文献速递消化内镜消化道肿瘤与早癌

结肠镜计算机辅助检测系统的开发及可公开访问的大型结肠镜视频数据库(附视频)

Development of a computer-aided detection system for colonoscopy and a publicly accessible large colonoscopy video database (with video).
PubMed 文献 · Gastrointest Endosc · 2020-07-31

本研究开发了基于深度学习的结肠镜息肉检测人工智能系统,使用5个中心的56,668张独立结肠镜图像进行训练。验证数据库来自2018年10月至2019年1月期间一所大学医院的1405段连续结肠镜视频,随机抽取100段含100个独立息肉及13段无息肉视频,共152,560帧。人工智能在帧水平分析中灵敏度为90.5%、特异度为93.7%,对各型息肉检测灵敏度高。

要点

  • 基于深度学习的人工智能息肉检测系统使用5个中心56,668张结肠镜图像训练。
  • 验证数据库共152,560帧,其中阳性帧49,799帧、阴性帧102,761帧。
  • 帧水平分析灵敏度90.5%、特异度93.7%,息肉水平灵敏度98.0%。

核心结论

  • 训练的人工智能系统通过新的大型可公开访问结肠镜数据库验证,能以高灵敏度和特异度识别结直肠病变。

研究设计与样本

  • 为开发深度学习人工智能系统,从5个中心获取56,668张独立结肠镜图像作为训练图像。
  • 为验证训练后的人工智能系统,检索2018年10月至2019年1月期间在大学医院拍摄的连续结肠镜视频,构建包含息肉且方差无偏的数据库。
  • 所有图像由内镜医师根据有无息肉及息肉位置以边界框进行标注。

主要发现

  • 研究期间共识别1405段视频用于验证数据库,其中797段至少含1个息肉。
  • 随机抽取100段含100个独立息肉的视频和13段无息肉视频,获得152,560帧(阳性帧49,799帧,阴性帧102,761帧)。
  • 人工智能帧水平分析灵敏度为90.5%,特异度为93.7%。
  • 息肉水平灵敏度:所有息肉98.0%,微小息肉98.3%,隆起型息肉98.5%,平坦型息肉97.0%。

局限性

  • 原文未报告局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND AND AIMS: Artificial intelligence (AI)-assisted polyp detection systems for colonoscopic use are currently attracting attention because they may reduce the possibility of missed adenomas. However, few systems have the necessary regulatory approval for use in clinical practice. We aimed to develop an AI-assisted polyp detection system and to validate its performance using a large colonoscopy video database designed to be publicly accessible. METHODS: To develop the deep learning-based AI system, 56,668 independent colonoscopy images were obtained from 5 centers for use as training images. To validate the trained AI system, consecutive colonoscopy videos taken at a university hospital between October 2018 and January 2019 were searched to construct a database containing polyps with unbiased variance. All images were annotated by endoscopists according to the presence or absence of polyps and the polyps' locations with bounding boxes. RESULTS: A total of 1405 videos acquired during the study period were identified for the validation database, 797 of which contained at least 1 polyp. Of these, 100 videos containing 100 independent polyps and 13 videos negative for polyps were randomly extracted, resulting in 152,560 frames (49,799 positive frames and 102,761 negative frames) for the database. The AI showed 90.5% sensitivity and 93.7% specificity for frame-based analysis. The per-polyp sensitivities for all, diminutive, protruded, and flat polyps were 98.0%, 98.3%, 98.5%, and 97.0%, respectively. CONCLUSIONS: Our trained AI system was validated with a new large publicly accessible colonoscopy database and could identify colorectal lesions with high sensitivity and specificity. (Clinical trial registration number: UMIN 000037064.).

来源:Gastrointest Endosc,查看原文。版权归原作者所有。

引用

  1. Misawa M, Kudo SE, Mori Y, et al. Development of a computer-aided detection system for colonoscopy and a publicly accessible large colonoscopy video database (with video). Gastrointest Endosc. 2020. PMID: 32745531. doi:10.1016/j.gie.2020.07.060

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。