Department of Ophthalmology, University Hospitals Cleveland Medical Center, School of Medicine, Case Western Reserve University, Cleveland, Ohio; and.
Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts.
Retina. 2022 Aug 1;42(8):1417-1424. doi: 10.1097/IAE.0000000000003535.
To survey the current literature regarding applications of deep learning to optical coherence tomography in age-related macular degeneration (AMD).
A Preferred Reporting Items for Systematic Reviews and Meta-Analyses systematic review was conducted from January 1, 2000, to May 9, 2021, using PubMed and EMBASE databases. Original research investigations that applied deep learning to optical coherence tomography in patients with AMD or features of AMD (choroidal neovascularization, geographic atrophy, and drusen) were included. Summary statements, data set characteristics, and performance metrics were extracted from included articles for analysis.
We identified 95 articles for this review. The majority of articles fell into one of six categories: 1) classification of AMD or AMD biomarkers (n = 40); 2) segmentation of AMD biomarkers (n = 20); 3) segmentation of retinal layers or the choroid in patients with AMD (n = 7); 4) assessing treatment response and disease progression (n = 13); 5) predicting visual function (n = 6); and 6) determining the need for referral to a retina specialist (n = 3).
Deep learning models generally achieved high performance, at times comparable with that of specialists. However, external validation and experimental parameters enabling reproducibility were often limited. Prospective studies that demonstrate generalizability and clinical utility of these models are needed.
调查目前关于深度学习在年龄相关性黄斑变性（AMD）中的光学相干断层扫描中的应用的文献。
我们从 2000 年 1 月 1 日至 2021 年 5 月 9 日，使用 PubMed 和 EMBASE 数据库进行了系统评价的首选报告项目。纳入了将深度学习应用于 AMD 患者或 AMD 特征（脉络膜新生血管、地理萎缩和玻璃膜疣）的光学相干断层扫描的原始研究调查。从纳入的文章中提取总结陈述、数据集特征和性能指标进行分析。
我们共为本次综述确定了 95 篇文章。大多数文章分为以下六个类别之一：1）AMD 或 AMD 生物标志物的分类（n=40）；2）AMD 生物标志物的分割（n=20）；3）AMD 患者的视网膜层或脉络膜的分割（n=7）；4）评估治疗反应和疾病进展（n=13）；5）预测视觉功能（n=6）；以及 6）确定是否需要转诊给视网膜专家（n=3）。
深度学习模型通常表现出较高的性能，有时可与专家相媲美。然而，外部验证和可重现性的实验参数往往受到限制。需要进行前瞻性研究，以证明这些模型的通用性和临床实用性。
