Retinal Disease Detection System

Abstract

Millions of people are affected by retinal abnormalities worldwide. Early detection and treatment of these abnormalities could arrest further progression, saving multitudes from avoidable blindness. Manual disease detection is time-consuming, tedious, and lacks repeatability. In this project, we work on deep learning models to detect eye disease using Retinal fundus photographs and OCT scans using cutting-edge computer vision techniques with deep neural networks. This project addresses the need for a user-friendly, Deep Learning based application that analyzes Optical Coherence Tomography (OCT) scans and Retinal fundus photographs for early detection of retinal diseases. Leveraging deep learning models, the application offers personalized health recommendations, tracks users' eye health history, and provides educational content to promote awareness and preventive care. To enhance user interaction and accessibility, we integrate a large language model, enabling users to prompt questions regarding their eye health and receive informative responses. This AI-driven assistant supports users by explaining diagnoses, suggesting preventive measures, and guiding them toward appropriate medical consultations. This solution aims for early detection and to bridge the gap between advanced eye care and accessibility, enabling proactive management of retinal health without needing immediate in-person visits to healthcare professionals