Application of artificial intelligence in screening and diagnosis of diabetic macular edema

Background and Aims: Diabetic macular edema (DME) is a leading cause of vision impairment, necessitating efficient screening and diagnosis. This review explores the application of artificial intelligence (AI) techniques in DME screening, diagnosis, and classification using retinal imaging modalities. Methods: We searched six databases (PubMed, Scopus, Web of Science, Science Direct, IEEE, and ACM) from January ۱, ۲۰۰۵, to July ۴, ۲۰۲۱, retrieving ۸۷۹ articles. After applying inclusion/exclusion criteria, ۳۸ studies were selected. Methodological quality was assessed using the QUADAS-۲ tool. Results: AI techniques, particularly deep learning, demonstrate high accuracy in DME screening and diagnosis using optical coherence tomography (OCT) and color fundus photography (CFP). These methods significantly improve sensitivity and specificity, with AI-based decision support systems enhancing diagnostic performance. Conclusion: Deep learning models offer an efficient and accurate approach to DME screening and diagnosis. Integrating AI into retinal image analysis improves diagnostic reliability, supporting early detection and management.

کلیدواژه ها:

DME ، AI ، ML ، DL ، Screening ، Diagnosis