From Retinal Pixels to Patients: Evolution of Deep Learning Research in Diabetic Retinopathy Screening
It addresses the problem of improving diabetic retinopathy screening for global health by consolidating research to guide reproducible and clinically deployable AI, though it is incremental as a survey rather than presenting new experimental results.
This survey synthesizes deep learning research in diabetic retinopathy screening from 2016 to 2025, analyzing over 50 studies and 20 datasets to track progress from early convolutional neural networks to advanced methods addressing issues like class imbalance and domain shift, while highlighting gaps in multi-center validation and clinical trust.
Diabetic Retinopathy (DR) remains a leading cause of preventable blindness, with early detection critical for reducing vision loss worldwide. Over the past decade, deep learning has transformed DR screening, progressing from early convolutional neural networks trained on private datasets to advanced pipelines addressing class imbalance, label scarcity, domain shift, and interpretability. This survey provides the first systematic synthesis of DR research spanning 2016-2025, consolidating results from 50+ studies and over 20 datasets. We critically examine methodological advances, including self- and semi-supervised learning, domain generalization, federated training, and hybrid neuro-symbolic models, alongside evaluation protocols, reporting standards, and reproducibility challenges. Benchmark tables contextualize performance across datasets, while discussion highlights open gaps in multi-center validation and clinical trust. By linking technical progress with translational barriers, this work outlines a practical agenda for reproducible, privacy-preserving, and clinically deployable DR AI. Beyond DR, many of the surveyed innovations extend broadly to medical imaging at scale.