Macular Degeneration Analysis Using Deep Learning Models

Author : Shubhra Pathak

Abstract :One of the main causes of vision loss in the elderly is age-related macular degeneration (AMD), a degenerative retinal disease. This study proposes a deep learning-based technique for automated AMD classification from retinal fundus pictures using EfficientNet-B5. The model maintains computation speed while achieving accuracy through fine-tuning and transfer learning. In addition to being compared to conventional diagnostic techniques, ablation research was conducted to see how adjusting various layers impacts outcomes. Tests show better classification results; this method can become a scalable and trustworthy solution for early AMD identification, helping ophthalmologists with on time diagnosis and treatment planning.

Keywords :Grad-CAM, OCT, SVM, EfficientNet B5, deep learning, macular degeneration, medical imaging.

Conference Name :National Conference on Researches in Science and Technology (NCRST-25)

Conference Place Visakhapatnam, India

Conference Date 19th Apr 2025