Glaucoma detection in retinal fundus images using deep learning architectures

Abstract

Diabetic retinopathy (DR) is a common complication of diabetes that can cause retinopathy to affect vision. If not caught early, it can lead to blindness. Unfortunately, DR is not a reversible process and treatment can only maintain vision. Early detection and treatment of DR can significantly reduce the risk of vision loss. Unlike computer-aided diagnostic systems, the manual diagnostic process of DR retinal fundus images by ophthalmologists is time consuming, cumbersome, and expensive, and it is easy to misdiagnose. Recently, deep learning has become one of the most widely used techniques and has achieved better performance in many areas, especially in medical image analysis and classification. In this work Googlenet and Alexnet networks will be used for classification and detection of Diabetic retinopathy are more widely used as a deep learning method in medical image analysis and they are highly effective. The performance will be done in terms of training Accuracy, Learning Rate, training loss, validation loss, validation accuracy, precision, recall, sensitivity the execution will be done on MATLAB software.