What question did this study set out to answer?

The research aims to enhance early detection and classification of diabetic retinopathy using machine learning techniques.

July 16, 2026

Deep Learning -Based Diabetic Retinopathy Detection and Severity Classification using CNN ResNET

YSYashashwini S.

Key Points

The research aims to enhance early detection and classification of diabetic retinopathy using machine learning techniques.
Utilized a Convolutional Neural Network (CNN) architecture for image analysis.
Classified retinal images into five stages of diabetic retinopathy: No DR, Mild DR, Moderate DR, Severe DR, and Proliferative DR.
Achieved effective classification of retinal images into five distinct stages of diabetic retinopathy.

Abstract

Diabetic Retinopathy (DR) is an ocular complication associated with diabetes and remains one of the primary contributors to vision impairment among the working-age population. The condition arises when prolonged high blood glucose levels damage the retinal blood vessels, causing them to dilate, leak fluids, or obstruct normal circulation. As the disease advances, it can lead to severe visual decline or even complete blindness. The central aim of this research is to enable early detection of DR by applying machine learning approaches and to classify retinal images into five distinct stages: No DR, Mild DR, Moderate DR, Severe DR, and Proliferative DR. Effective categorization of such medical images is facilitated through the use of a Convolutional Neural Network (CNN) architecture.

Ask AI

Helpful

Bookmark

View Full Paper