CADS
收藏资源简介:
CADS是一个用于全身计算机断层扫描(CT)分割的全面解剖数据集和分割框架。该数据集包含22,022个CT体积,对167个解剖结构进行了完整注释,代表了在规模和覆盖范围方面的重大进展,比现有集合多18倍的扫描次数,以及多60%的不同解剖目标。该数据集的创建是为了解决现有全身方法在数据异构性和解剖覆盖率方面的不足。通过综合评估,CADS-model在各种临床场景中展现出优越的性能,并得到了放射科专家的认可。
CADS is a comprehensive anatomical dataset and segmentation framework for whole-body computed tomography (CT) segmentation. This dataset contains 22,022 CT volumes with complete annotations for 167 anatomical structures, representing a significant advancement in scale and coverage, with 18 times more scan cases and 60% more distinct anatomical targets than existing collections. This dataset was developed to address the shortcomings of existing whole-body methods in terms of data heterogeneity and anatomical coverage. Through comprehensive evaluations, the CADS-model exhibits superior performance across various clinical scenarios and has been validated by radiologists.
CADS : 全身计算机断层扫描解剖数据集与分割框架
概述
- 框架定位:用于CT影像中167个解剖结构的全自动分割框架,覆盖头部至膝盖区域
- 核心组成:
- CADS-dataset:22,022例带完整标注的CT扫描,当前最大规模全身CT数据集
- CADS-model:开源模型套件,支持命令行和3D Slicer插件两种使用方式
数据集特征
- 规模优势:
- 扫描量超现有数据集18倍
- 解剖目标数量多60%(167个结构)
- 数据来源:
- 公开数据集+私立医院数据
- 覆盖16个国家100+影像中心
- 技术特点:
- 采用伪标记和无监督质控的自动化流程构建
- 包含临床变异、扫描协议和病理状态的多样性
模型功能
- 任务划分:9个专用模型(551-559)对应不同解剖系统
- 部署方式:
- Python脚本运行
- 3D Slicer可视化插件
- 验证标准:通过公开挑战赛和真实医院队列验证
解剖结构覆盖
| 任务ID | 目标区域 |
|---|---|
| 551 | 腹部主要器官/胸腔主要器官/腹部大血管 |
| 552 | 颈椎至腰椎的完整椎体 |
| 553 | 胸腹器官/脑部/盆腔大血管/面部 |
| 554 | 附肢骨骼/骶骨/大肌肉群 |
| 555 | 完整左右肋骨组 |
| 556 | 放射治疗相关结构 |
| 557 | 脑部及头部组织 |
| 558 | 头颈部结构 |
| 559 | 通用组织类型/体腔/广义解剖类别 |
资源链接
- 论文预印本:https://arxiv.org/abs/2507.22953
- 数据集地址:https://huggingface.co/datasets/mrmrx/CADS-dataset
- 模型权重:https://github.com/murong-xu/CADS/releases/tag/cads-model_v1.0.0
- 3D Slicer插件:https://github.com/murong-xu/SlicerCADS
引用格式
bibtex @article{xu2025cads, title={CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography}, author={Xu, Murong and Amiranashvili, Tamaz and Navarro, Fernando and Fritsak, Maksym and Hamamci, Ibrahim Ethem and Shit, Suprosanna and Wittmann, Bastian and Er, Sezgin and Christ, Sebastian M. and de la Rosa, Ezequiel and Deseoe, Julian and Graf, Robert and Möller, Hendrik and Sekuboyina, Anjany and Peeken, Jan C. and Becker, Sven and Baldini, Giulia and Haubold, Johannes and Nensa, Felix and Hosch, René and Mirajkar, Nikhil and Khalid, Saad and Zachow, Stefan and Weber, Marc-André and Langs, Georg and Wasserthal, Jakob and Ozdemir, Mehmet Kemal and Fedorov, Andrey and Kikinis, Ron and Tanadini-Lang, Stephanie and Kirschke, Jan S. and Combs, Stephanie E. and Menze, Bjoern}, journal={arXiv preprint arXiv:2507.22953}, year={2025} }

- 1CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography苏黎世大学定量生物医学系,苏黎世,瑞士 · 2025年



