Artificial intelligence in glaucoma: posterior segment optical coherence tomography

Abstract

Purpose of reviewTo summarize the recent literature on deep learning (DL) model applications in glaucoma detection and surveillance using posterior segment optical coherence tomography (OCT) imaging. Recent findingsDL models use OCT derived parameters including retinal nerve fiber layer (RNFL) scans, macular scans, and optic nerve head (ONH) scans, as well as a combination of these parameters, to achieve high diagnostic accuracy in detecting glaucomatous optic neuropathy (GON). Although RNFL segmentation is the most widely used OCT parameter for glaucoma detection by ophthalmologists, newer DL models most commonly use a combination of parameters, which provide a more comprehensive approach. Compared to DL models for diagnosing glaucoma, DL models predicting glaucoma progression are less commonly studied but have also been developed. SummaryDL models offer time-efficient, objective, and potential options in the management of glaucoma. Although artificial intelligence models have already been commercially accepted as diagnostic tools for other ophthalmic diseases, there is no commercially approved DL tool for the diagnosis of glaucoma, most likely in part due to the lack of a universal definition of glaucoma defined by OCT derived parameters alone (see Supplemental Digital Content 1 for video abstract, http://links.lww.com/COOP/A54).

Artificial intelligence for glaucoma: state of the art and future perspectives

“…Most studies on glaucoma detection have relied on color fundus photography (CFP) due to its accessibility and low cost [2 ▪ ,3–6]. Optical Coherence Tomography (OCT)-based DL models using conventional 2D B scans, 3D volumetric scans or OCT-angiography have yielded excellent accuracy [3–5,7 ▪ ]. Visual Field (VF)-based glaucoma detection models also showed good accuracy but are associated with inherent challenges like noisy data, cost and time-consumption [2 ▪ ,3].…”

“…The ability of OCT data to be used in DL models to detect glaucoma has been well established [7 ▪ ]. It has been recently suggested that unsegmented retinal nerve fiber layer (RNFL) B-scans or three-dimensional optic disc volumetric/cube scans may be more promising for AI-mediated glaucoma (progression) detection than scans with automated segmentation [2 ▪ ,5,7 ▪ ]. Recent studies employed different methodologies to improve model accuracy and explore newer regions of interest in OCT scans.…”

“…Akter et al showed recently that cup surface area is also a promising optic disc parameter across different DL models [9]. Combinations of OCT measurements (particularly with swept-source OCT) may be able to deliver better predictive accuracy with a single scan [7 ▪ ]. Moreover, a recent study suggests that 3D-OCT models may be less impacted by myopic features [20].…”

“…Research on machine-learning (ML) and deep-learning (DL) models/algorithms (both terms are used henceforth interchangeably) for glaucoma detection has primarily focused on specific imaging techniques individually or multimodal imaging, using state-of-the-art convolutional neural network (CNN) models as the most common DL architecture [2 Coherence Tomography (OCT)-based DL models using conventional 2D B scans, 3D volumetric scans or OCT-angiography have yielded excellent accuracy [3-5,7 & ]. Visual Field (VF)-based glaucoma detection models also showed good accuracy but are associated with inherent challenges like noisy data, cost and time-consumption [2 & ,3].…”

Translational ophthalmology 2023

“…There is a lot of interest in using artificial intelligence (AI) to help diagnose diseases at an earlier stage, identify biomarkers that may not be readily apparent to the clinician, and to follow disease progression over time. Chen et al [1] discuss using AI models with optical coherence tomography to diagnose and follow eyes with glaucoma. This type of work has direct applicability to other conditions, including macular degeneration as well as corneal diseases.…”