huggingface/CADS-dataset

CADS是一个强大的、完全自动化的框架，用于在计算机断层扫描（CT）中分割167个解剖结构，覆盖从头到膝的多个解剖系统。数据集包含22,022个CT扫描，标注了167个解剖结构，是目前规模最大、覆盖解剖结构最全面的全身CT数据集。数据来源于公开数据集和私人医院数据，覆盖100多个影像中心和16个国家。数据集分为多个子集，每个子集都有自己的许可证和详细信息。数据集主要用于医学图像分割任务，特别是CT图像中的全身解剖结构分割。

CADS is a robust, fully automated framework for segmenting 167 anatomical structures in Computed Tomography (CT), spanning from head to knee regions across diverse anatomical systems. The dataset includes 22,022 CT volumes with complete annotations for 167 anatomical structures. It is the most extensive whole-body CT dataset, exceeding current collections in both scale (18x more CT scans) and anatomical coverage (60% more distinct targets). Data is collected from publicly available datasets and private hospital data, spanning 100+ imaging centers across 16 countries. The dataset is divided into multiple subsets, each with its own license and detailed information. It is primarily used for medical image segmentation tasks, particularly whole-body anatomical segmentation in CT images.