DIABETIC RETINOPATHY DETECTION USING DEEP LEARNING

Diabetic Retinopathy (DR) is one of the leading causes of blindness globally, making it essential to detect it early for effective treatment and to prevent vision loss. Traditional diagnostic methods often depend on manual evaluations by ophthalmologists, which can be both time-consuming and susceptible to human error. However, recent advancements in deep learning and computer vision have paved the way for automated diagnosis through convolutional neural networks (CNNs). This paper introduces a deep learning- based method for classifying DR using YOLOv8(You Only Look once version 8), a cutting-edge object detection model. The system we propose utilizes a Flask-based web application that enables users to upload retinal images for real- time classification into two categories: No DR and DR. The model is trained on annotated retinal fundus images and fine- tuned to improve accuracy in medical imaging. We preprocess the images by applying resizing and normalization techniques to ensure the best input quality. Keywords Diabetic Retinopathy, YOLOv8, Deep Learning, Medical Image Analysis, Retina Screening.