RAOS
收藏资源简介:
RAOS数据集是由中国电子科技大学和上海AI实验室合作创建,包含413个腹部CT扫描数据,涵盖约80k 2D图像和8k 3D器官标注,涉及19种不同器官。该数据集特别关注临床挑战性案例,如器官切除后的情况,旨在评估模型在复杂场景下的鲁棒性。数据集的创建过程包括由资深肿瘤学家手动标注,确保了数据的高质量和准确性。RAOS数据集的应用领域主要集中在腹部器官分割,特别是在放射治疗规划中,以提高诊断和治疗的精确性。
The RAOS dataset was collaboratively developed by the University of Electronic Science and Technology of China and the Shanghai AI Laboratory. It contains 413 abdominal CT scan datasets, covering approximately 80k 2D images and 8k 3D organ annotations involving 19 distinct organs. This dataset specifically focuses on clinically challenging cases such as post-organ resection scenarios, with the goal of evaluating model robustness in complex clinical scenarios. During its construction, the dataset was manually annotated by senior oncologists, ensuring high data quality and accuracy. The primary application fields of the RAOS dataset center on abdominal organ segmentation, especially in radiation therapy planning, to improve the accuracy of diagnosis and treatment.
RAOS 数据集概述
数据集内容
- 类型与数量:包含413个真实临床CT扫描和413x9个MR扫描。
- 标注内容:所有19个器官均由资深肿瘤学家(MD. Wenjun Liao,10年经验)进行标注。
- 特殊标注:包含一些在先前公开数据集中未出现的器官标注,如前列腺、精囊等。
数据集特点
- 挑战性案例:包含一些临床实践中具有挑战性的案例,有助于评估深度学习方法的泛化能力和鲁棒性。
数据获取
- 申请流程:
- 使用Google邮箱申请下载权限。
- 使用机构邮箱获取解压密码或百度网盘访问码。
- 回复时间:申请后将在两天内回复。
- 申请要求:仅处理实名邮箱,且邮箱后缀必须与机构匹配。
引用信息
-
推荐引用: plaintext @article{luo2022word, title={{WORD}: A large-scale dataset, benchmark and clinically applicable study for abdominal organ segmentation from CT image}, author={Xiangde Luo, Wenjun Liao, Jianghong Xiao, Jieneng Chen, Tao Song, Xiaofan Zhang, Kang Li, Dimitris N. Metaxas, Guotai Wang, and Shaoting Zhang}, journal={Medical Image Analysis}, volume={82}, pages={102642}, year={2022}, publisher={Elsevier}}
@article{luo2024rethinking, title={Rethinking Abdominal Organ Segmentation (RAOS) in the clinical scenario: A robustness evaluation benchmark with challenging cases}, author={Luo, Xiangde and Li, Zihan and Zhang, Shaoting and Liao, Wenjun and Wang, Guotai}, booktitle={Medical Image Computing and Computer Assisted Intervention -- MICCAI 2024}, year={2024}, pages={}}




