Automated Diagnosis of Eye Problems Using Deep Learning Techniques on Retinal Fundus Images

Abstract

Automated diagnosis of eye diseases using deep learning techniques on retinal fundus images has become an active area of research in recent years. The suggested method divides retinal images into various disease categories by extracting relevant data using convolutional neural network (CNN) architecture. The dataset used in this study consists of retinal images taken from patients with various eye conditions, such as age-related macular degeneration, glaucoma, and diabetic retinopathy. The aim of this study is to investigate the potential of deep learning algorithms in detecting and classifying various retinal diseases from fundus images. The suggested approach may make early eye disease diagnosis and treatment easier, reducing the risk of vision loss and enhancing patient quality of life. The DenseNet-201 model is tested and achieved an accuracy rate of 80.06%, and the findings are extremely encouraging.