Research

Paper

TESTING March 24, 2026

Retinal Disease Classification from Fundus Images using CNN Transfer Learning

Authors

Ali Akram

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

Metadata

arXiv ID: 2603.23785
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-24
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23785v1</id>\n    <title>Retinal Disease Classification from Fundus Images using CNN Transfer Learning</title>\n    <updated>2026-03-24T23:40:48Z</updated>\n    <link href='https://arxiv.org/abs/2603.23785v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23785v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-24T23:40:48Z</published>\n    <arxiv:comment>4 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Ali Akram</name>\n    </author>\n  </entry>"
}