Automated Glaucoma Screening using CDR from 2D Fundus Images

Abstract

Glaucoma is a chronic eye disease that leads to blindness. This disease cannot be cured but we can detect the disease in time. Current tests using intraocular pressure (IOP)measurement are not sensitive enough for population based glaucoma screening. Optic nerve head assessment in retinal fundus images is more promising and superior than current methods. This paper proposes segmentation of optic disc and optic cup using superpixel classification for glaucoma screening. In optic disc segmentation, clustering algorithms are used to classify each superpixel as disc or non-disc. For optic cup segmentation, in addition to the clustering algorithms, the Gabor filter and thresholding is used. . The segmented optic disc and optic cup are then used to compute the cup to disc ratio for glaucoma screening. The Cup to Disc Ratio (CDR) of retinal fundus camera image is the primary identifier to confirm glaucoma for a given patient.