We are proud to introduce AbdomenAtlas-8K, a substantial multi-organ dataset with the spleen, liver, kidneys, stomach, gallbladder, pancreas, aorta, and IVC annotated in 8,448 CT volumes, totaling 3.2 million CT slices.
An endeavor of such magnitude would demand a staggering 1,600 weeks or roughly 30.8 years of an experienced annotator's time.
In contrast, our annotation method has accomplished this task in three weeks (premised on an 8-hour workday, five days a week) while maintaining a similar or even better annotation quality.
| Option | Image & Mask | Image-Only | Mask-Only | |
|---|---|---|---|---|
| Huggingface | All-in-one | Download (3.3GB) A single compressed file containing all labels. |
||
| Zips | Download (328GB) 11 compressed files in TAR.GZ format. |
Download 11 compressed files in TAR.GZ format. |
||
| Folders | Download (340GB) 5,195 folders, each containing CT, combined labels, and a segmentations folder of nine masks in NII.GZ format. |
Download (325GB) 5,195 folders, each containing CT in NII.GZ format. |
Download (15GB) 5,195 folders, each containing combined labels, and a segmentations folder of nine masks in NII.GZ format. |
|
| Dropbox | All-in-one | Download (306GB) A single compressed file containing all images and labels. |
Download (303GB) A single compressed file containing all images. |
Download (3.3GB) A single compressed file containing all labels. |
| Zips | Download (328GB) 11 compressed files in TAR.GZ format. |
Download 11 compressed files in TAR.GZ format. |
||
| Baidu Wangpan | All-in-one | Download (306GB) A single compressed file containing all images and labels. |
Download (303GB) A single compressed file containing all images. |
Download (3.3GB) A single compressed file containing all labels. |
| Zips | Download (328GB) 11 compressed files in TAR.GZ format. |
Download 11 compressed files in TAR.GZ format. |
AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarking
Wenxuan Li, Chongyu Qu, 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, Zongwei Zhou*
Johns Hopkins University
Medical Image Analysis, 2024
AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks
Chongyu Qu1, Tiezheng Zhang1, Hualin Qiao2, Jie Liu3, Yucheng Tang4, Alan L. Yuille1, and Zongwei Zhou1,*
1 Johns Hopkins University,
2 Rutgers University,
3 City University of Hong Kong,
4 NVIDIA
NeurIPS 2023
paper | code | dataset | poster
AbdomenAtlas-8K: Human-in-the-Loop Annotating Eight Anatomical Structures for 8,448 Three-Dimensional Computed Tomography Volumes in Three Weeks
Chongyu Qu1, Tiezheng Zhang1, Hualin Qiao2, Jie Liu3, Yucheng Tang4, Alan L. Yuille1, and Zongwei Zhou1,*
1 Johns Hopkins University,
2 Rutgers University,
3 City University of Hong Kong,
4 NVIDIA
RSNA 2023 (Oral Presentation)
paper | code | slides
★ An improved version, AbdomenAtlas 1.1, can be found at SuPreM 
★ Touchstone - Let's benchmark!
★ We have maintained a document for Frequently Asked Questions.
git clone https://github.com/MrGiovanni/AbdomenAtlasSee installation instructions to create an environment and obtain requirements.
We offer pre-trained checkpoints of Swin UNETR and U-Net. The models were trained on a combination of 14 publicly available CT datasets, consisting of 3,410 (see details in CLIP-Driven Universal Model).
Download the trained models and save them into ./pretrained_checkpoints/.
| Architecture | Param | Download |
|---|---|---|
| U-Net | 19.08M | link |
| Swin UNETR | 62.19M | link |
It can be publicly available datasets (e.g., BTCV) or your private datasets. Currently, we only take data formatted in nii.gz. This repository will help you assign annotations to these datasets, including 25 organs and six types of tumors (where the annotation of eight organs is pretty accurate).
Taking the BTCV dataset as an example, download this dataset and save it to the datapath directory.
cd $datapath
wget https://www.dropbox.com/s/jnv74utwh99ikus/01_Multi-Atlas_Labeling.tar.gz
tar -xzvf 01_Multi-Atlas_Labeling.tar.gzGenerate a list for this dataset.
cd AbdomenAtlas/
python -W ignore generate_datalist.py --data_path $datapath --dataset_name $dataname --folder img --out ./dataset/dataset_list --save_file $dataname.txtCUDA_VISIBLE_DEVICES=0 python -W ignore test.py --resume pretrained_checkpoints/unet.pth --backbone unet --save_dir $savepath --dataset_list $dataname --data_root_path $datapath --store_result >> logs/$dataname.unet.txtCUDA_VISIBLE_DEVICES=0 python -W ignore test.py --resume pretrained_checkpoints/swinunetr.pth --backbone swinunetr --save_dir $savepath --dataset_list $dataname --data_root_path $datapath --store_result >> logs/$dataname.swinunetr.txtTo generate attention maps for the active learning process (Step 5 [optional]), remember to save entropy and soft predictions by using the options --store_entropy and --store_soft_pred
In the assembly process, our utmost priority is given to the original annotations supplied by each public dataset. Subsequently, we assign secondary priority to the revised labels from our annotators. The pseudo labels, generated by AI models, are accorded the lowest priority. The following code can implement this priority into the assembled dataset.
python -W ignore assemble.py --data_path $savepath --dataset_name $dataname --backbone swinunetr --save_dir SAVE_DIR --version V1This is how our AbdonmenAtlas-8K appears
$savepath/
├── $dataname_img0001
├── $dataname_img0002
├── $dataname_img0003
│── ct.nii.gz
├── original_label.nii.gz
├── pseudo_label.nii.gz
└── segmentations
├── spleen.nii.gz
├── liver.nii.gz
├── pancreas.nii.gz
If you want to perform the active learning process, you will need the following active learning instructions to generate the attention map for human annotators.
- Release pre-trained AI model checkpoints (U-Net and Swin UNETR)
- Release the AbdomenAtlas-8K dataset (we commit to releasing 3,410 of the 8,448 CT volumes)
- Support more data formats (e.g., dicom)
@article{li2024abdomenatlas,
title={AbdomenAtlas: A large-scale, detailed-annotated, \& multi-center dataset for efficient transfer learning and open algorithmic benchmarking},
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},
journal={Medical Image Analysis},
pages={103285},
year={2024},
publisher={Elsevier},
url={https://github.com/MrGiovanni/AbdomenAtlas}
}
@article{qu2023abdomenatlas,
title={Abdomenatlas-8k: Annotating 8,000 CT volumes for multi-organ segmentation in three weeks},
author={Qu, Chongyu and Zhang, Tiezheng and Qiao, Hualin and Tang, Yucheng and Yuille, Alan L and Zhou, Zongwei and others},
journal={Advances in Neural Information Processing Systems},
volume={36},
year={2023}
}
@inproceedings{li2024well,
title={How Well Do Supervised Models Transfer to 3D Image Segmentation?},
author={Li, Wenxuan and Yuille, Alan and Zhou, Zongwei},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024}
}
This work was supported by the Lustgarten Foundation for Pancreatic Cancer Research and partially by the Patrick J. McGovern Foundation Award. We appreciate the effort of the MONAI Team to provide open-source code for the community.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent