Request access to the OmniLesion weights
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
These weights are released by Nucleo Research for non-commercial research and educational use under the CC BY-NC 4.0 license. They are research artefacts from the MICCAI FLARE 2026 challenge, not a medical device: they must not be used for clinical decision making, diagnosis or patient care. By requesting access you agree to (1) use the weights only for non-commercial research or education, (2) not redistribute them outside your research group and point others to this page instead, (3) cite the paper "Pan-cancer Lesion Segmentation in CT under Heterogeneous and Partial Annotation" (FLARE 2026) in any resulting publication, and (4) accept that the weights are provided as is, without warranty of any kind. Requests are reviewed manually; please state your affiliation and intended use.
Log in or Sign Up to review the conditions and access this model content.
OmniLesion: trained weights
Weights of the OmniLesion submission to the MICCAI FLARE 2026 pan-cancer segmentation task (Task 1). Code, training recipe and evaluation scripts: https://github.com/Nucleo-Research/omnilesion. On the challenge's hidden validation set (100 cases) the pipeline scores 0.8122 lesion DSC and 0.7642 lesion NSD.
Files
| path | content |
|---|---|
model/plans.json, model/dataset.json |
nnU-Net v2 plan (residual-encoder U-Net, 3 x 2 x 2 mm, 96 x 128 x 128 patches) and dataset description |
model/fold_0/checkpoint_final.pth |
main network after 4000 epochs x 750 iterations (3.0 M updates), with optimiser state; trainer nnUNetTrainerOmniLesion |
lung/detector.pt |
RetinaNet lung-nodule detector (MONAI, 3D ResNet-50 + FPN) after 300,000 iterations |
lung/segmentor_state_dict.pt, lung/segmentor_manifest.json |
65^3 nodule patch U-Net (12 base channels) after 40,000 iterations |
sha256.txt lists the checksums. All networks were trained from scratch on the challenge's labelled training data
only (no pretrained weights, no external data, no pseudo labels). These are exactly the weights inside the submitted
container; only the trainer and plan names stored in the checkpoint were renamed to the ones used by the code
repository.
Use
git clone https://github.com/Nucleo-Research/omnilesion.git && cd omnilesion
pip install -r requirements-inference.txt && python -m omnilesion.nnunet_trainer.install
hf download Nucleo-Research/omnilesion --local-dir weights # this repository
python scripts/08_predict.py --inputs /data/images --outputs /data/masks \
--model weights/model --lung-dir weights/lung
Inputs are CT volumes <case>_0000.nii.gz; outputs are binary lesion masks <case>.nii.gz. The pipeline (sliding
window with mirroring, confidence and empty rules, lung-nodule cascade behind a 3.5 L lung gate) and every threshold
are described in the code repository's README and in the paper Pan-cancer Lesion Segmentation in CT under
Heterogeneous and Partial Annotation (FLARE 2026 proceedings).
License
Weights: CC BY-NC 4.0, non-commercial research use, access on request (see the form above). Code: Apache-2.0 at the GitHub repository. Built with nnU-Net v2 and MONAI (both Apache-2.0).