CheXpert Plus
收藏DataCite Commons2024-11-20 更新2025-04-16 收录
下载链接:
https://aimi.stanford.edu/datasets/chexpert-plus
下载链接
链接失效反馈官方服务:
资源简介:
The CheXpert Plus dataset is a comprehensive collection that brings together text and images in the medical field, featuring a total of 223,462 unique pairs of radiology reports and chest X-rays across 187,711 studies from 64,725 patients. This dataset is notable for its organization and depth, with each patient potentially linked to multiple studies, and each study possibly including several chest X-rays. The X-rays are provided in DICOM format, including 47 DICOM metadata elements to support detailed analysis. Accompanying these images are 187,711 radiology reports, each meticulously divided into 11 subsections for thorough examination. Finally, the dataset is enriched with annotations for 14 different chest pathologies across the studies, alongside 8 metadata elements concerning patient information. The curation and release of this dataset was supported in part by the Medical Imaging and Data Resource Center (MIDRC), which is funded by the National Institute of Biomedical Imaging and Bioengineering (NIBIB) of the National Institutes of Health under contract 75N92020D00021 and through The Advanced Research Projects Agency for Health (ARPA-H).
CheXpert Plus数据集是一款汇聚医学文本与影像的综合性数据集,共计包含来自64725名患者的187711项研究,对应223464组独立的放射学报告与胸部X线影像配对。该数据集以其规整的组织形式与丰富的内容深度著称:每位患者可关联多项研究,而每项研究可能包含多幅胸部X线影像。此类影像采用DICOM格式存储,内含47项DICOM元数据元素,可支撑精细化的分析工作。随影像配套的187711份放射学报告均被细致划分为11个子模块,便于开展全面解析。此外,该数据集还针对各项研究中的14种胸部病变提供了标注信息,并补充了8项患者相关元数据。本数据集的整理与发布得到了医学影像与数据资源中心(Medical Imaging and Data Resource Center, MIDRC)的部分支持;该中心由美国国立卫生研究院下属的美国国立生物医学成像与生物工程研究所(National Institute of Biomedical Imaging and Bioengineering, NIBIB)依据合同75N92020D00021资助,并获得了美国卫生高级研究计划局(Advanced Research Projects Agency for Health, ARPA-H)的支持。
提供机构:
Center for Artificial Intelligence in Medicine and Imaging
创建时间:
2024-10-15
搜集汇总
数据集介绍

背景与挑战
背景概述
CheXpert Plus数据集是一个医学领域的综合数据集,包含223,462对放射学报告和胸部X光片,覆盖64,725名患者的187,711项研究。数据集提供DICOM格式的X光片和详细标注的14种胸部病理,支持深入的医学影像分析。
以上内容由遇见数据集搜集并总结生成



