Ocular image-based deep learning for predicting refractive error:A systematic review

作     者：Samantha Min Er Yew Yibing Chen Jocelyn Hui Lin Goh David Ziyou Chen Marcus Chun Jin Tan Ching-Yu Cheng Victor Teck Chang Koh Yih Chung Tham 

作者机构：Department of OphthalmologyYong Loo Lin School of MedicineNational University of SingaporeSingapore Centre for Innovation and Precision Eye HealthYong Loo Lin School of MedicineNational University of SingaporeSingapore School of ChemistryChemical Engineeringand BiotechnologyNanyang Technological UniversitySingapore Singapore Eye Research InstituteSingapore National Eye CentreSingapore Department of OphthalmologyNational University HospitalSingapore Ophthalmology and Visual Sciences(Eye ACP)Duke-NUS Medical SchoolSingapore 

出 版 物：《Advances in Ophthalmology Practice and Research》 (眼科实践与研究新进展（英文）)

年 卷 期：2024年第4卷第3期

页      面：164-172页

学科分类：1010[医学-医学技术（可授医学、理学学位）] 10[医学] 

主　　题：Deep Learning Artificial Intelligence Refractive Error Retinal images Optical Coherence Tomography Photorefraction Ocular images Prediction 

摘      要：ackground:Uncorrected refractive error is a major cause of vision impairment worldwide and its increasing prevalent necessitates effective screening and management ***,deep learning,a subset of Artificial Intelligence,has significantly advanced ophthalmological diagnostics by automating tasks that required extensive clinical *** recent studies have investigated the use of deep learning models for refractive power detection through various imaging techniques,a comprehensive systematic review on this topic is has yet be *** review aims to summarise and evaluate the performance of ocular image-based deep learning models in predicting refractive *** text:We search on three databases(PubMed,Scopus,Web of Science)up till June 2023,focusing on deep learning applications in detecting refractive error from ocular *** included studies that had reported refractive error outcomes,regardless of publication *** systematically extracted and evaluated the continuous outcomes(sphere,SE,cylinder)and categorical outcomes(myopia),ground truth measurements,ocular imaging modalities,deep learning models,and performance metrics,adhering to PRISMA *** studies were identified and categorised into three groups:retinal photo-based(n=5),OCT-based(n=1),and external ocular photo-based(n=3).For high myopia prediction,retinal photo-based models achieved AUC between 0.91 and 0.98,sensitivity levels between 85.10%and 97.80%,and specificity levels between 76.40%and 94.50%.For continuous prediction,retinal photo-based models reported MAE ranging from 0.31D to 2.19D,and R^(2) between 0.05 and *** OCT-based model achieved an AUC of 0.79–0.81,sensitivity of 82.30%and 87.20%and specificity of 61.70%–68.90%.For external ocular photo-based models,the AUC ranged from 0.91 to 0.99,sensitivity of 81.13%–84.00%and specificity of 74.00%–86.42%,MAE ranges from 0.07D to 0.18D and accuracy ranges from 81.60%to 96.70%.The reported papers colle