Diabetic retinopathy(DR)is the most common microvascular complication of diabetes and a leading cause of vision loss among the working-age population. Conventional screening models rely on manual interpretation of fundus images by ophthalmologists, facing limitations including uneven distribution of medical resources and subjectivity in diagnosis. In recent years, deep learning(DL)technology, with its strengths in image recognition and feature learning, has emerged as a novel and efficient automated approach for early DR screening. This article provides a systematic review of DL applications in DR screening, covering technical principles, mainstream algorithms, dataset construction, model training strategies, and the potential for integrating multi-modal data. It further provides an in-depth analysis of key challenges in current applications, such as data quality, model interpretability, system integration, and obstacles to clinical translation. What's more, future directions are discussed, including the development of light weight models, multi-disease joint prediction, and the establishment of interdisciplinary collaborative frameworks, aiming to support the clinical adoption of DL-based DR screening.

四川省卫健委科研项目(No.24WXXT13); 中国研究型医院学会眼科基金(No.Y2025FH-YKYSJSJ07-18); 川北医学院科研发展计划项目(No.CBY24-QDA01)