OCTDL — The Second Largest Open Access Dataset for OCT

With more than 2,000 images OCTDL is the world’s second largest OCT Image Dataset. Image created by the author.

Vision is one of humanity’s most precious senses, yet millions face sight-threatening diseases like Age-Related Macular Degeneration (AMD) and Diabetic Macular Edema (DME). Early detection is critical, but accurate diagnoses require sophisticated imaging technologies and expert interpretation — resources often inaccessible in underserved regions. Optical Coherence Tomography (OCT) is a marvel of modern imaging capable of producing detailed cross-sectional images of the retina. OCT is indispensable in ophthalmology, but its potential remains underutilized due to a lack of open, high-quality datasets for training artificial intelligence (AI) models.

The newly released Optical Coherence Tomography Dataset for Image-Based Deep Learning (OCTDL) addresses this gap. This open-access dataset, curated by an international team of researchers, contains over 2,000 OCT images meticulously labeled with various retinal diseases and pathologies. At a time when AI is poised to transform healthcare, OCTDL emerges as a timely and invaluable resource for researchers, clinicians, and engineers alike.

OCT allows to image the different layers of the 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. Source: Scientific Data, License: CC BY 4.0

How Does OCT Work?