文献速递炎症性肠病消化内镜

溃疡性结肠炎内镜下疾病活动度的全自动评估

Fully automated endoscopic disease activity assessment in ulcerative colitis.
PubMed 文献 · Gastrointest Endosc · 2020-08-15

本研究开发并测试了一种全自动视频分析系统,用于对溃疡性结肠炎(UC)内镜疾病进行分级。开发集包含51段高分辨率视频,测试集为多中心临床试验的264段视频。自动方法在高分辨率视频中正确预测78%的Mayo内镜评分(MES),在临床试验视频中区分缓解与活动性疾病的准确率为83.7%。早期结果支持人工智能有望提供接近经验丰富评审者的内镜疾病分级。

要点

  • 全自动视频分析系统在高分辨率UC视频中正确预测MES的比率为78%(41/50,κ=0.84)。
  • 在多中心临床试验视频中,自动评分与中心评审者一致率为57.1%(κ=0.59),考虑评审者分歧后提高至69.5%(107/169)。
  • 自动MES分级区分缓解(MES 0,1)与活动性疾病(MES 2,3)的准确率为83.7%(221/264)。

核心结论

  • 这些早期结果支持人工智能有潜力提供接近经验丰富评审者评分的UC内镜疾病分级。

研究设计与样本

  • 开发集为51段高分辨率UC内镜视频,由2名经验丰富的评审者提供Mayo内镜评分(MES)。
  • 使用卷积神经网络训练预测静态图像信息性和疾病严重程度的模型。
  • 采用模板匹配网格搜索,基于预测的静态图像MES比例估计整个人类评审者提供的全视频MES。
  • 自动化全视频MES工作流在多中心UC临床试验的未修改内镜视频(264段)中进行测试。

主要发现

  • 静态图像信息性分类器性能优异,敏感性为0.902,特异性为0.870。
  • 在高分辨率视频中,全自动方法正确预测MES的比率为78%(41/50,κ=0.84)。
  • 在外部临床试验视频中,评审者MES一致率为82.8%(140/169,κ=0.78)。
  • 自动评分与中心评审者评分一致率为57.1%(κ=0.59),考虑评审者分歧后提高至69.5%(107/169)。
  • 对临床试验视频(常为低分辨率)的自动MES分级正确区分缓解(MES 0,1)与活动性疾病(MES 2,3)的比率为83.7%(221/264)。

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: Endoscopy is essential for disease assessment in ulcerative colitis (UC), but subjectivity threatens accuracy and precision. We aimed to pilot a fully automated video analysis system for grading endoscopic disease in UC. METHODS: A developmental set of high-resolution UC endoscopic videos were assigned Mayo endoscopic scores (MESs) provided by 2 experienced reviewers. Video still-image stacks were annotated for image quality (informativeness) and MES. Models to predict still-image informativeness and disease severity were trained using convolutional neural networks. A template-matching grid search was used to estimate whole-video MESs provided by human reviewers using predicted still-image MES proportions. The automated whole-video MES workflow was tested using unaltered endoscopic videos from a multicenter UC clinical trial. RESULTS: The developmental high-resolution and testing multicenter clinical trial sets contained 51 and 264 videos, respectively. The still-image informative classifier had excellent performance with a sensitivity of 0.902 and specificity of 0.870. In high-resolution videos, fully automated methods correctly predicted MESs in 78% (41 of 50, κ = 0.84) of videos. In external clinical trial videos, reviewers agreed on MESs in 82.8% (140 of 169) of videos (κ = 0.78). Automated and central reviewer scoring agreement occurred in 57.1% of videos (κ = 0.59), but improved to 69.5% (107 of 169) when accounting for reviewer disagreement. Automated MES grading of clinical trial videos (often low resolution) correctly distinguished remission (MES 0,1) versus active disease (MES 2,3) in 83.7% (221 of 264) of videos. CONCLUSIONS: These early results support the potential for artificial intelligence to provide endoscopic disease grading in UC that approximates the scoring of experienced reviewers.

来源:Gastrointest Endosc,查看原文。版权归原作者所有。

引用

  1. Yao H, Najarian K, Gryak J, et al. Fully automated endoscopic disease activity assessment in ulcerative colitis. Gastrointest Endosc. 2020. PMID: 32810479. doi:10.1016/j.gie.2020.08.011

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。