Automated classification of glaucoma stages using higher order cumulant features

Kevin P. Noronha, U. Rajendra Acharya, K. Prabhakar Nayak, Roshan Joy Martis, Sulatha V. Bhandary

Research output: Contribution to journalArticle

61 Citations (Scopus)

Abstract

Glaucoma is a group of disease often causing visual impairment without any prior symptoms. It is usually caused due to high intra ocular pressure (IOP) which can result in blindness by damaging the optic nerve. Hence, diagnosing the glaucoma in the early stage can prevent the vision loss. This paper proposes a novel automated glaucoma diagnosis system using higher order spectra (HOS) cumulants extracted from Radon transform (RT) applied on digital fundus images. In this work, the images are classified into three classes: normal, mild glaucoma and moderate/severe glaucoma. The 3rd order HOS cumulant features are subjected to linear discriminant analysis (LDA) to reduce the number of features and then these clinically significant linear discriminant (LD) features are fed to the support vector machine (SVM) and Naïve Bayesian (NB) classifiers for automated diagnosis. This work is validated using 272 fundus images with 100 normal, 72 mild glaucoma and 100 moderate/severe glaucoma images using ten-fold cross validation method. The proposed system can detect the early glaucoma stage with an average accuracy of 84.72%, and the three classes with an average accuracy of 92.65%, sensitivity of 100% and specificity of 92% using NB classifier. This automated system can be used during the mass screening of glaucoma.

Original languageEnglish
Pages (from-to)174-183
Number of pages10
JournalBiomedical Signal Processing and Control
Volume10
Issue number1
DOIs
Publication statusPublished - 2014

Fingerprint

Glaucoma
Classifiers
Radon
Discriminant analysis
Support vector machines
Optics
Screening
Mass Screening
Vision Disorders
Discriminant Analysis
Blindness
Optic Nerve
Pressure
Sensitivity and Specificity

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Health Informatics

Cite this

Noronha, Kevin P. ; Acharya, U. Rajendra ; Nayak, K. Prabhakar ; Martis, Roshan Joy ; Bhandary, Sulatha V. / Automated classification of glaucoma stages using higher order cumulant features. In: Biomedical Signal Processing and Control. 2014 ; Vol. 10, No. 1. pp. 174-183.
@article{bf82e8a9e8634d4baa78d6c295b3113e,
title = "Automated classification of glaucoma stages using higher order cumulant features",
abstract = "Glaucoma is a group of disease often causing visual impairment without any prior symptoms. It is usually caused due to high intra ocular pressure (IOP) which can result in blindness by damaging the optic nerve. Hence, diagnosing the glaucoma in the early stage can prevent the vision loss. This paper proposes a novel automated glaucoma diagnosis system using higher order spectra (HOS) cumulants extracted from Radon transform (RT) applied on digital fundus images. In this work, the images are classified into three classes: normal, mild glaucoma and moderate/severe glaucoma. The 3rd order HOS cumulant features are subjected to linear discriminant analysis (LDA) to reduce the number of features and then these clinically significant linear discriminant (LD) features are fed to the support vector machine (SVM) and Na{\"i}ve Bayesian (NB) classifiers for automated diagnosis. This work is validated using 272 fundus images with 100 normal, 72 mild glaucoma and 100 moderate/severe glaucoma images using ten-fold cross validation method. The proposed system can detect the early glaucoma stage with an average accuracy of 84.72{\%}, and the three classes with an average accuracy of 92.65{\%}, sensitivity of 100{\%} and specificity of 92{\%} using NB classifier. This automated system can be used during the mass screening of glaucoma.",
author = "Noronha, {Kevin P.} and Acharya, {U. Rajendra} and Nayak, {K. Prabhakar} and Martis, {Roshan Joy} and Bhandary, {Sulatha V.}",
year = "2014",
doi = "10.1016/j.bspc.2013.11.006",
language = "English",
volume = "10",
pages = "174--183",
journal = "Biomedical Signal Processing and Control",
issn = "1746-8094",
publisher = "Elsevier BV",
number = "1",

}

Automated classification of glaucoma stages using higher order cumulant features. / Noronha, Kevin P.; Acharya, U. Rajendra; Nayak, K. Prabhakar; Martis, Roshan Joy; Bhandary, Sulatha V.

In: Biomedical Signal Processing and Control, Vol. 10, No. 1, 2014, p. 174-183.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated classification of glaucoma stages using higher order cumulant features

AU - Noronha, Kevin P.

AU - Acharya, U. Rajendra

AU - Nayak, K. Prabhakar

AU - Martis, Roshan Joy

AU - Bhandary, Sulatha V.

PY - 2014

Y1 - 2014

N2 - Glaucoma is a group of disease often causing visual impairment without any prior symptoms. It is usually caused due to high intra ocular pressure (IOP) which can result in blindness by damaging the optic nerve. Hence, diagnosing the glaucoma in the early stage can prevent the vision loss. This paper proposes a novel automated glaucoma diagnosis system using higher order spectra (HOS) cumulants extracted from Radon transform (RT) applied on digital fundus images. In this work, the images are classified into three classes: normal, mild glaucoma and moderate/severe glaucoma. The 3rd order HOS cumulant features are subjected to linear discriminant analysis (LDA) to reduce the number of features and then these clinically significant linear discriminant (LD) features are fed to the support vector machine (SVM) and Naïve Bayesian (NB) classifiers for automated diagnosis. This work is validated using 272 fundus images with 100 normal, 72 mild glaucoma and 100 moderate/severe glaucoma images using ten-fold cross validation method. The proposed system can detect the early glaucoma stage with an average accuracy of 84.72%, and the three classes with an average accuracy of 92.65%, sensitivity of 100% and specificity of 92% using NB classifier. This automated system can be used during the mass screening of glaucoma.

AB - Glaucoma is a group of disease often causing visual impairment without any prior symptoms. It is usually caused due to high intra ocular pressure (IOP) which can result in blindness by damaging the optic nerve. Hence, diagnosing the glaucoma in the early stage can prevent the vision loss. This paper proposes a novel automated glaucoma diagnosis system using higher order spectra (HOS) cumulants extracted from Radon transform (RT) applied on digital fundus images. In this work, the images are classified into three classes: normal, mild glaucoma and moderate/severe glaucoma. The 3rd order HOS cumulant features are subjected to linear discriminant analysis (LDA) to reduce the number of features and then these clinically significant linear discriminant (LD) features are fed to the support vector machine (SVM) and Naïve Bayesian (NB) classifiers for automated diagnosis. This work is validated using 272 fundus images with 100 normal, 72 mild glaucoma and 100 moderate/severe glaucoma images using ten-fold cross validation method. The proposed system can detect the early glaucoma stage with an average accuracy of 84.72%, and the three classes with an average accuracy of 92.65%, sensitivity of 100% and specificity of 92% using NB classifier. This automated system can be used during the mass screening of glaucoma.

UR - http://www.scopus.com/inward/record.url?scp=84897980968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897980968&partnerID=8YFLogxK

U2 - 10.1016/j.bspc.2013.11.006

DO - 10.1016/j.bspc.2013.11.006

M3 - Article

AN - SCOPUS:84897980968

VL - 10

SP - 174

EP - 183

JO - Biomedical Signal Processing and Control

JF - Biomedical Signal Processing and Control

SN - 1746-8094

IS - 1

ER -