Skip to content
Open access

GAN-Driven Retinal Augmentation: A Study of Synthetic Augmentation Strategies and Their Effect on Multilabel Retinal Disease Classification

Sep 2026 · Cureus Journal of Computer Science · Vol 3 · 0 citations · 32 references

TL;DR

Findings suggest that at 128-pixel resolution and with only hundreds of real training images per class, GAN-generated retinal images do not yet carry enough diagnostic signal to benefit a classifier and may introduce noise that misleads training.

Abstract

Diabetic retinopathy (DR) is a leading cause of preventable blindness that affects millions of people with diabetes across all income settings. Automated grading of fundus photographs holds real promise for expanding screening access in resource-limited settings. A persistent barrier, however, is class imbalance, where early and intermediate disease grades are under-represented in clinical datasets, degrading per-class sensitivity exactly where early detection matters most. This paper investigates whether synthetic image augmentation using generative adversarial networks (GANs) can address this gap, using the Brazilian Retinal Image Dataset, a patient-wise split fundus dataset with five DR severity grades. Two GAN architectures, DCGAN and FastGAN, were trained on three underrepresented classes (Mild NPDR, Moderate NPDR, and Proliferative DR) to generate 500 synthetic images each. The synthetic images were then used under five augmentation strategies with two classification backbones, DenseNet121 and ResNet50, tested on a held-out set using macro-averaged area under the curve and F1 score. FastGAN consistently achieved lower Fréchet Inception Distance values than DCGAN across all three classes (168.03, 129.17, and 125.86 versus 171.06, 138.78, and 132.81), but GAN augmentation did not improve downstream classification. DenseNet121 with no augmentation yielded the highest macro F1 (0.615), and every GAN-based strategy underperformed relative to this baseline. These findings suggest that at 128-pixel resolution and with only hundreds of real training images per class, GAN-generated retinal images do not yet carry enough diagnostic signal to benefit a classifier and may introduce noise that misleads training.

Read PDF

Similar papers

Open access Oct 2026

Interpretable Deep Learning for Retinal Disease Detection

Eye diseases are a leading cause of global vision impairment, yet detection is often hindered by limited resources and geographic barriers. While Deep Learning (DL) offers automated diagnostic solutions, its black-box nature challenges clinical trust. This research investigates whether interpretability can be integrate...

Nuzhat Tarannum Ibrahimy, M. Ibn Ibrahimy · 0 citations
#diffusion models Open access Oct 2026

Diffusion-augmented contrastive learning for diabetic retinopathy severity classification

Automated diabetic retinopathy (DR) severity classification faces persistent challenges from limited annotated datasets, severe class imbalance across the five-level International Clinical Diabetic Retinopathy (ICDR) scale, and domain shift between imaging environments. This paper presents an integrated deep learning f...

Ali Abidalkareem, Ali K. Ibrahim, Han-Qi Zhuang · 0 citations
Open access Oct 2026

Automated Diabetic Retinopathy Classification Using Swin Transformer: A Comparative Study with CNN-Based Approaches

Diabetic retinopathy (DR) is a progressive eye condition that is one of the most common causes of irreversible loss of vision among working-age adults in the global population. The urgent need to scale up automated screening is especially acute in resource-scarce areas, where ophthalmology specialist coverage remains d...

Manu Chauhan, Mohammad Aaftab, Sarika Agarwal · 0 citations
Conference Open access Sep 2026

A Two-Stage Deep Learning Cascade for Multi-Label Retinal Detection and DR Grading

Diabetic Retinopathy (DR) is a leading cause of blindness among diabetic individuals, where early detection is critical yet hindered by a global shortage of ophthalmologists, particularly in resource-constrained regions. This paper proposes a two-stage cascade pipeline for automated multi-label retinal disease detectio...

Arzav Saikia, Biswajit Tamuli, Bitopan Das et al. · 0 citations
Conference Open access Sep 2026

Ocularai: an Explainable and Confidence-Aware Deep Learning Framework for Multi-Class Retinal Disease Detection Using Fundus Imaging

Some of the major causes of permanent vision loss worldwide remain glaucoma, diabetic retinopathy and age-related macular degeneration. However, in developing countries such as India where the incidence of such diseases is the highest, access to specialized expert ophthalmological care is limited. Early detection is es...

P. Mounika, G. Amulya · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.