AbdomenAtlas/RSuperMaskPretrained

Learning Segmentation from Radiology Reports

This repository contains a segmentation model (MedFormer architecture) which served as a baseline for the paper Learning Segmentation from Radiology Reports.

This model was trained for organ and tumor (kidney, liver and pancreas tumors) segmentation in the Beta version of AbdomenAtlas 3.0. Performance improvements are expected for models trained on the released version of AbdomenAtlas 3.0. For the official release of AbdomenAtlas 3.0 (ICCV 2025), please check our GitHub: https://github.com/MrGiovanni/RadGPT.

This model was only trained with per-voxel segmentation masks. In the MICCAI 2025 paper "Learning Segmentation from Radiology Report", it served as the "segmentation" baseline.

Also, this is the model is a starting point for our R-Super: you can can fine-tune it with radiology reports, please see our Report Supervision (R-Super) GitHub.

Training and inference code: https://github.com/MrGiovanni/R-Super

Label order

['adrenal_gland_left',
 'adrenal_gland_right',
 'aorta',
 'bladder',
 'celiac_trunk',
 'colon',
 'common_bile_duct',
 'duodenum',
 'esophagus',
 'femur_left',
 'femur_right',
 'gall_bladder',
 'hepatic_vessel',
 'intestine',
 'kidney_left',
 'kidney_lesion',
 'kidney_right',
 'liver',
 'liver_lesion',
 'liver_segment_1',
 'liver_segment_2',
 'liver_segment_3',
 'liver_segment_4',
 'liver_segment_5',
 'liver_segment_6',
 'liver_segment_7',
 'liver_segment_8',
 'lung_left',
 'lung_right',
 'pancreas',
 'pancreas_body',
 'pancreas_head',
 'pancreas_tail',
 'pancreatic_lesion',
 'portal_vein_and_splenic_vein',
 'postcava',
 'prostate',
 'rectum',
 'spleen',
 'stomach',
 'superior_mesenteric_artery',
 'veins']

---

Papers

Learning Segmentation from Radiology Reports
Pedro R. A. S. Bassi, Wenxuan Li, Jieneng Chen, Zheren Zhu, Tianyu Lin, Sergio Decherchi, Andrea Cavalli, Kang Wang, Yang Yang, Alan Yuille, Zongwei Zhou*
Johns Hopkins University
MICCAI 2025
Best Paper Award Runner-up (top 2 in 1,027 papers)

Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks
Pedro R. A. S. Bassi, Xinze Zhou, Wenxuan Li, Szymon Płotka, Jieneng Chen, Qi Chen, Zheren Zhu, Jakub Prządo, Ibrahim E. Hamacı, Sezgin Er, Yuhan Wang, Ashwin Kumar, Bjoern Menze, Jarosław B. Ćwikła, Yuyin Zhou, Akshay S. Chaudhari, Curtis P. Langlotz, Sergio Decherchi, Andrea Cavalli, Kang Wang, Yang Yang, Alan Yuille, Zongwei Zhou*
Johns Hopkins University

RadGPT: Constructing 3D Image-Text Tumor Datasets
Pedro R. A. S. Bassi, Mehmet Yavuz, Kang Wang, Sezgin Er, Ibrahim E. Hamamci, Wenxuan Li, Xiaoxi Chen, Sergio Decherchi, Andrea Cavalli, Yang Yang, Alan Yuille, Zongwei Zhou*
Johns Hopkins University
ICCV, 2025

Inference

0- Download and installation.

[Optional] Install Anaconda on Linux

wget https://repo.anaconda.com/archive/Anaconda3-2024.06-1-Linux-x86_64.sh
bash Anaconda3-2024.06-1-Linux-x86_64.sh -b -p ./anaconda3
./anaconda3/bin/conda init
source ~/.bashrc

git clone https://github.com/MrGiovanni/R-Super
cd R-Super/rsuper_train
conda create -n rsuper python=3.10
conda activate rsuper
pip install -r requirements.txt
pip install -U "huggingface_hub[cli]"
hf download AbdomenAtlas/RSuperMaskPretrained --local-dir ./RSuperMaskPretrained

1- Pre-processing. Prepare your dataset in the format below. You can use symlinks instead of copying your data.

Dataset format.

/path/to/dataset/
├── BDMAP_0000001
|    └── ct.nii.gz
├── BDMAP_0000002
|    └── ct.nii.gz
...

2- Inference. The code below will inference, generating binary segmentation masks. To save probabilities, add the argument --save_probabilities or --save_probabilities_lesions (which saves only probabilities for lesions, not for organs). The optional argument --organ_mask_on_lesion will use organ segmentations (produced by the R-Super model itself, not ground-truth) to remove tumor predictions outside its organ.

python predict_abdomenatlas.py --load RSuperMaskPretrained/atlas3_medformer/fold_0_latest.pth --img_path /path/to/test/dataset/ --class_list RSuperMaskPretrained/labels_rsuper_mask.yaml --save_path /path/to/inference/output/ --organ_mask_on_lesion

Argument Details

• load: path to the model checkpoint (fold_0_latest.pth)
• img_path: path to dataset
• class_list: a yaml file with the class names of your model
• save_path: path to output, where masks will be saved
• ids: this is an optional argument. By default, the code will predict on all cases in --img_path. If you pass ids, the code will only test with the CT scans indicated in ids. You can use this to separate a test set: --ids /path/to/test/set/ids.csv. The csv file must have a 'BDMAP ID' column with the ids of the test cases.

For more details, see https://github.com/MrGiovanni/R-Super/tree/main/rsuper_train#test

Citations

If you use this data, please cite the 3 paper below:

@article{bassi2025learning,
  title={Learning Segmentation from Radiology Reports},
  author={Bassi, Pedro RAS and Li, Wenxuan and Chen, Jieneng and Zhu, Zheren and Lin, Tianyu and Decherchi, Sergio and Cavalli, Andrea and Wang, Kang and Yang, Yang and Yuille, Alan L and others},
  journal={arXiv preprint arXiv:2507.05582},
  year={2025}
}

@article{bassi2025radgpt,
  title={Radgpt: Constructing 3d image-text tumor datasets},
  author={Bassi, Pedro RAS and Yavuz, Mehmet Can and Wang, Kang and Chen, Xiaoxi and Li, Wenxuan and Decherchi, Sergio and Cavalli, Andrea and Yang, Yang and Yuille, Alan and Zhou, Zongwei},
  journal={arXiv preprint arXiv:2501.04678},
  year={2025}
}

@misc{bassi2025scaling,
      title={Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks}, 
      author={Pedro R. A. S. Bassi and Xinze Zhou and Wenxuan Li and Szymon Płotka and Jieneng Chen and Qi Chen and Zheren Zhu and Jakub Prządo and Ibrahim E. Hamacı and Sezgin Er and Yuhan Wang and Ashwin Kumar and Bjoern Menze and Jarosław B. Ćwikła and Yuyin Zhou and Akshay S. Chaudhari and Curtis P. Langlotz and Sergio Decherchi and Andrea Cavalli and Kang Wang and Yang Yang and Alan L. Yuille and Zongwei Zhou},
      year={2025},
      eprint={2510.14803},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2510.14803}, 
}

Acknowledgement

This work was supported by the Lustgarten Foundation for Pancreatic Cancer Research, the Patrick J. McGovern Foundation Award, and the National Institutes of Health (NIH) under Award Number R01EB037669. We would like to thank the Johns Hopkins Research IT team in IT@JH for their support and infrastructure resources where some of these analyses were conducted; especially DISCOVERY HPC. Paper content is covered by patents pending.