基于彩色眼底像和深度学习的视神经炎及非动脉炎性前部缺血性视神经病变的筛查诊断系统的构建  

Screening and diagnostic system construction for optic neuritis and non-arteritic anterior ischemic optic neuropathy based on color fundus images using deep learning

作　　者：刘开群 刘少鹏 谭笑[3] 林浩添[1] 杨晖[1] Liu Kaiqun;Liu Shaopeng;Tan Xiao;Lin Haotian;Yang Hui(State Key Laboratory of Ophthalmology,Zhongshan Ophthalmic Center,Sun Yat-sen University,Guangzhou 510060,China;School of Computer Science,Guangdong Polytechnic Normal University,Guangzhou 510665,China;Affiliated Shenzhen Aier Eye Hospital of Jinan University,Shenzhen 51800,China)

机构地区：[1]中山大学中山眼科中心眼科学国家重点实验室,广州510060 [2]广东技术师范大学计算机科学学院,广州510665 [3]暨南大学附属深圳爱尔眼科医院,深圳518000

出　　处：《中华眼底病杂志》2023年第1期51-58,共8页Chinese Journal of Ocular Fundus Diseases

基　　金：国家自然科学基金(81870656)。

摘　　要：目的构建并评估基于彩色眼底像和人工智能(AI)辅助筛查视神经炎(ON)及非动脉炎性前部缺血性视神经病变(NAION)的筛查诊断系统。方法诊断性试验研究。2016年至2020年于中山大学中山眼科中心检查确诊的NAION患者178例267只眼(NAION组)、ON患者204例346只眼(ON组),以及2018年至2020年经视力、眼压及光相干断层扫描(OCT)检查为眼底正常的健康者513名1160只眼(正常对照组)共2909张彩色眼底像作为筛查诊断系统的数据集,其中NAION组、ON组、正常对照组分别为730、805、1374张。将正确标注后的彩色眼底像作为输入数据,选用EfficientNet-B0算法进行系统训练并验证,最终构建是否存在异常视盘、是否存在ON和是否存在NAION的3个筛查系统(二分法)。采用受试者工作特征(ROC)曲线、ROC下面积(AUC)、准确度、灵敏度、特异性和热力图作为诊断效能和科学性的判断指标。结果测试集中,诊断是否存在异常视盘、是否存在ON、是否存在NAION的AUC分别为0.967[95%可信区间(CI)0.947~0.980]、0.964(95%CI 0.938~0.979)、0.979(95%CI 0.958~0.989),并且系统在决策过程中的激活区域主要位于视盘。结论基于彩色眼底像的异常视盘、ON和NAION筛查诊断系统具有准确高效的诊断性能。Objective To construct and evaluate a screening and diagnostic system based on color fundus images and artificial intelligence(AI)-assisted screening for optic neuritis(ON)and non-arteritic anterior ischemic optic neuropathy(NAION).Methods A diagnostic test study.From 2016 to 2020,178 cases 267 eyes of NAION patients(NAION group)and 204 cases 346 eyes of ON patients(ON group)were examined and diagnosed in Zhongshan Ophthalmic Center of Sun Yat-sen University;513 healthy individuals of 1160 eyes(the normal control group)with normal fundus by visual acuity,intraocular pressure and optical coherence tomography examination were collected from 2018 to 2020.All 2909 color fundus images were as the data set of the screening and diagnosis system,including 730,805,and 1374 images for the NAION group,ON group,and normal control group,respectively.The correctly labeled color fundus images were used as input data,and the EfficientNet-B0 algorithm was selected for model training and validation.Finally,three systems for screening abnormal optic discs,ON,and NAION were constructed.The subject operating characteristic(ROC)curve,area under the ROC(AUC),accuracy,sensitivity,specificity,and heat map were used as indicators of diagnostic efficacy.Results In the test data set,the AUC for diagnosing the presence of an abnormal optic disc,the presence of ON,and the presence of NAION were 0.967[95%confidence interval(CI)0.947-0.980],0.964(95%CI 0.938-0.979),and 0.979(95%CI 0.958-0.989),respectively.The activation area of the systems were mainly located in the optic disc area in the decision-making process.Conclusion Abnormal optic disc,ON and NAION,and screening diagnostic systems based on color fundus images have shown accurate and efficient diagnostic performance.

关 键 词：视神经炎 非动脉炎性前部缺血性视神经病变 异常视盘 人工智能 深度学习 

分 类 号：R774.6[医药卫生—眼科]