A COMPREHENSIVE ANALYSIS OF DEEP LEARNNING MODEL FOR THE DETECTION OF DIABETIC RETINOPATHY USING EXPLAINABLE ARTIFICIAL INTELLIGENCE

Project Code :TCMAPY1807

Objective

The objective of this project is to develop a deep learning-based system for the automated detection of Diabetic Retinopathy (DR) stages, including Mild, Moderate, No_DR, Proliferate_DR, and Severe, from retinal images. The project aims to leverage advanced convolutional neural networks (CNNs) like MobileNet and DenseNet to achieve accurate classification. Additionally, the integration of Explainable Artificial Intelligence (XAI) techniques, particularly Grad-CAM, will enhance model interpretability, providing visual explanations for the decision-making process. This approach seeks to improve early diagnosis, assist clinicians in treatment planning, and increase trust in AI-based systems for medical applications.

Abstract

Diabetic Retinopathy (DR) is a leading cause of blindness worldwide, necessitating early detection for effective treatment. This study explores the application of deep learning models for the detection of diabetic retinopathy stages, ranging from Mild to Severe, including Moderate, No_DR, and Proliferate_DR. We evaluate the performance of MobileNet and DenseNet, two advanced convolutional neural networks (CNNs), in classifying retinal images into the aforementioned DR categories. These models were trained on a dataset consisting of annotated retinal images with varying levels of DR severity.

Keywords: Diabetic Retinopathy, Deep Learning, MobileNet, DenseNet, Explainable AI, Grad-CAM, Classification, Retinal Image Analysis.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.