A novel algorithm to detect glaucoma risk using texton and local configuration pattern features extracted from fundus images

U. Rajendra Acharya, Shreya Bhat, Joel E.W. Koh, Sulatha V. Bhandary, Hojjat Adeli

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Glaucoma is an optic neuropathy defined by characteristic damage to the optic nerve and accompanying visual field deficits. Early diagnosis and treatment are critical to prevent irreversible vision loss and ultimate blindness. Current techniques for computer-aided analysis of the optic nerve and retinal nerve fiber layer (RNFL) are expensive and require keen interpretation by trained specialists. Hence, an automated system is highly desirable for a cost-effective and accurate screening for the diagnosis of glaucoma. This paper presents a new methodology and a computerized diagnostic system. Adaptive histogram equalization is used to convert color images to grayscale images followed by convolution of these images with Leung-Malik (LM), Schmid (S), and maximum response (MR4 and MR8) filter banks. The basic microstructures in typical images are called textons. The convolution process produces textons. Local configuration pattern (LCP) features are extracted from these textons. The significant features are selected using a sequential floating forward search (SFFS) method and ranked using the statistical t-test. Finally, various classifiers are used for classification of images into normal and glaucomatous classes. A high classification accuracy of 95.8% is achieved using six features obtained from the LM filter bank and the k-nearest neighbor (kNN) classifier. A glaucoma integrative index (GRI) is also formulated to obtain a reliable and effective system.

Original languageEnglish
Pages (from-to)72-83
Number of pages12
JournalComputers in Biology and Medicine
Volume88
DOIs
Publication statusPublished - 01-09-2017

Fingerprint

Glaucoma
Optics
Filter banks
Optic Nerve
Convolution
Classifiers
Computer aided analysis
Optic Nerve Diseases
Statistical tests
Blindness
Visual Fields
Nerve Fibers
Early Diagnosis
Screening
Color
Costs and Cost Analysis
Microstructure
Fibers
Costs
Therapeutics

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Health Informatics

Cite this

@article{68c19d9bc4634165ab1fc5436c1d9760,
title = "A novel algorithm to detect glaucoma risk using texton and local configuration pattern features extracted from fundus images",
abstract = "Glaucoma is an optic neuropathy defined by characteristic damage to the optic nerve and accompanying visual field deficits. Early diagnosis and treatment are critical to prevent irreversible vision loss and ultimate blindness. Current techniques for computer-aided analysis of the optic nerve and retinal nerve fiber layer (RNFL) are expensive and require keen interpretation by trained specialists. Hence, an automated system is highly desirable for a cost-effective and accurate screening for the diagnosis of glaucoma. This paper presents a new methodology and a computerized diagnostic system. Adaptive histogram equalization is used to convert color images to grayscale images followed by convolution of these images with Leung-Malik (LM), Schmid (S), and maximum response (MR4 and MR8) filter banks. The basic microstructures in typical images are called textons. The convolution process produces textons. Local configuration pattern (LCP) features are extracted from these textons. The significant features are selected using a sequential floating forward search (SFFS) method and ranked using the statistical t-test. Finally, various classifiers are used for classification of images into normal and glaucomatous classes. A high classification accuracy of 95.8{\%} is achieved using six features obtained from the LM filter bank and the k-nearest neighbor (kNN) classifier. A glaucoma integrative index (GRI) is also formulated to obtain a reliable and effective system.",
author = "Acharya, {U. Rajendra} and Shreya Bhat and Koh, {Joel E.W.} and Bhandary, {Sulatha V.} and Hojjat Adeli",
year = "2017",
month = "9",
day = "1",
doi = "10.1016/j.compbiomed.2017.06.022",
language = "English",
volume = "88",
pages = "72--83",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

A novel algorithm to detect glaucoma risk using texton and local configuration pattern features extracted from fundus images. / Acharya, U. Rajendra; Bhat, Shreya; Koh, Joel E.W.; Bhandary, Sulatha V.; Adeli, Hojjat.

In: Computers in Biology and Medicine, Vol. 88, 01.09.2017, p. 72-83.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A novel algorithm to detect glaucoma risk using texton and local configuration pattern features extracted from fundus images

AU - Acharya, U. Rajendra

AU - Bhat, Shreya

AU - Koh, Joel E.W.

AU - Bhandary, Sulatha V.

AU - Adeli, Hojjat

PY - 2017/9/1

Y1 - 2017/9/1

N2 - Glaucoma is an optic neuropathy defined by characteristic damage to the optic nerve and accompanying visual field deficits. Early diagnosis and treatment are critical to prevent irreversible vision loss and ultimate blindness. Current techniques for computer-aided analysis of the optic nerve and retinal nerve fiber layer (RNFL) are expensive and require keen interpretation by trained specialists. Hence, an automated system is highly desirable for a cost-effective and accurate screening for the diagnosis of glaucoma. This paper presents a new methodology and a computerized diagnostic system. Adaptive histogram equalization is used to convert color images to grayscale images followed by convolution of these images with Leung-Malik (LM), Schmid (S), and maximum response (MR4 and MR8) filter banks. The basic microstructures in typical images are called textons. The convolution process produces textons. Local configuration pattern (LCP) features are extracted from these textons. The significant features are selected using a sequential floating forward search (SFFS) method and ranked using the statistical t-test. Finally, various classifiers are used for classification of images into normal and glaucomatous classes. A high classification accuracy of 95.8% is achieved using six features obtained from the LM filter bank and the k-nearest neighbor (kNN) classifier. A glaucoma integrative index (GRI) is also formulated to obtain a reliable and effective system.

AB - Glaucoma is an optic neuropathy defined by characteristic damage to the optic nerve and accompanying visual field deficits. Early diagnosis and treatment are critical to prevent irreversible vision loss and ultimate blindness. Current techniques for computer-aided analysis of the optic nerve and retinal nerve fiber layer (RNFL) are expensive and require keen interpretation by trained specialists. Hence, an automated system is highly desirable for a cost-effective and accurate screening for the diagnosis of glaucoma. This paper presents a new methodology and a computerized diagnostic system. Adaptive histogram equalization is used to convert color images to grayscale images followed by convolution of these images with Leung-Malik (LM), Schmid (S), and maximum response (MR4 and MR8) filter banks. The basic microstructures in typical images are called textons. The convolution process produces textons. Local configuration pattern (LCP) features are extracted from these textons. The significant features are selected using a sequential floating forward search (SFFS) method and ranked using the statistical t-test. Finally, various classifiers are used for classification of images into normal and glaucomatous classes. A high classification accuracy of 95.8% is achieved using six features obtained from the LM filter bank and the k-nearest neighbor (kNN) classifier. A glaucoma integrative index (GRI) is also formulated to obtain a reliable and effective system.

UR - http://www.scopus.com/inward/record.url?scp=85022055882&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85022055882&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2017.06.022

DO - 10.1016/j.compbiomed.2017.06.022

M3 - Article

VL - 88

SP - 72

EP - 83

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -