CLASSIFICATION OF DIABETIC RETINOPATHY DISEASE LEVELS BY EXTRACTING TOPOLOGICAL FEATURES USING GRAPH NEURAL NETWORKS

Abstract

Diabetic Retinopathy (DR) affects over 93 million people globally, with approximately one-third of them experiencing vision-threatening stages of the disease. Early and accurate classification of DR severity is critical to preventing irreversible blindness, yet manual diagnosis remains subjective and time-consuming. Existing diagnosis methods rely heavily on manual interpretation of retinal fundus  images by ophthalmologists, which introduces variability and is resource-intensive.