Deep Learning for Ocular Disease Classification: A Study on ODIR-5K Dataset
This research investigates the utilization of deep learning methodologies for classifying ocular dis-eases using the ODIR-5K dataset. A tailored convolutional neural network (CNN) architecture is developed to categorize fundus images into five distinct classes: diabetes, glaucoma, cataract, age-related macular de-generation, and normal. Notably, experimental outcomes achieve a 96.32 % accuracy rate, underscoring the effi-cacy of deep learning in ocular disease diagnosis.
Authors
- Suresh Rasappan (ORCID: https://orcid.org/0000-0002-6779-9000)
- Sathish Kumar Kumaravel (ORCID: https://orcid.org/0000-0002-7538-2766)
- Regan Murugesan (ORCID: https://orcid.org/0000-0002-3449-4702)
- Kala Raja Mohan (ORCID: https://orcid.org/0000-0003-2514-9111)
- Nagadevi Bala Nagaram (ORCID: https://orcid.org/0000-0002-3309-1506)
- S. Ahamed Nishath
Institutions
- Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology (IN)
- College of Applied Sciences- Ibri (OM)
Publication Details
- Published
- 2025-02-03
- DOI
- https://doi.org/10.1109/ai2e64943.2025.10983793
- Citations
- 4
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 5.44