OCTDL: Optical Coherence Tomography Dataset for Image-Based Deep Learning Methods

TL;DR

This work presents an open-access OCT dataset (OCTDL) comprising over 2000 OCT images labeled according to disease group and retinal pathology, and applies Deep Learning classification techniques to this new open-access dataset.

Abstract

Optical coherence tomography (OCT) is a non-invasive imaging technique with extensive clinical applications in ophthalmology. OCT enables the visualization of the retinal layers, playing a vital role in the early detection and monitoring of retinal diseases. OCT uses the principle of light wave interference to create detailed images of the retinal microstructures, making it a valuable tool for diagnosing ocular conditions. This work presents an open-access OCT dataset (OCTDL) comprising over 2000 OCT images labeled according to disease group and retinal pathology. The dataset consists of OCT records of patients with Age-related Macular Degeneration (AMD), Diabetic Macular Edema (DME), Epiretinal Membrane (ERM), Retinal Artery Occlusion (RAO), Retinal Vein Occlusion (RVO), and Vitreomacular Interface Disease (VID). The images were acquired with an Optovue Avanti RTVue XR using raster scanning protocols with dynamic scan length and image resolution. Each retinal b-scan was acquired by centering on the fovea and interpreted and cataloged by an experienced retinal specialist. In this work, we applied Deep Learning classification techniques to this new open-access dataset.

Figures (8)

• Figure 1: Structure of the posterior segment of the eye as visualized with OCT B-scan and labelled accordingly from inner to outer retina. 1 - Posterior Hyaloid Membrane; 2 - preretinal space; 3 - retinal nerve fiber layer and inner limiting membrane; 4 - ganglion cell layer; 5 - inner plexiform layer; 6 - inner nuclear layer; 7 - outer plexiform layer; 8 - outer nuclear layer; 9 - Henle's nerve fiber layer; 10 - external limiting membrane; 11 - myoid zone of the photoreceptors; 12 - ellipsoid zone of the photoreceptors; 13 - outer segments of the photoreceptors; 14 - interdigitation zone of the photoreceptors; 15 - retinal pigment epithelium and Bruch’s membrane; 16 - choriocapillarises.
• Figure 2: Age-related Macular Degeneration (AMD). Initial stage (a) with an arrow indicating a solitary hard drusen deposit on Bruch's membrane below the basolateral membrane of the retinal pigment epithelium; Intermediate stage (b) with medium-sized cuticular drusen which gives a ribbon-like or saw-tooth pattern of hyperreflectivity on OCT indicated by the arrow; Intermediate stage (c) with drusenoid detachment of retinal pigment epithelium with hyporeflective subretinal space filled with fluid and the retinal pigment epithelium detached from Bruch's membrane.
• Figure 3: Age-related Macular Degeneration (AMD). Markers (a): 1 - outer retinal tubulation or cystic spaces; 2 - Subretinal fibrosis causing distortion of the macular and hyporeflectivity of the underlying choroid. Types of fluid (b): 1 - subretinal fluid; 2 - intraretinal fluid; 3 - sub-retinal pigment epithelial fluid accumulation.
• Figure 4: (a) Signs of Diabetic Macular Edema (DME): 1 - Hard exudates (HE), 2 - Intraretinal fluid (IRF), 3 - Hyperreflective foci; (b) Disorganization of retinal inner layers (DRIL).
• Figure 5: Retinal Vein Occlusion (RVO). Cystic macular edema in central retinal vein thrombosis. (a): 1 - Intraretinal fluid (IRF), 2 - hyperreflectivity of the inner retinal layers; Signs of Retinal Artery Occlusion (RAO) (a): 1 - Increased hyperreflectivity of the inner retina following ischemia, 2 - prominent middle limiting membrane (p-MLM).