人工智能技术在结肠镜退镜速度实时监控中的应用  

Application of artificial intelligence in real-time monitoring of withdrawal speed of colonoscopy

作　　者：朱晓芸[1,2] 吴练练 李素琴 李夏[1] 张军[1] 胡珊[3] 陈奕云[3] 于红刚[1] Zhu Xiaoyun;Wu Lianlian;Li Suqin;Li Xia;Zhang Jun;Hu Shan;Chen Yiyun;Yu Honggang(Department of Gastroenterology,Renmin Hospital of Wuhan University,Wuhan 430060,China;Department of Gastroenterology,Gansu Provincial Hospital,Lanzhou 730000,China;School of Resources and Environmental Sciences,Wuhan University,Wuhan 430060,China)

机构地区：[1]武汉大学人民医院消化内科,430060 [2]甘肃省人民医院消化科,兰州730000 [3]武汉大学资源与环境学院,430060

出　　处：《中华消化内镜杂志》2020年第2期125-130,共6页Chinese Journal of Digestive Endoscopy

基　　金：国家自然科学基金(81672387);湖北省自然科学基金(2016CFA066)。

摘　　要：目的构建一种基于计算机视觉的结肠镜退镜速度实时监控系统,并验证其可行性和性能。方法从武汉大学人民医院消化内镜中心数据库选取2018年5—10月期间的35938张肠镜图片和63个结肠镜检查视频。肠镜图片分成体外/体内/不合格和回盲部/非盲肠两个数据集,分别从第一个、第二个数据集中选取3594张和2000张图片用于深度学习模型的测试,其余图片用于训练模型;选取3个结肠镜检查视频资料评价实时监控系统自动监控退镜速度的可行性,剩余60个结肠镜检查视频资料用于评估实时监控系统的性能。结果深度学习模型对于结肠镜检查图片分类识别体外/体内/不合格图片的准确率分别为90.79%(897/988)、99.92%(1300/1301)、99.08%(1293/1305),总体准确率为97.11%(3490/3594);分类识别回盲部/非盲肠图片的准确率分别为96.70%(967/1000)、94.90%(949/1000),总体准确率为95.80%(1916/2000)。在其可行性评价方面,3个结肠镜视频资料显示退镜速度与图片处理间隔时间呈线性关系,提示该监控系统可在结肠镜退出过程中自动监控退镜速度。在其性能评价方面,结肠镜退镜速度实时监控系统正确预测了所有60个肠镜检查的开始时间和结束时间,分析显示结肠镜平均退镜速度和退镜时间呈明显负相关(R=-0.661,P<0.001),退镜时间不足5 min、5~6 min和超过6 min视频的平均退镜速度的95%置信区间分别为43.90~49.74、40.19~45.43和34.89~39.11,故将39.11设为安全退镜速度,将45.43设为预警退镜速度。结论构建的结肠镜退镜速度实时监控系统可用于实时监控结肠镜退镜速度,可在结肠镜检查中辅助内镜医师进行实时监测,以提高结肠镜检查质量。Objective To construct a real-time monitoring system based on computer vision for monitoring withdrawal speed of colonoscopy and to validate its feasibility and performance.Methods A total of 35938 images and 63 videos of colonoscopy were collected in endoscopic database of Renmin Hospital of Wuhan University from May to October 2018.The images were divided into two datasets,one dataset included in vitro,in vivo and unqualified colonoscopy images,and another dataset included ileocecal and non-cecal area images.And then 3594 and 2000 images were selected respectively from the two datasets for testing the deep learning model,and the remaining images were used to train the model.Three colonoscopy videos were selected to evaluate the feasibility of real-time monitoring system,and 60 colonoscopy videos were used to evaluate its performance.Results The accuracy rate of the deep learning model for classification for in vitro,in vivo,and unqualified colonoscopy images was 90.79%(897/988),99.92%(1300/1301),and 99.08%(1293/1305),respectively,and the overall accuracy rate was 97.11%(3490/3594).The accuracy rate of identifying ileocecal and non-cecal area was 96.70%(967/1000)and 94.90%(949/1000),respectively,and the overall accuracy rate was 95.80%(1916/2000).In terms of feasibility evaluation,3 colonoscopy videos data showed a linear relationship between the retraction speed and the image processing interval,which indicated that the real-time monitoring system automatically monitored the retraction speed during the colonoscopy withdrawal process.In terms of performance evaluation,the real-time monitoring system correctly predicted entry time and withdrawal time of all 60 examinations,and the results showed that the withdrawal speed and withdrawal time was significantly negative-related(R=-0.661,P<0.001).The 95%confidence interval of withdrawal speed for the colonoscopy with withdrawal time of less than 5 min,5-6 min,and more than 6 min was 43.90-49.74,40.19-45.43,and 34.89-39.11 respectively.Therefore,39.11 was set as the s

关 键 词：质量控制 人工智能 结肠镜检查 退镜时间 退镜速度 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] R57[自动化与计算机技术—控制科学与工程]