Short Analysis of Machine Learning and Deep Learning Techniques used for Glaucoma Detection

Glaucoma is a neurodegenerative and chronic ocular disease derived from optic neuropathy and caused by visual disturbances regarding degeneration of optic nerve fiber and cupping in the optic disc. Recently, glaucoma detection and monitoring need precise eye evaluation and additional testing. Owing to the advance of artificial intelligence, deep learning methods require to process the availability of huge-scale datasets and recent progressions in computing technology. Moreover, these deep learning methods produce higher performance in pattern recognition and image classification tasks. The clinical studies are hugely derived based on the auxiliary imaging tests, where the utilization of deep learning and machine learning techniques helps analyze the huge range of medical data attained from the imaging tests particularly for glaucoma to evaluate the macula and optic nerve. Hence, this work aims to make an analysis of deep learning and machine learning algorithms used for detecting glaucoma diseases by considering the recently developed works. This review includes the algorithmic classification, datasets used, performance measures,and also the tools used for their implementation. In addition, the chronological review was also added. Finally, the current research gaps are discussed to understand the complexity of findingsuitable solutions for glaucoma detection in practical applications.