[2603.23785] Retinal Disease Classification from Fundus Images using CNN Transfer Learning

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.23785 (cs) [Submitted on 24 Mar 2026] Title:Retinal Disease Classification from Fundus Images using CNN Transfer Learning Authors:Ali Akram View a PDF of the paper titled Retinal Disease Classification from Fundus Images using CNN Transfer Learning, by Ali Akram View PDF Abstract:Retinal diseases remain among the leading preventable causes of visual impairment worldwide. Automated screening based on fundus image analysis has the potential to expand access to early detection, particularly in underserved populations. This paper presents a reproducible deep learning pipeline for binary retinal disease risk classification from publicly available fundus photographs. We implement and compare a baseline convolutional neural network with a transfer learning approach using a pretrained VGG16 backbone and evaluate generalization on held-out data. To address class imbalance, we apply class weighting and report standard classification metrics including accuracy, precision, recall, F1-score, confusion matrices, and ROC-AUC. The VGG16 transfer learning model achieves 90.8% test accuracy with a weighted F1-score of 0.90, substantially outperforming the baseline CNN (83.1% accuracy). Results indicate that transfer learning improves discrimination compared to a baseline CNN, while also revealing remaining challenges in sensitivity to minority disease cases. We discuss practical limitations related to dataset characterist...