{"id":18686281,"url":"https://github.com/mrgiovanni/suprem","last_synced_at":"2025-04-11T00:54:50.444Z","repository":{"id":209320088,"uuid":"723720580","full_name":"MrGiovanni/SuPreM","owner":"MrGiovanni","description":"[ICLR 2024 Oral] Supervised Pre-Trained 3D Models for Medical Image Analysis (9,262 CT volumes + 25 annotated classes)","archived":false,"fork":false,"pushed_at":"2025-02-28T15:38:04.000Z","size":42297,"stargazers_count":325,"open_issues_count":11,"forks_count":11,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-04-11T00:54:18.463Z","etag":null,"topics":["dataset","medical-imaging","pre-trained-model","segmentation","transfer-learning"],"latest_commit_sha":null,"homepage":"https://www.cs.jhu.edu/~alanlab/Pubs23/li2023suprem.pdf","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MrGiovanni.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-26T15:09:13.000Z","updated_at":"2025-04-10T08:28:04.000Z","dependencies_parsed_at":"2023-11-26T17:27:35.149Z","dependency_job_id":"67f84643-1ab4-44ba-8bfc-15e3be865410","html_url":"https://github.com/MrGiovanni/SuPreM","commit_stats":null,"previous_names":["mrgiovanni/suprem"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MrGiovanni%2FSuPreM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MrGiovanni%2FSuPreM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MrGiovanni%2FSuPreM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MrGiovanni%2FSuPreM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MrGiovanni","download_url":"https://codeload.github.com/MrGiovanni/SuPreM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248322610,"owners_count":21084336,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dataset","medical-imaging","pre-trained-model","segmentation","transfer-learning"],"created_at":"2024-11-07T10:26:54.698Z","updated_at":"2025-04-11T00:54:50.433Z","avatar_url":"https://github.com/MrGiovanni.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n![logo](document/fig_suprem_logo.png)\n\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n\n![visitors](https://visitor-badge.laobi.icu/badge?page_id=MrGiovanni/SuPreM)\n[![GitHub Repo stars](https://img.shields.io/github/stars/MrGiovanni/SuPreM?style=social)](https://github.com/MrGiovanni/SuPreM/stargazers)\n\u003ca href=\"https://twitter.com/bodymaps317\"\u003e\n        \u003cimg src=\"https://img.shields.io/twitter/follow/BodyMaps?style=social\" alt=\"Follow on Twitter\" /\u003e\n\u003c/a\u003e\u003cbr/\u003e\n**Subscribe us: https://groups.google.com/u/2/g/bodymaps**  \n\n\u003c/div\u003e\n\nWe developed a suite of pre-trained 3D models, named **SuPreM**, that combined the best of large-scale datasets and per-voxel annotations, showing the transferability across a range of 3D medical imaging tasks.\n\n## Paper\n\n\u003cb\u003eAbdomenAtlas: A Large-Scale, Detailed-Annotated, \u0026 Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarking\u003c/b\u003e \u003cbr/\u003e\n[Wenxuan Li](https://scholar.google.com/citations?hl=en\u0026user=tpNZM2YAAAAJ), [Chongyu Qu](https://github.com/Chongyu1117), Xiaoxi Chen, Pedro R. A. S. Bassi, Yijia Shi, Yuxiang Lai, Qian Yu, Huimin Xue, Yixiong Chen, Xiaorui Lin, Yutong Tang, Yining Cao, Haoqi Han, Zheyuan Zhang, Jiawei Liu, Tiezheng Zhang, Yujiu Ma, Jincheng Wang, Guang Zhang, [Alan Yuille](https://www.cs.jhu.edu/~ayuille/), [Zongwei Zhou](https://www.zongweiz.com/)* \u003cbr/\u003e\nJohns Hopkins University \u003cbr/\u003e\nMedical Image Analysis, 2024 \u003cbr/\u003e\n\u003ca href='https://www.zongweiz.com/dataset'\u003e\u003cimg src='https://img.shields.io/badge/Project-Page-Green'\u003e\u003c/a\u003e \u003ca href='https://www.cs.jhu.edu/~alanlab/Pubs24/li2024abdomenatlas.pdf'\u003e\u003cimg src='https://img.shields.io/badge/Paper-PDF-purple'\u003e\u003c/a\u003e\n\n\u003cb\u003eHow Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?\u003c/b\u003e \u003cbr/\u003e\n[Wenxuan Li](https://scholar.google.com/citations?hl=en\u0026user=tpNZM2YAAAAJ), [Alan Yuille](https://www.cs.jhu.edu/~ayuille/), and [Zongwei Zhou](https://www.zongweiz.com/)\u003csup\u003e*\u003c/sup\u003e \u003cbr/\u003e\nJohns Hopkins University  \u003cbr/\u003e\nInternational Conference on Learning Representations (ICLR) 2024 (oral; top 1.2%) \u003cbr/\u003e\n\u003ca href='https://www.zongweiz.com/dataset'\u003e\u003cimg src='https://img.shields.io/badge/Project-Page-Green'\u003e\u003c/a\u003e \u003ca href='https://www.cs.jhu.edu/~alanlab/Pubs23/li2023suprem.pdf'\u003e\u003cimg src='https://img.shields.io/badge/Paper-PDF-purple'\u003e\u003c/a\u003e \u003ca href='document/promotion_slides.pdf'\u003e\u003cimg src='https://img.shields.io/badge/Slides-PDF-orange'\u003e\u003c/a\u003e \u003ca href='document/dom_wse_poster.pdf'\u003e\u003cimg src='https://img.shields.io/badge/Poster-PDF-blue'\u003e\u003c/a\u003e [![YouTube](https://badges.aleen42.com/src/youtube.svg)](https://vtizr.xetslk.com/s/1HUGNo) \u003ca href='https://www.cs.jhu.edu/news/ai-and-radiologists-unite-to-map-the-abdomen/'\u003e\u003cimg src='https://img.shields.io/badge/WSE-News-yellow'\u003e\u003c/a\u003e\n\n\u003cb\u003eTransitioning to Fully-Supervised Pre-Training with Large-Scale Radiology ImageNet for Improved AI Transferability in Three-Dimensional Medical Segmentation\u003c/b\u003e \u003cbr/\u003e\n[Wenxuan Li](https://scholar.google.com/citations?hl=en\u0026user=tpNZM2YAAAAJ)\u003csup\u003e1\u003c/sup\u003e, [Junfei Xiao](https://lambert-x.github.io/)\u003csup\u003e1\u003c/sup\u003e, [Jie Liu](https://ljwztc.github.io/)\u003csup\u003e2\u003c/sup\u003e, [Yucheng Tang](https://scholar.google.com/citations?hl=en\u0026user=0xheliUAAAAJ)\u003csup\u003e3\u003c/sup\u003e, [Alan Yuille](https://www.cs.jhu.edu/~ayuille/)\u003csup\u003e1\u003c/sup\u003e, and [Zongwei Zhou](https://www.zongweiz.com/)\u003csup\u003e1,*\u003c/sup\u003e \u003cbr/\u003e\n\u003csup\u003e1\u003c/sup\u003eJohns Hopkins University  \u003cbr/\u003e\n\u003csup\u003e2\u003c/sup\u003eCity University of Hong Kong  \u003cbr/\u003e\n\u003csup\u003e3\u003c/sup\u003eNVIDIA  \u003cbr/\u003e\nRadiological Society of North America (RSNA) 2023  \u003cbr/\u003e\n\u003ca href='document/rsna_abstract.pdf'\u003e\u003cimg src='https://img.shields.io/badge/Abstract-PDF-purple'\u003e\u003c/a\u003e \u003ca href='document/rsna2023_slides.pdf'\u003e\u003cimg src='https://img.shields.io/badge/Slides-2023-orange'\u003e\u003c/a\u003e \u003ca href='document/rsna2024_slides.pdf'\u003e\u003cimg src='https://img.shields.io/badge/Slides-2024-orange'\u003e\u003c/a\u003e\n\n\n**\u0026#9733; We have maintained a document for [Frequently Asked Questions](document/frequently_asked_questions.md).**\n\n**\u0026#9733; We have maintained a paper list for [Awesome Medical SAM](document/awesome_medical_segment_anything.md).**\n\n**\u0026#9733; We have maintained a paper list for [Awesome Medical Pre-Training](document/awesome_medical_pretraining.md).**\n\n**\u0026#9733; We have maintained a paper list for [Awesome Medical Segmentation Backbones](document/awesome_medical_backbone.md).**\n\n## An Extensive Dataset: AbdomenAtlas 1.1\n\nThe release of AbdomenAtlas 1.0 can be found at https://huggingface.co/datasets/AbdomenAtlas/AbdomenAtlas1.0Mini\n\nAbdomenAtlas 1.1 is an extensive dataset of 9,262 CT volumes with per-voxel annotation of **25 organs** and pseudo annotations for **seven types of tumors**, enabling us to *finally* perform supervised pre-training of AI models at scale. Based on AbdomenAtlas 1.1, we also provide a suite of pre-trained models comprising several widely recognized AI models. \n\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"document/fig_benchmark.png\" /\u003e\u003c/p\u003e\n\nPrelimianry benchmark showed that supervised pre-training strikes as a preferred choice in terms of performance and efficiency compared with self-supervised pre-training. \n\nWe anticipate that the release of large, annotated datasets (AbdomenAtlas 1.1) and the suite of pre-trained models (SuPreM) will bolster collaborative endeavors in establishing Foundation Datasets and Foundation Models for the broader applications of 3D volumetric medical image analysis.\n\nThe AbdomenAtlas 1.1 dataset is organized as\n```\nAbdomenAtlas1.1\n    ├── BDMAP_00000001\n    │   ├── ct.nii.gz\n    │   └── segmentations\n    │       ├── aorta.nii.gz\n    │       ├── gall_bladder.nii.gz\n    │       ├── kidney_left.nii.gz\n    │       ├── kidney_right.nii.gz\n    │       ├── liver.nii.gz\n    │       ├── pancreas.nii.gz\n    │       ├── postcava.nii.gz\n    │       ├── spleen.nii.gz\n    │       ├── stomach.nii.gz\n    │       └── ...\n    ├── BDMAP_00000002\n    │   ├── ct.nii.gz\n    │   └── segmentations\n    │       ├── aorta.nii.gz\n    │       ├── gall_bladder.nii.gz\n    │       ├── kidney_left.nii.gz\n    │       ├── kidney_right.nii.gz\n    │       ├── liver.nii.gz\n    │       ├── pancreas.nii.gz\n    │       ├── postcava.nii.gz\n    │       ├── spleen.nii.gz\n    │       ├── stomach.nii.gz\n    │       └── ...\n    ├── BDMAP_00000003\n    │   ├── ct.nii.gz\n    │   └── segmentations\n    │       ├── aorta.nii.gz\n    │       ├── gall_bladder.nii.gz\n    │       ├── kidney_left.nii.gz\n    │       ├── kidney_right.nii.gz\n    │       ├── liver.nii.gz\n    │       ├── pancreas.nii.gz\n    │       ├── postcava.nii.gz\n    │       ├── spleen.nii.gz\n    │       ├── stomach.nii.gz\n    │       └── ...\n    ...\n```\n\n\u003cdetails\u003e\n\u003csummary style=\"margin-left: 25px;\"\u003eClass map for 9 classes in AbdomenAtlas 1.0 and 25 classes in AbdomenAtlas 1.1\u003c/summary\u003e\n\u003cdiv style=\"margin-left: 25px;\"\u003e\n\n```python\n# class map for the AbdomenAtlas 1.0 dataset\nclass_map_abdomenatlas_1_0 = {\n    1: 'aorta',\n    2: 'gall_bladder',\n    3: 'kidney_left',\n    4: 'kidney_right',\n    5: 'liver',\n    6: 'pancreas',\n    7: 'postcava',\n    8: 'spleen',\n    9: 'stomach',\n    }\n\n# class map for the AbdomenAtlas 1.1 dataset\nclass_map_abdomenatlas_1_1 = {\n    1: 'aorta', \n    2: 'gall_bladder', \n    3: 'kidney_left', \n    4: 'kidney_right', \n    5: 'liver', \n    6: 'pancreas', \n    7: 'postcava', \n    8: 'spleen', \n    9: 'stomach', \n    10: 'adrenal_gland_left', \n    11: 'adrenal_gland_right', \n    12: 'bladder', \n    13: 'celiac_trunk', \n    14: 'colon', \n    15: 'duodenum', \n    16: 'esophagus', \n    17: 'femur_left', \n    18: 'femur_right', \n    19: 'hepatic_vessel', \n    20: 'intestine', \n    21: 'lung_left', \n    22: 'lung_right', \n    23: 'portal_vein_and_splenic_vein', \n    24: 'prostate', \n    25: 'rectum'\n    }\n```\n\n\u003c/div\u003e\n\u003c/details\u003e\n\n## A Suite of Pre-trained Models: SuPreM\n\nThe following is a list of supported model backbones in our collection. Select the appropriate family of backbones and click to expand the table, download a specific backbone and its pre-trained weights (`name` and `download`), and save the weights into `./pretrained_weights/`. More backbones will be added along time. **Please suggest the backbone in [this channel](https://github.com/MrGiovanni/SuPreM/issues/1) if you want us to pre-train it on AbdomenAtlas 1.1 containing 9,262 annotated CT volumes.**\n\n\u003cdetails\u003e\n\u003csummary style=\"margin-left: 25px;\"\u003eSwin UNETR\u003c/summary\u003e\n\u003cdiv style=\"margin-left: 25px;\"\u003e\n\n| name | params | pre-trained data | resources | download |\n|:----  |:----  |:----  |:----  |:----  |\n| [Tang et al.](https://openaccess.thecvf.com/content/CVPR2022/papers/Tang_Self-Supervised_Pre-Training_of_Swin_Transformers_for_3D_Medical_Image_Analysis_CVPR_2022_paper.pdf) | 62.19M | 5050 CT | [![GitHub stars](https://img.shields.io/github/stars/Project-MONAI/research-contributions.svg?logo=github\u0026label=Stars)](https://github.com/Project-MONAI/research-contributions) | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/self_supervised_nv_swin_unetr_5050.pt?download=true) |\n| [Jose Valanaras et al.](https://arxiv.org/pdf/2307.16896) | 62.19M | 50000 CT/MRI | [![GitHub stars](https://img.shields.io/github/stars/Project-MONAI/research-contributions.svg?logo=github\u0026label=Stars)](https://github.com/Project-MONAI/research-contributions) | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/self_supervised_nv_swin_unetr_50000.pth?download=true) |\n| [Universal Model](https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_CLIP-Driven_Universal_Model_for_Organ_Segmentation_and_Tumor_Detection_ICCV_2023_paper.pdf) | 62.19M | 2100 CT | [![GitHub stars](https://img.shields.io/github/stars/ljwztc/CLIP-Driven-Universal-Model.svg?logo=github\u0026label=Stars)](https://github.com/ljwztc/CLIP-Driven-Universal-Model) | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/supervised_clip_driven_universal_swin_unetr_2100.pth?download=true) |\n| SuPreM | 62.19M | 2100 CT | ours :star2: | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/supervised_suprem_swinunetr_2100.pth?download=true) |\n\n\u003c/div\u003e\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary style=\"margin-left: 25px;\"\u003eU-Net\u003c/summary\u003e\n\u003cdiv style=\"margin-left: 25px;\"\u003e\n\n| name | params | pre-trained data | resources | download |\n|:----  |:----  |:----  |:----  |:----  |\n| [Models Genesis](http://www.cs.toronto.edu/~liang/Publications/ModelsGenesis/MICCAI_2019_Full.pdf) | 19.08M | 623 CT | [![GitHub stars](https://img.shields.io/github/stars/MrGiovanni/ModelsGenesis.svg?logo=github\u0026label=Stars)](https://github.com/MrGiovanni/ModelsGenesis) | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/self_supervised_models_genesis_unet_620.pt?download=true) |\n| [UniMiSS](https://link.springer.com/chapter/10.1007/978-3-031-19803-8_33) | tiny | 5022 CT\u0026MRI | [![GitHub stars](https://img.shields.io/github/stars/YtongXie/UniMiSS-code.svg?logo=github\u0026label=Stars)](https://github.com/YtongXie/UniMiSS-code) | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/self_supervised_unimiss_nnunet_tiny_5022.pth?download=true) |\n|  | small | 5022 CT\u0026MRI |  | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/self_supervised_unimiss_nnunet_small_5022.pth?download=true) |\n| [Med3D](https://arxiv.org/pdf/1904.00625.pdf) | 85.75M | 1638 CT | [![GitHub stars](https://img.shields.io/github/stars/Tencent/MedicalNet.svg?logo=github\u0026label=Stars)](https://github.com/Tencent/MedicalNet) | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/supervised_med3D_residual_unet_1623.pth?download=true) |\n| [DoDNet](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhang_DoDNet_Learning_To_Segment_Multi-Organ_and_Tumors_From_Multiple_Partially_CVPR_2021_paper.pdf) | 17.29M | 920 CT | [![GitHub stars](https://img.shields.io/github/stars/jianpengz/DoDNet.svg?logo=github\u0026label=Stars)](https://github.com/jianpengz/DoDNet) | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/supervised_dodnet_unet_920.pth?download=true) |\n| [Universal Model](https://openaccess.thecvf.com/content/ICCV2023/papers/Liu_CLIP-Driven_Universal_Model_for_Organ_Segmentation_and_Tumor_Detection_ICCV_2023_paper.pdf) | 19.08M | 2100 CT | [![GitHub stars](https://img.shields.io/github/stars/ljwztc/CLIP-Driven-Universal-Model.svg?logo=github\u0026label=Stars)](https://github.com/ljwztc/CLIP-Driven-Universal-Model) | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/supervised_clip_driven_universal_unet_2100.pth?download=true) |\n| SuPreM | 19.08M | 2100 CT | ours :star2: | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/supervised_suprem_unet_2100.pth?download=true) |\n\n\u003c/div\u003e\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary style=\"margin-left: 25px;\"\u003eSegResNet\u003c/summary\u003e\n\u003cdiv style=\"margin-left: 25px;\"\u003e\n\n| name | params | pre-trained data | resources | download |\n|:----  |:----  |:----  |:----  |:----  |\n| SuPreM | 4.70M | 2100 CT | ours :star2: | [weights](https://huggingface.co/MrGiovanni/SuPreM/resolve/main/supervised_suprem_segresnet_2100.pth?download=true) |\n\n\u003c/div\u003e\n\u003c/details\u003e\n\nExamples of predicting organ masks on unseen CT volumes using our SuPreM: [README](https://github.com/MrGiovanni/SuPreM/blob/main/direct_inference/README.md)\n\nExamples of fine-tuning our SuPreM on other downstream medical tasks are provided in this repository.\n\n| **task** | **dataset** | **document** |\n|:---------|:------------|:-----------|\n| organ, muscle, vertebrae, cardiac, rib segmentation | TotalSegmentator | [README](https://github.com/MrGiovanni/SuPreM/blob/main/target_applications/totalsegmentator/README.md) |\n| pancreas tumor detection | JHH | [README](https://github.com/MrGiovanni/SuPreM/blob/main/target_applications/pancreas_tumor_detection/README.md) |\n\n#### If you want to re-pre-train SuPreM on AbdomenAtlas 1.1 (*not recommended*), please refer to our [instruction](https://github.com/MrGiovanni/SuPreM/blob/main/supervised_pretraining/README.md)\n\nEstimated cost:\n- Eight A100 GPUs\n- At least seven days\n- 733GB disk space\n\n**\u0026#9733; Or simply make a request here: https://github.com/MrGiovanni/SuPreM/issues/1**\n\n\n## Citation\n\n```\n@article{li2024abdomenatlas,\n  title={AbdomenAtlas: A large-scale, detailed-annotated, \\\u0026 multi-center dataset for efficient transfer learning and open algorithmic benchmarking},\n  author={Li, Wenxuan and Qu, Chongyu and Chen, Xiaoxi and Bassi, Pedro RAS and Shi, Yijia and Lai, Yuxiang and Yu, Qian and Xue, Huimin and Chen, Yixiong and Lin, Xiaorui and others},\n  journal={Medical Image Analysis},\n  pages={103285},\n  year={2024},\n  publisher={Elsevier},\n  url={https://github.com/MrGiovanni/AbdomenAtlas}\n}\n\n@inproceedings{li2024well,\n  title={How Well Do Supervised Models Transfer to 3D Image Segmentation?},\n  author={Li, Wenxuan and Yuille, Alan and Zhou, Zongwei},\n  booktitle={The Twelfth International Conference on Learning Representations},\n  year={2024}\n}\n\n@article{bassi2024touchstone,\n  title={Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?},\n  author={Bassi, Pedro RAS and Li, Wenxuan and Tang, Yucheng and Isensee, Fabian and Wang, Zifu and Chen, Jieneng and Chou, Yu-Cheng and Kirchhoff, Yannick and Rokuss, Maximilian and Huang, Ziyan and Ye, Jin and He, Junjun and Wald, Tassilo and Ulrich, Constantin and Baumgartner, Michael and Roy, Saikat and Maier-Hein, Klaus H. and Jaeger, Paul and Ye, Yiwen and Xie, Yutong and Zhang, Jianpeng and Chen, Ziyang and Xia, Yong and Xing, Zhaohu and Zhu, Lei and Sadegheih, Yousef and Bozorgpour, Afshin and Kumari, Pratibha and Azad, Reza and Merhof, Dorit and Shi, Pengcheng and Ma, Ting and Du, Yuxin and Bai, Fan and Huang, Tiejun and Zhao, Bo and Wang, Haonan and Li, Xiaomeng and Gu, Hanxue and Dong, Haoyu and Yang, Jichen and Mazurowski, Maciej A. and Gupta, Saumya and Wu, Linshan and Zhuang, Jiaxin and Chen, Hao and Roth, Holger and Xu, Daguang and Blaschko, Matthew B. and Decherchi, Sergio and Cavalli, Andrea and Yuille, Alan L. and Zhou, Zongwei},\n  journal={Conference on Neural Information Processing Systems},\n  year={2024},\n  utl={https://github.com/MrGiovanni/Touchstone}\n}\n\n@article{qu2023abdomenatlas,\n  title={Abdomenatlas-8k: Annotating 8,000 CT volumes for multi-organ segmentation in three weeks},\n  author={Qu, Chongyu and Zhang, Tiezheng and Qiao, Hualin and Tang, Yucheng and Yuille, Alan L and Zhou, Zongwei and others},\n  journal={Advances in Neural Information Processing Systems},\n  volume={36},\n  year={2023}\n}\n```\n\n## Acknowledgement\n\nThis work was supported by the Lustgarten Foundation for Pancreatic Cancer Research and the McGovern Foundation. The codebase is modified from [NVIDIA MONAI](https://monai.io/). Paper content is covered by patents pending.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmrgiovanni%2Fsuprem","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmrgiovanni%2Fsuprem","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmrgiovanni%2Fsuprem/lists"}