Deep Learning-Based Analysis for Diabetic Retinopathy Identification

Abstract

The eye condition known as diabetic retinopathy (DR) is characterized by damage to the blood vessels in the retina. Blindness may result if it is not identified in a timely manner. Early detection and treatment of DR can greatly lower the risk of visual loss. Experts with a great deal of training often use colored fundus photos to diagnose this terrible disease. Compared to computer-aided methods, manual diagnosis of DR retina fundus images by ophthalmologists takes longer because of the rising number of diabetic patients worldwide. Consequently, automatic DR detection is becoming essential. With an emphasis on medical research, deep neural network applications in healthcare have advanced significantly. The goal of this effort is to identify the five stages of DR: Normal, Mild, Moderate, Severe, and Proliferate_DR. Deep learning is one of the most popular methods for improving performance, particularly in the categorization and interpretation of medical images. Six deep-learning models—Custom CNN, Resnet50, Densenet121, EfficientNetB0, EfficientNetB2, and ViT—for the acceleration of diabetic retinopathy (DR) detection were evaluated using an extensive fundus image dataset that we got from Kaggle. With enhanced accuracy of 89%, precision of 89%, recall of 89%, and F1-score of 89% in a five-stage DR classification, the results show the superior performance of a DenseNet121 model.