Diabetic Retinopathy Detection by Means of Deep Learning

Author : Upendar Para

Abstract : Diabetic Retinopathy (DR) is a severe eye disease caused by diabetes, often leading to blindness if not detected early. Traditional screening depends on manual examination of retinal fundus images by ophthalmologists, which is time-consuming and prone to errors. To address this, the project proposes an automated DR detection system using Deep Learning. The system employs Convolutional Neural Networks (CNNs) to analyze retinal images and detect key features such as microaneurysms, hemorrhages, and exudates, which indicate DR severity. The workflow includes image preprocessing (enhancement and normalization), feature extraction via CNNs, and a classification module that categorizes DR into stages: No DR, Mild, Moderate, Severe, and Proliferative. A final report generation module provides quick results for doctors and patients. The project will be implemented using Python, TensorFlow/Keras, and OpenCV for preprocessing and training on large datasets. This AI-driven solution enables early detection, automation, scalability, and affordability, improving patient care and preventing blindness.

Keywords : CNN, Deep Learning , Diabetic Retinopathy, Medical Image Processing, Retinal Images.

Conference Name : "National Conference on Computing and Electronics Engineering (NCCEE - 25)"

Conference Place : Coimbatore, India

Conference Date : 13th Dec 2025