糖尿病视网膜病变人工智能机器人辅助诊断系统的建立及应用  

Validation and application of an artificial intelligence robot assisted diagnosis system for diabetic retinopathy

作　　者：高韶晖 金学民[1] 赵朝霞[1] 于伟泓[2] 陈有信[2] 孙宇辉 丁大勇 Gao Shaohui;Jin Xuemin;Zhao Zhaoxia;Yu Weihong;Chen Youxin;Sun Yuhui;Ding Dayong(Department of Ophthalmology,Henan Provincial People's Hospital,Henan Eye Hospital,Henan Eye Institute,Zhengzhou 450003,China;Department of Ophthalmology,Peking Union Medical College Hospital,Chinese Academy of Medical Sciences,Beijing 100730,China;Beijing Visionary Intelligence Technology Ltd.,Beijing 100086,China)

机构地区：[1]河南省人民医院眼科河南省立眼科医院河南省眼科研究所,郑州450003 [2]中国医学科学院北京协和医院眼科,北京100730 [3]北京致远慧图科技有限公司,100086

出　　处：《中华实验眼科杂志》2019年第8期669-673,共5页Chinese Journal Of Experimental Ophthalmology

基　　金：河南省科技攻关项目(162102410004);河南省立眼科医院影像与人工智能研发平台.

摘　　要：目的建立和评估基于深度学习理论的糖尿病视网膜病变(DR)人工智能(AI)机器人辅助诊断系统。方法联合包括北京协和医院等国内8家医院眼底专业医师对25297张糖尿病患者眼底图像病变进行标记,训练和建立一个深度学习框架同时识别DR病变的AI机器人辅助诊断系统,即“嵩岳”机器人系统。依据DR分级和标识眼底病变,构建是否罹患DR、是否需要转诊DR、是否重度非增生性和增生性DR以及是否增生性DR4种模型,建立一个基于病变识别技术的DR筛选系统,应用受试者工作特征曲线(ROC曲线)、敏感度、特异度进行AI诊断性能的数据分析。结果“嵩岳”系统中是否罹患DR模型的敏感度为96.0%,特异度为87.9%,曲线下面积(AUC)为0.920;需要转诊DR模型的敏感度为90.4%,特异度为95.2%,AUC为0.925;是否为重度非增生性和增生性DR模型的敏感度为72.7%,特异度为96.2%,AUC为0.845;增生性DR模型的敏感度为73.5%,特异度为97.3%,AUC为0.855。结论“嵩岳”AI机器人辅助诊断系统具有精确高效的DR诊断性能,具有良好的临床应用价值。Objective To evaluate the performance of an artificial intelligence (AI) assisted diagnosis system for diabetic retinopathy (DR) based on deep learning theory. Methods Diagnostic performance of a robot assisted diagnosis system called SongYue for DR was trained by using 25 297 retinal images tagged by fundus doctors from multiple hospitals in China.Four types of DR detection model consisting of abnormal DR,referable DR,severe non-proliferative and proliferative DR as well as proliferative DR according to fundus leisions identification were established.The ability of the system to distinguish DR was determined by using receiver operator characteristic (ROC) analysis,sensitivity and specificity of the system. Results SongYue system achieved an area under the ROC curve (AUC) of 0.920 for successfully distinguishing normal images from those DR with a sensitivity of 96.0% at a specificity of 87.9%.The AUC of SongYue for referable DR was 0.925,sensitivity was 90.4%,and specificity was 95.2%.For severe non-proliferative and proliferative DR,AUC was 0.845,sensitivity was 72.7%,and specificity was 96.2%.For proliferative DR,AUC was 0.855,sensitivity was 73.5%,and specificity was 97.3%. Conclusions SongYue robot assisted diagnosis system has high AUC,sensitivity and specificity for identifying DR,showing good clinical applicable benefits.

关 键 词：糖尿病视网膜病变 人工智能 机器人 辅助诊断 深度学习 

分 类 号：R587.2[医药卫生—内分泌]