机构：[1]Department of Ophthalmology, University of California, San Francisco, San Francisco, California.[2]State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China.[3]Department of Ophthalmology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China.[4]Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.[5]Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore.[6]Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing Ophthalmology and Visual Sciences Key Laboratory, Beijing, China.首都医科大学附属北京同仁医院首都医科大学附属同仁医院[7]Centre for Eye Research Australia, University of Melbourne, Royal Victorian Eye and Ear Hospital, East Melbourne, VIC, Australia.[8]Ophthalmology Section, Surgical Service, San Francisco Veterans Affairs Medical Center, San Francisco, California.
Purpose: To assess the performance and generalizability of a convolutional neural network (CNN) model for objective and high -throughput identification of primary angle -closure disease (PACD) as well as PACD stage differentiation on anterior segment swept -source OCT (AS-OCT). Design: Cross-sectional. Participants: Patients from 3 different eye centers across China and Singapore were recruited for this study. Eight hundred forty-one eyes from the 2 Chinese centers were divided into 170 control eyes, 488 PACS, and 183 PAC + PACG eyes. An additional 300 eyes were recruited from Singapore National Eye Center as a testing data set, divided into 100 control eyes, 100 PACS, and 100 PAC + PACG eyes. Methods: Each participant underwent standardized ophthalmic examination and was classified by the presiding physician as either control, primary angle -closure suspect (PACS), primary angle closure (PAC), or primary angle -closure glaucoma (PACG). Deep Learning model was used to train 3 different CNN classifiers: classifier 1 aimed to separate control versus PACS versus PAC + PACG; classifier 2 aimed to separate control versus PACD; and classifier 3 aimed to separate PACS versus PAC + PACG. All classifiers were evaluated on independent validation sets from the same region, China and further tested using data from a different country, Singapore. Main Outcome Measures: Area under receiver operator characteristic curve (AUC), precision, and recall. Results: Classifier 1 achieved an AUC of 0.96 on validation set from the same region, but dropped to an AUC of 0.84 on test set from a different country. Classifier 2 achieved the most generalizable performance with an AUC of 0.96 on validation set and AUC of 0.95 on test set. Classifier 3 showed the poorest performance, with an AUC of 0.83 and 0.64 on test and validation data sets, respectively. Conclusions: Convolutional neural network classifiers can effectively distinguish PACD from controls on AS-OCT with good generalizability across different patient cohorts. However, their performance is moderate when trying to distinguish PACS versus PAC + PACG. Financial Disclosures: The authors have no proprietary or commercial interest in any materials discussed in this article. (c) 2023 Published by Elsevier Inc. on behalf of the American Academy of Ophthalmology
基金：
Supported by a National Eye Institute grant (NEI EY028747-01 [Y.H.]) and
an unrestricted grant from Research to Prevent Blindness, New York, NY;
the computational Innovator Faculty Research Award (to J.S.); the UCSF
Initiative for Digital Transformation in Computational Biology & Health;
grants from the All May See Foundation and Think Forward Foundation (to
J.S.); and the UCSF Irene Perstein Award (to J.S.).
第一作者机构：[1]Department of Ophthalmology, University of California, San Francisco, San Francisco, California.
通讯作者：
通讯机构：[1]Department of Ophthalmology, University of California, San Francisco, San Francisco, California.[8]Ophthalmology Section, Surgical Service, San Francisco Veterans Affairs Medical Center, San Francisco, California.[*1]490 Illinois street, San Francisco, CA, 94143
推荐引用方式(GB/T 7714)：
Shan Jing,Li Zhixi,Ma Ping,et al.Deep Learning Classification of Angle Closure based on Anterior Segment OCT[J].OPHTHALMOLOGY GLAUCOMA.2024,7(1):8-15.doi:10.1016/j.ogla.2023.06.011.
APA：
Shan, Jing,Li, Zhixi,Ma, Ping,Tun, Tin A.,Yonamine, Sean...&Han, Ying.(2024).Deep Learning Classification of Angle Closure based on Anterior Segment OCT.OPHTHALMOLOGY GLAUCOMA,7,(1)
MLA：
Shan, Jing,et al."Deep Learning Classification of Angle Closure based on Anterior Segment OCT".OPHTHALMOLOGY GLAUCOMA 7..1(2024):8-15
