An Automated Framework for Screening of Glaucoma using Cup-to-Disc Ratio and ISNT Rule with a Support Vector Machine

Abstract

Glaucoma is a common eye disease that damages an optic nerve due to abnormally high pressure inside the eye. Glaucoma can cause visual impairments and eventually lead to blindness. There is no appropriate treatment to prevent blindness when the optic nerve is damaged. Therefore, an early diagnosis is important to prevent vision loss from glaucoma. An automated framework for glaucoma screening from fundus images is advantageous. It can facilitate the ophthalmologist in the diagnosis and prevent blindness. Many glaucoma screening algorithms have been developed based on a clinical indicator, the cup-to-disc ratio (CDR). However, these algorithms have some limitations for myopia and genetically large optic cup eyes. Therefore, this paper proposes a framework for glaucoma screening that can be applied even in myopia. The 2 clinical indicators, cup-to-disc ratio (CDR) and neuroretinal rim area rule (inferior > superior > nasal > temporal (ISNT)), are applied in the proposed screening algorithm for accurate glaucoma assessment. Moreover, the automatic classification of glaucoma or non-glaucoma from fundus images is performed by a support vector machine (SVM). Therefore, the experimental results show that the proposed screening algorithm can accurately classify glaucoma to normal eyes or myopic eyes.
 HIGHLIGHTS
 
 A framework for glaucoma screening is proposed to classify myopia and genetically large optic cup eyes
 Two clinical indicators, cup-to-disc ratio (CDR) and neuroretinal rim area rule (inferior > superior > nasal > temporal (ISNT)), are applied in the proposed screening algorithm for accurate glaucoma assessment
 Automatic classification of glaucoma or non-glaucoma from fundus images is performed by a support vector machine (SVM)
 The proposed framework can provide less time consuming, cost-effective and physician independent system for glaucoma screening
 
 GRAPHICAL ABSTRACT