A Survey on Deep Learning Models in Glaucoma Detection using Fundus Images(Feasibility Study of Semi-Supervised Learning)

Abstract

In the human world today is affected by numerous diseases that lead to damage to body parts or degrade their pace of operation.As main factors, eye disorders include loss of vision due to glaucoma and diabetic retinopathy.As a result of technological advances in deep learning, fundus early detection of glaucoma with an automated approach offers significant advantages.This article addresses deep learning models that are useful for glaucoma detection and to identify opportunities for using Semi-Supervised deep learning models over supervised deep learning methods.Using both labelled and unlabeled data on fundus images, the Semi-supervised GAN model consists of a SegNet, real data generator, and classifier to improve segmentation performance.