Detection of Glaucoma in Retinal Images Based on Multiobjective Approach

Detection of Glaucoma in Retinal Images Based on Multiobjective Approach

Law Kumar Singh (Sharda University, Noida, India & Hindustan College of Science and Technology, Jamaalpur, India), Pooja (Sharda University, Noida, India) and Hitendra Garg (GLA University, Mathura, India)
Copyright: © 2020 |Pages: 13
DOI: 10.4018/IJAEC.2020040102

Abstract

Glaucoma is one of the major causes of blindness. Glaucoma is a condition due to increased pressure within the eyeball, causing progressive, irreversible and gradual loss of sight. It can be prevented only detection in disc ratio (CDR), ratio of blood vessel area in interior and superior side of the blood vessel in the nasal temporal side extracted from retinal fundus images. Reducing the number of features and reducing the error rate are two conflicting objectives. The proposed methodology aims to explore the use of Differential Evolution based multi objective feature selection technique to select a subset of features which minimize both our conflicting objectives. The performance of selected subset of features has been evaluated using KNN classification technique. It has been observed that said extracted subset of five features, KNN classification achieved better accuracy than any other subset of features.
Article Preview
Top

1. Introduction

Glaucoma is a major cause for blindness globally. It is estimated that in the near future, about 80 million people of the world are likely to be affected by glaucoma (Saroj, 2014).It is a neuro degenerative disease in which there is progressive damage to the optic nerves, ultimately leading to vision loss that is irreversible (Gupta & Yucel, 2007).Glaucoma is not retinopathy but is rather primarily a neuropathy problem i.e., it affects the retina by causing physical damage to ganglion cells. The main indication of glaucoma is expansion of the optic disc region, which is the observable manifestation of optic nerve head. Optic nerve head in the eyeball is the region where all the optic nerve fibers converge and exit the eyeball. There are two main classes of glaucoma, one is open angle glaucoma and the other is angle closure glaucoma. In case of open angle glaucoma, also referred to as wide angle glaucoma, there is partial blockage of the drainage canal due to which pressure increases slowly since the fluid does not drain out properly. In case of angle closure glaucoma, also referred to as acute glaucoma, there is a sudden and complete blockage of aqueous drainage, which results in rise in pressure causing vision loss (Abbasi, Chen & Salem, 2008).In a normal eye, there is equilibrium in the amount of fluids i.e., fluid that is produced in the eye and fluid that exits the eye through the drainage angle. Equilibrium in fluids maintains the Inter-ocular pressure (or the IOP) of eye as constant, whereas if the subject is suffering from glaucoma, IOP will bury and will keep on increasing, resulting in damage to the optic nerve. For normal eye, this inter ocular pressure is somewhere to be between 14 to 20 mmHg. When it reaches somewhere between the mark of 20 to 24mmHg, one can observe symptoms of glaucoma in the subject. However, the pressure may lead to increase in the cup size i.e., the region in the optic disk where the optic nerves meet and go inside. Cup size increases due to increase in pressure inside the eye; this increases the Cup-Disc ratio (CDR) i.e., ratio between the Optic Cup and Optic Disc. For normal eyes, Cup-Disc Ratio is considered to be nearby 0.3 where as in galucomatic eyes, it would be about 0.3 or greater. Increase in the size of the cup also affects the Neuroretinal Rim (NRR). NRR is the total region located between the edge of optic disc and the optic cup. From previous studies, we see that glaucoma detection can be performed via domain-based features such as the cup to disc ratio and ISNT ratio, and/or other features such as texture and intensity-based features (Abramoff, Garvin, & Sonka, 2010).

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 12: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 11: 4 Issues (2020): 3 Released, 1 Forthcoming
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing