Dataset Overview

The AMOS dataset includes two main challenges: AMOS22 and AMOS-MM.

AMOS22 provides 500+ CT & 100+ MRI scans with 15 abdominal organs annotated (for semantic segmentation).

The AMOS-MM dataset includes 2000+ CT scans with comprehensive radiology reports (Findings & Impressions) covering Chest/Abdomen/Pelvis regions (for medical report generation), and 19,562 vision questions (for medical vision question answering).

600
Scans with 15 Annotated Organs
(500 CT & 100 MRI)
2000+
Clinical Reports
Chest, Abdomen & Pelvis
19,562
VQA Pairs
6 Clinical Scopes

Download

AMOS22
Semantic Segmentation
Zenodo
AMOS-MM
Report Generation & VQA
Google Drive

Citation

If you use the AMOS dataset in your research, please cite our paper: 
@article{ji2022amos,
    title     = {Amos: A large-scale abdominal multi-organ benchmark for versatile 
                 medical image segmentation},
    author    = {Ji, Yuanfeng and Bai, Haotian and Ge, Chongjian and Yang, Jie 
                 and Zhu, Ye and Zhang, Ruimao and Li, Zhen and Zhanng, Lingyan 
                 and Ma, Wanling and Wan, Xiang and others},
    journal   = {Advances in neural information processing systems},
    volume    = {35},
    pages     = {36722--36732},
    year      = {2022}
}
If you use GREEN-Score for the evaluation of medical report generation, please cite: 
@article{ostmeier2024green,
    title     = {GREEN: Generative Radiology Report Evaluation and Error Notation},
    author    = {Ostmeier, Sophie and Xu, Justin and Chen, Zhihong and Varma, Maya 
                 and Blankemeier, Louis and Bluethgen, Christian and Michalson, 
                 Arne Edward and Moseley, Michael and Langlotz, Curtis 
                 and Chaudhari, Akshay S and others},
    journal   = {arXiv preprint arXiv:2405.03595},
    year      = {2024}
}