb2000`
Dataset ID	101 (`Dataset101_FLAREPanCancer`)

Training Data

FLARE-MedFM/FLARE-Task1-Pancancer — 10,762 cases total:

train_label (~10,000 cases): Partially labeled (primary lesion only per case)
DeepLesion5K-MedSAM2 (~762 cases): Pseudo labels from MedSAM2

Only the primary lesion is annotated per training case. Metastatic lesions may be present but unlabeled.

Performance

Evaluated on 50 validation-public cases:

Metric	Mean	Median	Std
Lesion DSC	0.3278	0.2318	0.2883
Lesion NSD (2 mm)	0.1797	0.1046	0.2029

How to Use

# 1. Install dependencies
pip install nnunetv2==2.6.4 huggingface-hub

# 2. Clone code repo (needed for the custom trainer)
git clone https://github.com/Kappapapa123/CVPR2026-PanCancerSeg-baseline.git

# 3. Symlink the custom trainer into nnUNet
VARIANTS_DIR=$(python -c "import nnunetv2; print(nnunetv2.__path__[0])")/training/nnUNetTrainer/variants
ln -sf $(realpath CVPR2026-PanCancerSeg-baseline/trainers/nnUNetTrainerWandb2000.py) \
    "$VARIANTS_DIR/nnUNetTrainerWandb2000.py"

# 4. Download model weights
huggingface-cli download KS987/CVPR2026-PanCancerSeg-baseline \
    --local-dir ./model --repo-type model

# 5. Run inference
nnUNetv2_predict \
    -i /path/to/input_images \
    -o /path/to/output_predictions \
    -d 101 -c 3d_fullres -f 0 \
    -tr nnUNetTrainerWandb2000 \
    -p nnUNetResEncUNetMPlans \
    -m ./model/nnUNet/Dataset101_FLAREPanCancer \
    --disable_tta

Both checkpoint_final.pth and checkpoint_best.pth are provided. nnUNet uses checkpoint_final.pth by default.

Inference resampling requires ~64 GB RAM.

Limitations

Partial labels: Training data only labels the primary lesion per case.
False positive fragmentation: The dominant failure mode is scattered false-positive blobs. See the failure analysis.

Files

nnUNet/
  Dataset101_FLAREPanCancer/
    nnUNetTrainerWandb2000__nnUNetResEncUNetMPlans__3d_fullres/
      fold_0/
        checkpoint_best.pth      # Best validation checkpoint
        checkpoint_final.pth     # Final epoch (2000) checkpoint
      dataset.json
      dataset_fingerprint.json
      plans.json

Quellen

1 Quelle

Hugging FacePrimärVersion b9c65ae155292d4d90416185422714898186f8c3

huggingface.co/KS987/CVPR2026-PanCancerSeg-baseline/tree/b9c65ae155292d4d90416185422714898186f8c3

Verifiziert 15. Sept.

Modellartefakte

7 Artefakte

nnUNet/Dataset101_FLAREPanCancer/nnUNetTrainerWandb2000__nnUNetResEncUNetMPlans__3d_fullres/fold_0/checkpoint_best.pth

pth · 779 MB · SHA-256 ea0a70c53568…a364 · Hugging Face

Herunterladen

nnUNet/Dataset101_FLAREPanCancer/nnUNetTrainerWandb2000__nnUNetResEncUNetMPlans__3d_fullres/fold_0/checkpoint_epoch1200.pth

pth · 778 MB · SHA-256 7d987097caa3…85d8 · Hugging Face

Herunterladen

nnUNet/Dataset101_FLAREPanCancer/nnUNetTrainerWandb2000__nnUNetResEncUNetMPlans__3d_fullres/fold_0/checkpoint_epoch1400.pth

pth · 779 MB · SHA-256 71ef5059f333…576a · Hugging Face

Herunterladen

nnUNet/Dataset101_FLAREPanCancer/nnUNetTrainerWandb2000__nnUNetResEncUNetMPlans__3d_fullres/fold_0/checkpoint_epoch1600.pth

pth · 779 MB · SHA-256 903b355b94d0…5929 · Hugging Face

Herunterladen

nnUNet/Dataset101_FLAREPanCancer/nnUNetTrainerWandb2000__nnUNetResEncUNetMPlans__3d_fullres/fold_0/checkpoint_epoch1800.pth

pth · 779 MB · SHA-256 d09e200c8fb1…f7f8 · Hugging Face

Herunterladen

nnUNet/Dataset101_FLAREPanCancer/nnUNetTrainerWandb2000__nnUNetResEncUNetMPlans__3d_fullres/fold_0/checkpoint_epoch2000.pth

pth · 779 MB · SHA-256 7a1e8690ca3d…2b64 · Hugging Face

Herunterladen

nnUNet/Dataset101_FLAREPanCancer/nnUNetTrainerWandb2000__nnUNetResEncUNetMPlans__3d_fullres/fold_0/checkpoint_final.pth

pth · 779 MB · SHA-256 c68dab3c51cd…a8a3 · Hugging Face

Herunterladen

Quellenauszüge

2 Auszüge

Readme15. Sept.huggingface.co/KS987/CVPR2026-PanCancerSeg-baseline

--- license: apache-2.0 tags: - medical-imaging - segmentation - nnunet - computed-tomography - cancer - cvpr2026 - flare datasets: - FLARE-MedFM/FLARE-Task1-Pancancer metrics: - dice - normalized-surface-dice pipeline_tag: image-segmentation --- # Vanilla nnUNet v2 Baseline — CVPR 2026 Task 1: Pan-Cancer Segmentation Binary lesion segmentation from CT using vanilla nnU-Net v2 (ResEncM). Reference baseline for [CVPR 2026: Foundation Models for Pan-cancer Segmentation in CT Images Task 1](https://www.codabench.org/competitions/7149/). **Code + failure analysis:** [GitHub — Kappapapa123/CVPR2026-PanCancerSeg-baseline](https://github.com/Kappapapa123/CVPR2026-PanCancerSeg-baseline) --- ## Model Details | Parameter | Value | |-----------|-------| | Framework | nnU-Net v2.6.4 | | Architecture | Residual Encoder U-Net Medium (`nnUNetResEncUNetMPlans`) | | Configuration | 3d_fullres | | Task | Binary segmentation (0=background, 1=tumor) | | Epochs | 2000 | | Fold | 0 (official competition split via `splits_final.json`) | | Trainer class | `nnUNetTrainerWandb2000` | | Dataset ID | 101 (`Dataset101_FLAREPanCancer`) | ## Training Data [FLARE-MedFM/FLARE-Task1-Pancancer](https://huggingface.co/datasets/FLARE-MedFM/FLARE-Task1-Pancancer) — 10,762 cases total: - **train_label** (~10,000 cases): Partially labeled (primary lesion only per case) - **DeepLesion5K-MedSAM2** (~762 cases): Pseudo labels from MedSAM2 Only the primary lesion is annotated per training case. Metastatic lesions may be present but unlabeled. ## Performance Evaluated on 50 validation-public cases: | Metric | Mean | Median | Std | |--------|------|--------|-----| | Lesion DSC | 0.3278 | 0.2318 | 0.2883 | | Lesion NSD (2 mm) | 0.1797 | 0.1046 | 0.2029 | ## How to Use ```bash # 1. Install dependencies pip install nnunetv2==2.6.4 huggingface-hub # 2. Clone code repo (needed for the custom trainer) git clone https://github.com/Kappapapa123/CVPR2026-PanCancerSeg-baseline.git # 3. Symlink the custom trainer into nnUNet VARIANTS_DIR=$(python -c "import nnunetv2; print(nnunetv2.__path__[0])")/training/nnUNetTrainer/variants ln -sf $(realpath CVPR2026-PanCancerSeg-baseline/trainers/nnUNetTrainerWandb2000.py) \ "$VARIANTS_DIR/nnUNetTrainerWandb2000.py" # 4. Download model weights huggingface-cli download KS987/CVPR2026-PanCancerSeg-baseline \ --local-dir ./model --repo-type model...

Note15. Sept.huggingface.co/KS987/CVPR2026-PanCancerSeg-baseline

Source context: 0 downloads · 0 likes · Pipeline image-segmentation · Repo KS987/CVPR2026-PanCancerSeg-baseline