基于深度学习的DR筛查智能诊断系统的初步研究  

A preliminary study of a deep learning-assisted diagnostic system with an artificial intelligence for detection of diabetic retinopathy

作　　者：翁铭 郑博 吴茂念[2,3] 朱绍军 孙元强 刘云芳 马子伟[1,2] 蒋云良 刘勇[4] 杨卫华 

机构地区：[1]湖州师范学院附属第一医院眼科,中国浙江省湖州市313000 [2]湖州师范学院医学人工智能重点实验室,中国浙江省湖州市313000 [3]湖州师范学院信息工程学院,中国浙江省湖州市313000 [4]浙江大学控制科学与工程学院,中国浙江省湖州市310058

出　　处：《国际眼科杂志》2018年第3期568-571,共4页International Eye Science

基　　金：浙江省自然科学基金项目(No.LQ18F020002);浙江省公益技术研究计划项目(No.LGF18H120003)~~

摘　　要：目的:评估基于深度学习的糖尿病视网膜病变(diabetic retinopathy,DR)筛查智能诊断系统的应用价值。方法:收集2017-01/06在我院就诊的糖尿病患者186例372眼,比较专家诊断及基于深度学习的人工智能诊断的应用情况,并比较其特异性和敏感性。结果:专家诊断组显示42眼(11.3%)为无DR,330眼(88.7%)患有不同程度DR;其中轻度非增殖型糖尿病视网膜病变(non-proliferative diabetic retinopathy,NPDR)者62眼(16.7%),中度NPDR者55眼(14.8%),重度NPDR者155眼(41.7%),PDR者58眼(15.6%)。而智能诊断结果显示38眼(10.2%)为无DR,44眼为PDR(11.8%),其他为不同分期NPDR。智能诊断系统与专家诊断结果DR一致性分析结果显示,高度一致性为309眼(83.1%),Kappa值为0.78。智能诊断灵敏度为0.82,特异性为0.91,Kappa为0.77(χ2=20.39,P<0.05)。结论:基于深度学习的DR人工智能诊断系统能较好显示眼底病变的严重程度,有望为DR提供一种新的筛查工具。AIM:To evaluate a deep learning-assisted diagnostic system with an artificial intelligence for the detection ofdiabetic retinopathy(DR).METHODS:A total of 186 patients(372 eyes) with diabetes were recruited from January to July 2017.Discrepancies between manual grades and artificial intelligence results were sent to a reading center for arbitration.The sensitivity and specificity in the detection of DR were determined by comparison with artificial intelligence diagnostic system and experts human grading.RESULTS:Based on manual grades,the results as follows:non DR(NDR) in 42 eyes(11.3%),330 eyes(88.7%) in different stages of DR.Among 330 DR eyes,there were mild non proliferative DR(NPDR) in 62 eyes(16.7%),moderate NPDR in 55 eyes(14.8%),severe NPDR in 155 eyes(41.7%),and proliferative DR(PDR)in 58 eyes(15.6%).Based on artificial intelligence diagnostic system,the results were as follows:NDR in38 eyes(10.2%),PDR in 44 eyes(11.8%),others were NPDR.The sensitivity and specificity of artificial intelligence diagnostic system,compared with human expert grading,for the detection of any DR were 0.82 and 0.91,and the kappa value was 0.77(χ2 = 20.39,P<0.05).CONCLUSION:This study shows that a deep learningassisted diagnostic system with an artificial intelligence for grading diabetic retinopathy is a reliable alternative to diabetic retinopathy assessment,thus the use of this system may be a valuable tool in evaluating the DR.

关 键 词：糖尿病视网膜病变 分期 人工智能 深度学习 

分 类 号：R587.2[医药卫生—内分泌] R774.1[医药卫生—内科学]