STUDY ON PREDICTION OF GLAUCOMA USING FEATURES OF OPTIC NERVE HEAD FROM RETINAL FUNDUS IMAGES OF EYE

Abstract

Glaucoma is one of the leading causes of blindness because it progresses very slowly without any noticeable symptoms or pain in the eyes. It can only be diagnosed through proper eye tests such as perimetry or Optical Coherence Tomography (OCT) conducted at regular intervals. These tests, however, are expensive and accessible to only a limited number of ophthalmologists. In this paper, we have reviewed various research efforts focused on detecting and predicting glaucoma before it causes irreversible eye damage. We observed that most researchers employed deep learning techniques, utilizing Spectral Domain OCT (SD-OCT) and Fundus images. Our study aims to consolidate the different deep learning models and datasets used, along with their reported accuracy. We conclude that while deep learning has been widely applied, its effectiveness can be further enhanced through the use of retinal Fundus images, making glaucoma detection and prediction more cost-effective and accessible for patients.