基于深度学习的系统自动检测胶囊内镜视频中多种异常:一项多中心研究
本研究训练了一个基于深度卷积神经网络(CNN)的系统,使用66,028张胶囊内镜图像,并在来自3家机构的379段连续小肠胶囊内镜视频上独立测试,按患者评估其对黏膜破损、血管扩张、隆起性病变和血液内容物等多种异常的检出率,并与QuickView模式比较。CNN对异常的总检出率显著高于QuickView模式(99% vs 89%,P < .001),结论认为该系统可作为QuickView模式的替代高级筛查工具。
要点
- CNN对多种异常的总检出率显著高于QuickView模式(99% vs 89%,P < .001)。
- CNN对黏膜破损、血管扩张、隆起性病变和血液内容的检出率分别为100%、97%、99%和100%。
- CNN从5,050,226张测试图像中选取1,135,104张(22.5%),QuickView采样率设为23%。
核心结论
- 基于CNN的检测系统使用多中心胶囊内镜视频开发并测试,可作为QuickView模式的替代高级筛查工具。
研究设计与样本
- 使用66,028张胶囊内镜图像(44,684张异常图像和21,344张正常图像)训练CNN系统。
- 使用来自3家机构的379段连续小肠胶囊内镜视频作为独立测试集,按患者评估CNN对多种异常的检出率。
- 测试集中黏膜破损、血管扩张、隆起性病变和血液内容物分别见于94、29、81和23例患者。
- 将CNN的检测能力与QuickView模式进行比较。
主要发现
- CNN从5,050,226张测试图像中选取1,135,104张(22.5%),因此本研究将QuickView模式的采样率设为23%。
- CNN对异常的总检出率显著高于QuickView模式(99% vs 89%,P < .001)。
- CNN对黏膜破损、血管扩张、隆起性病变和血液内容的检出率分别为100%(94/94)、97%(28/29)、99%(80/81)和100%(23/23)。
- QuickView模式对黏膜破损、血管扩张、隆起性病变和血液内容的检出率分别为91%、97%、80%和96%。
临床怎么用
- 原文结论认为该系统可作为QuickView模式的替代高级筛查工具。
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: A deep convolutional neural network (CNN) system could be a high-level screening tool for capsule endoscopy (CE) reading but has not been established for targeting various abnormalities. We aimed to develop a CNN-based system and compare it with the existing QuickView mode in terms of their ability to detect various abnormalities. METHODS: We trained a CNN system using 66,028 CE images (44,684 images of abnormalities and 21,344 normal images). The detection rate of the CNN for various abnormalities was assessed per patient, using an independent test set of 379 consecutive small-bowel CE videos from 3 institutions. Mucosal breaks, angioectasia, protruding lesions, and blood content were present in 94, 29, 81, and 23 patients, respectively. The detection capability of the CNN was compared with that of QuickView mode. RESULTS: The CNN picked up 1,135,104 images (22.5%) from the 5,050,226 test images, and thus, the sampling rate of QuickView mode was set to 23% in this study. In total, the detection rate of the CNN for abnormalities per patient was significantly higher than that of QuickView mode (99% vs 89%, P < .001). The detection rates of the CNN for mucosal breaks, angioectasia, protruding lesions, and blood content were 100% (94 of 94), 97% (28 of 29), 99% (80 of 81), and 100% (23 of 23), respectively, and those of QuickView mode were 91%, 97%, 80%, and 96%, respectively. CONCLUSIONS: We developed and tested a CNN-based detection system for various abnormalities using multicenter CE videos. This system could serve as an alternative high-level screening tool to QuickView mode.
引用
- Aoki T, Yamada A, Kato Y, et al. Automatic detection of various abnormalities in capsule endoscopy videos by a deep learning-based system: a multicenter study. Gastrointest Endosc. 2020. PMID: 32417297. doi:10.1016/j.gie.2020.04.080
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。