AMOS Unlabeled Data Part I: Abdominal CT Scans
others and Ji, Yuanfeng and Bai, Haotian and Yang, Jie and Ge, Chongjian and Zhu, Ye and Zhang, Ruimao and Li, Zhen and Zhang, Lingyan and Ma, Wanling and Wan, Xiang

@article{ji2022amos_unlabeled_ct_part1,
  title={AMOS Unlabeled Data Part I: Unlabeled Abdominal CT Scans},
  author={Ji, Yuanfeng and Bai, Haotian and Yang, Jie and Ge, Chongjian and Zhu, Ye and Zhang, Ruimao and Li, Zhen and Zhang, Lingyan and Ma, Wanling and Wan, Xiang and others},
  journal={arXiv preprint arXiv:2206.08023},
  year={2022},
  url={https://zenodo.org/records/7262586},
  doi={10.5281/zenodo.7262586},
  keywords={medical imaging, CT, abdominal, segmentation, unlabeled, semi-supervised},
  license={CC BY 4.0},
  abstract={**Unlabeled abdominal CT scans** from AMOS, a large-scale, multi-center clinical benchmark for abdominal multi-organ segmentation. These scans have no annotations. They are meant for semi-supervised, self-supervised, unsupervised and domain adaptation research.

## What is in this torrent

A single file, `amos22_unlabeled_ct_5000_5399.zip` (23.3 GB), holding the unlabeled CT volumes with case IDs in the 5000 to 5399 range.

## About AMOS

Most abdominal segmentation datasets cover few organs or few patients. AMOS provides 500 CT and 100 MRI scans from multiple centers, vendors, modalities, phases and diseases, each annotated voxel by voxel for 15 abdominal organs. The authors also benchmark several state of the art segmentation models on it. The labeled scans and the unlabeled parts are released separately.

## Other parts of AMOS

- Labeled data: 500 CT and 100 MRI scans
- Unlabeled Part I: CT scans (this torrent)
- Unlabeled Part II: CT scans
- Unlabeled Part III: MRI scans

## Links

- Paper: https://arxiv.org/abs/2206.08023
- Original record: https://zenodo.org/records/7262586
- DOI: 10.5281/zenodo.7262586

## License

CC BY 4.0. Attribution is required.

## Citation

If you use this data, please cite:

    Ji, Y., Bai, H., Yang, J., Ge, C., Zhu, Y., Zhang, R., Li, Z., Zhang, L., Ma, W., Wan, X., et al.
    AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation.
    arXiv preprint arXiv:2206.08023, 2022.
  }
}