Unconditional GAN-Based Generation of Stage-Specific Fundus Images for Augmenting Diabetic Retinopathy Screening
Open Access
- 18 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 47800-47815
Abstract
Class imbalance in diabetic retinopathy (DR) datasets, particularly the underrepresentation of advanced stages such as proliferative DR, limits classifier performance and necessitates specialized augmentation strategies. This study presents a data augmentation approach using StyleGAN2-ADAto generate stage-specific synthetic fundus images. Unlike conditional approaches requiring labels or segmentation masks, our method trains separate unconditional models for each DR severity stage, producing anatomically realistic images while preserving pathological characteristics. We propose a comprehensive evaluation framework comprising three components: quantitative assessment using distribution-based metrics (FID, KID, IS) and nearest-neighbor-based metrics (NN-SSIM, NN-PSNR); task-based evaluation through DR classification experiments with ConvNeXt Tiny, MobileNet V3 Small, and Xception architectures; and expert validation by three ophthalmologists assessing clinical plausibility. Classification experiments demonstrated improvements in overall accuracy, with ConvNeXt Tiny achieving 73.48% accuracy (+1.82% over baseline) when combining synthetic and classical augmentation. Inter-rater reliability analysis (κ = 0.723 between two evaluators) confirmed the clinical realism of generated images. Our unconditional StyleGAN2-ADA approach provides a scalable, mask-free augmentation solution addressing class imbalance in fundus imaging datasets, potentially enhancing DR screening systems in resource-constrained clinical settings.Keywords
Funding Information
- Ph.D. Students and Young Researchers Call of Slovak University of Technology in Bratislava to start a Research Career (23-03-09-A)
- Recovery and Resilience Plan of Slovak Republic (RRP SR) through a call (09I03-03-V05)
- Agentúra na Podporu Výskumu a Vývoja (APVV-22-606-AI4EYE)
- Internal Faculty of Electrical Engineering and Information Technology (FEI) Slovak University of Technology (STU) [TRUST-DIAG-Artificial Intelligence (AI)] (2026-01-24)
This publication has 48 references indexed in Scilit:
- Efficient multi-scale learning via scale embedding for diabetic retinopathy multi-lesion segmentationBiomedical Signal Processing and Control, 2024
- Modified deep inductive transfer learning diagnostic systems for diabetic retinopathy severity levels classificationBiomedical Signal Processing and Control, 2024
- A feasibility study on the adoption of a generative denoising diffusion model for the synthesis of fundus photographs using a small datasetDiscover Applied Sciences, 2024
- Fine-Grained Multi-modal Fundus Image Generation Based on Diffusion Models for Glaucoma Classification2024
- MedGAN: An adaptive GAN approach for medical image generationComputers in Biology and Medicine, 2023
- DeepDrRVO: A GAN-auxiliary two-step masked transformer framework benefits early recognition and differential diagnosis of retinal vascular occlusion from color fundus photographsComputers in Biology and Medicine, 2023
- A survey on deep learning applied to medical images: from simple artificial neural networks to generative modelsNeural Computing and Applications, 2022
- Diabetic retinopathy screening using deep learning for multi-class imbalanced datasetsComputers in Biology and Medicine, 2022
- GANs for medical image analysisArtificial Intelligence in Medicine, 2020
- Large-Scale Machine Learning with Stochastic Gradient Descent2010