Automated Detection of Glaucoma Using Color Fundus Images

Abstract

Glaucoma is a chronic and irreversible neurodegenerative disease in which the neuro-retinal nerve that connects the eye to the brain (optic nerve) is progressively damaged and patients suffer from vision loss and blindness. According to World Health Organization, glaucoma is the second leading cause of blindness; it is responsible for approximately 5.2 million cases of blindness. The timely detection and treatment of glaucoma is very crucial to save patient's vision. Computer aided diagnostic systems are used for automated detection of glaucoma which calculate cup to disc ratio from colored retinal images. In this research, we present a novel method for early and accurate detection of glaucoma. The proposed system consists of preprocessing, optic disc segmentation, extraction of features from optic disc region of interest and classification for detection of glaucoma. The main novelty of our research lies in formation of feature vector which consists of spatial and spectral features along with cup to disc ratio and rim to disc ratio. The validation of proposed system is performed using four publicly available fundus image databases along with one locally gathered database. The statistical analysis of system is done by calculating sensitivity, specificity, positive predictive value and accuracy for each database. The system has achieved an average accuracy 91.1. A comparative analysis is also performed for HRF database which shows the improvement of proposed system as compared to existing methods.