Machine learning in optical coherence tomography angiography. Issue 20 (October 2021)

• Record Type: Journal Article
• Authors: Le, David; Son, Taeyoon; Yao, Xincheng
• Is Part Of: Experimental biology and medicine. Volume 246:Issue 20(2021)
• Page Start: 2170
• Page End: 2183
• Publication Date: 2021-10
• Subjects: Retina -- retinopathy -- optical coherence tomography angiography -- artificial intelligence -- machine learning -- deep learning -- convolutional neural network; Physiology -- Periodicals; Biology, Experimental -- Periodicals; Medicine, Experimental -- Periodicals; 610.72
• DOI: 10.1177/15353702211026581
• Languages: English
• ISSNs: 1535-3702

Abstract

Optical coherence tomography angiography (OCTA) offers a noninvasive label-free solution for imaging retinal vasculatures at the capillary level resolution. In principle, improved resolution implies a better chance to reveal subtle microvascular distortions associated with eye diseases that are asymptomatic in early stages. However, massive screening requires experienced clinicians to manually examine retinal images, which may result in human error and hinder objective screening. Recently, quantitative OCTA features have been developed to standardize and document retinal vascular changes. The feasibility of using quantitative OCTA features for machine learning classification of different retinopathies has been demonstrated. Deep learning-based applications have also been explored for automatic OCTA image analysis and disease classification. In this article, we summarize recent developments of quantitative OCTA features, machine learning image analysis, and classification.