Optical Coherence Tomography for Retinal Disease Detection with Integrating Deep Learning Concepts- Review

Abstract

Optical coherence tomography (OCT) enables retinal imaging by providing high-resolution, non- invasive cross-sectional views of ocular structures, aiding early detection of various retinal diseases such as diabetic macular edema (DME), age-related macular degeneration (AMD), glaucoma and diabetic retinopathy (DR). This paper reviews the burgeoning role of deep Learning (DL) techniques integrated with OCT for automated image analysis, segmentation, classification, progression and prognosis of various retinal diseases highlighting models like CNNs and performance metrics. Key challenges include dataset variability and clinical translation. This review also summarizes the trends in DL- based OCT image analysis in ophthalmology, discusses the current gaps, and provides potential research directions. DL in OCT analysis shows promising performance in vital tasks such as segmentation and quantification of layers, disease classification, progression and prognosis. There are some challenges identified and described using DL- based OCT image analysis in the development as follows, (1) OCT data are scarce and scattered; (2) models create performance discrepancies in real- world settings; (3) models lack transparency and lack of society acceptance and regulatory standards; and (5) OCT is still unavailable in most underprivileged areas. More work is needed to tackle the challenges and gaps, before DL is further applied in OCT image analysis for clinical use.