Retinal Disease Classification from Fundus Images using CNN Transfer Learning

TL;DR

This study develops a deep learning pipeline using transfer learning with VGG16 for retinal disease classification from fundus images, achieving high accuracy and highlighting challenges in sensitivity and dataset limitations.

Contribution

Introduces a reproducible transfer learning approach with VGG16 for retinal disease detection, outperforming baseline CNN models and providing practical insights for clinical screening.

Findings

VGG16 transfer learning achieves 90.8% accuracy.

Transfer learning outperforms baseline CNN.

Remaining challenges in sensitivity to minority cases.

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 characteristics, class imbalance, and threshold selection, and provide guidance for reproducibility and future improvements for clinically reliable screening