Classification of Macular Diseases of Oct Images Using Hybrid Deep Learning Model

Abstract

Retinal diseases can occur in any part of the eye. A thin layer of tissue on the inside back wall of your eye, can be affected by retinal diseases. These are caused by damage to the blood vessels at the back of the eye, causing fluid to leak. This fluid buildup can damage the retina and cause vision changes. Hypertension and cancer are few conditions that can cause defects in the eye. Convolutional neural networks (CNNs), a cutting-edge technology that enables effective disease detection in deep learning, have seen remarkable success in the classification of numerous eye illnesses. Upon diagnosis, neural networks can capture the colours and textures of lesions specific to respective diseases, which is similar to human decision-making. Convolutional neural networks were tested with different retinal features as input for effective retinal image classification. Understanding issues in the posterior the eyes is very tricky .The diseases that occur in the macular region of the eye due to fluid retention and blood vessel damages. The differences between the diseases are very minute for medical errors to happen .We are deploying a software that classifies the what kind of disease it is or no disease when the user provides their OCT[1] scan image . This project is intended for users who wants to verify their OCT eye scan report to seek second consultation to doctors.