Diffusion-augmented contrastive learning for diabetic retinopathy severity classification

Second, SimCLR contrastive self-supervised learning pre-trains an encoder on the combined real-and-synthetic corpus, learning discriminative retinal representations without label supervision.

In ophthalmology, demonstrated lesion-guided contrastive learning for DR grading, and Multi-Instance Contrastive Learning () constructs positive pairs from images of the same patient, capturing clinically meaningful patient-level features.

Both datasets formulate diabetic retinopathy grading as a five-class classification problem, with labels 0–4 corresponding to no apparent diabetic retinopathy (No DR), mild non-proliferative diabetic retinopathy (NPDR), moderate NPDR, severe NPDR, and proliferative diabetic retinopathy (PDR), respectively.

6 Conclusions This paper presented an integrated deep learning framework for five-class diabetic retinopathy severity classification that advances our earlier multi-model inception ensemble by incorporating class-conditional diffusion-based augmentation and SimCLR contrastive self-supervised pre-training.

doi: 10.1038/s41586-023-06555-x Summary Keywords class imbalance , contrastive learning , convolutional neural networks , denoising diffusion probabilistic models , diabetic retinopathy , domain shift , ensemble learning , external validation Citation Abidalkareem A, Ibrahim AK and Zhuang H (2026) Diffusion-augmented contrastive learning for diabetic retinopathy severity classification .