From Retinal Pixels to Patients: Evolution of Deep Learning Research in Diabetic Retinopathy Screening

TL;DR

This survey reviews a decade of deep learning advancements in diabetic retinopathy screening, highlighting methodological innovations, challenges, and future directions for clinical deployment and broader medical imaging applications.

Contribution

It provides the first comprehensive synthesis of DR deep learning research from 2016-2025, analyzing methodological progress, evaluation standards, and translational barriers.

Findings

Deep learning models have significantly improved DR detection accuracy.

Challenges remain in multi-center validation and clinical trust.

Innovations like semi-supervised learning and federated training are promising.

Abstract

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.