An efficient deep learning framework for diabetic retinopathy classification using generative data augmentation and knowledge distillation

Fahim, Tasnimul MohammadSabur, Sarika BinteyAlam, Jawad BinAyon, Tanzim HossainDatta, ShuvoAziz, AzwadChakrabarty, Amitabha2026-08-192026-08-192025-01-01T. M. Fahim et al., "An Efficient Deep Learning Framework for Diabetic Retinopathy Classification using Generative Data Augmentation and Knowledge Distillation," 2025 IEEE 7th International Conference on Sustainable Technologies For Industry 5.0 (STI), Dhaka, Bangladesh, 2025, pp. 1-6, doi: 10.1109/STI69347.2025.11367503.F. Reza and M. Mostakim, "Quantifying the Impact of Gaussian Noise on Aleatoric Uncertainty in Healthcare Data," 2025 IEEE 7th International Conference on Sustainable Technologies For Industry 5.0 (STI), Dhaka, Bangladesh, 2025, pp. 1-5, doi: 10.1109/STI69347.2025.11367583.97983315831012-s2.0-105034003933https://hdl.handle.net/10361/29329Diabetic retinopathy (DR) affects 93 million people globally and represents a leading cause of preventable blindness. Automated screening systems face critical challenges: severe class imbalance in medical datasets where healthy cases vastly outnumber vision-threatening stages, and computational demands limiting deployment in resource-constrained settings. This research presents a comprehensive three-stage framework integrating Progressive Growing GANs for synthetic fundus image generation, a dual-branch ensemble combining EfficientNet-V2-S with Vision Transformer-B/16, and knowledge distillation to compress the model into MobileNetV2. The generative approach created a balanced training corpus of 10,000 images across five severity classes, achieving FID score of 23.4. On APTOS 2019, the ensemble achieves 95.8% accuracy with 0.975 quadratic weighted kappa. Cross-dataset validation on DDR and Messidor-2 confirms robust generalization across diverse clinical populations. The distilled MobileNetV2 student retains 90.0% accuracy and 0.938 kappa while reducing parameters by 96.8% and computational operations by 98.8%. This framework demonstrates that generative augmentation combined with heterogeneous ensemble learning and knowledge distillation overcomes the accuracydeployability trade-off, enabling accessible DR screening in resource-limited settings.6 pagesen-USfalseClass imbalanceDiabetic retinopathyEfficientNetEnsemble learningKnowledge distillationMedical image analysisMobile deploymentProgressive growing GANVision transformerDiabetic retinopathy.Machine learning.An efficient deep learning framework for diabetic retinopathy classification using generative data augmentation and knowledge distillationConference Proceeding10.1109/STI69347.2025.11367503