A Survey on Computer Aided Systems for Diabetic Retinopathy Detection and Classification using Deep Learning

Diabetic Retinopathy (DR) is a prominent contributor to visual disablement on a global scale, especially in those diagnosed with diabetes mellitus. Timely identification and cate-gorization of DR are essential for prompt management and the avoidance of permanent visual impairment.Recently, computer aided diagnostic (CAD) systems that utilize deep convolutional neural networks (CNNs) have become a promising approach for automatically recognizing and categorizing retinal fundus pictures for Diabetic Retinopathy (DR).This paper presents a thorough examination of the latest progress, difficulties, and future prospects in the creation and use of computer aided diagnostic (CAD) systems for diabetic retinopathy (DR) diagnosing with deep convolutional neural networks (CNNs).This study evaluates fundamental techniques, Retinal Fundus image datasets, performance measures, and clinical implications of current CAD systems, emphasizing their advantages and constraints.In addition, we investigate current trends like various preprocessing techniques and deep learning models, which have improved the effectiveness and practicality of CAD systems for diagnosing diabetic retinopathy (DR).