Deep Learning-Based Classification of Retinal Pathologies

  • Kawtar NAIM FST, Cadi Ayyad University
  • Aziz DAROUICHI Computer and Systems Engineering Laboratory (L2IS), FST, Cadi Ayyad University, Marrakech, Morocco
DOI: https://doi.org/10.19139/soic-2310-5070-2767
Keywords: Ophthalmic Disease, Retinal, OCT, Classification, Deep Learning (DL), Artificial Intelligence (AI), CapsNet, ResNet50

Abstract

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) are prevalent eye conditions that can lead to partial or complete vision impairment and blindness. Addressing these challenges in eye care necessitates advanced imaging technologies like Optical Coherence Tomography (OCT). The evolution of OCT from time-domain to frequency-domain techniques has significantly enhanced its utility in routine clinical procedures. This paper introduces a novel R50-CapsNet architecture designed to classify retinal diseases more accurately and reliably. Our approach aims to improve diagnostic accuracy for the OCTDL and Kermany datasets.
Published
2025-10-15
How to Cite
NAIM, K., & DAROUICHI, A. (2025). Deep Learning-Based Classification of Retinal Pathologies. Statistics, Optimization & Information Computing. https://doi.org/10.19139/soic-2310-5070-2767
Issue
Online First
Section
ICCSAI'24
Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).