Deep Learning Enabled Diabetic Retinopathy Diagnosis Using Retinal Fundus Images
A MATLAB-based system is developed for automated classification of eye diseases, specifically targeting Diabetic Retinopathy (DR). The process begins with an input image undergoing preprocessing steps, including resizing, noise removal, contrast enhancement, and segmentation using Mayfly Optimization-based Region Growing (MFORG) to isolate relevant regions. The system initially classifies the image as either healthy or indicative of DR. For detected DR cases, a further stage-wise classification is performed to identify the severity level: Mild DR, Moderate DR, Severe DR, or Proliferative DR (PDR).
View project
