The Warren Alpert Medical School of Brown University, Division of Gastroenterology, Providence, Rhode Island, 02903, United States of America.
Chulabhorn Hospital, Chulabhorn Royal Academy, Bangkok, 10210, Thailand.
Sci Data. 2022 Oct 6;9(1):602. doi: 10.1038/s41597-022-01726-3.
Complete endoscopic evaluation of the small bowel is challenging due to its length and anatomy. Although several advances have been made to achieve diagnostic and therapeutic goals, including double-balloon enteroscopy, single-balloon enteroscopy, and spiral enteroscopy, video capsule endoscopy (VCE) remains the least invasive tool for complete visualization of the small bowel and is the preferred method for initial diagnostic evaluation. At present, interpretation of VCE data requires manual annotation of landmarks and abnormalities in recorded videos, which can be time consuming. Computer-assisted diagnostic systems using artificial intelligence may help to optimize VCE reading efficiency by reducing the need for manual annotation. Here we present a large VCE data set compiled from studies performed at two United States hospitals in Providence, Rhode Island, including 424 VCE studies and 5,247,588 total labeled images. In conjunction with existing published data sets, these files may aid in the development of algorithms to further improve VCE.
由于小肠的长度和解剖结构，对其进行全面的内镜评估具有挑战性。尽管已经取得了一些进展，以实现诊断和治疗目标，包括双气囊小肠镜、单气囊小肠镜和螺旋小肠镜，但视频胶囊内镜（VCE）仍然是全面可视化小肠的最微创工具，也是初始诊断评估的首选方法。目前，VCE 数据的解释需要手动标注记录视频中的地标和异常，这可能很耗时。使用人工智能的计算机辅助诊断系统可以通过减少手动标注的需求来帮助优化 VCE 阅读效率。在这里，我们展示了一个从美国罗德岛普罗维登斯的两家医院进行的研究中编译的大型 VCE 数据集，其中包括 424 项 VCE 研究和 5247588 张总标记图像。与现有的已发表数据集结合使用，这些文件可能有助于开发算法以进一步改进 VCE。
