A Two Layer Sparse Autoencoder for Glaucoma Identification with Fundus Images

U. Raghavendra, Anjan Gudigar, Sulatha V. Bhandary, Tejaswi N. Rao, Edward J. Ciaccio, U. Rajendra Acharya

Research output: Contribution to journalArticle

Abstract

Glaucoma is a type of eye condition which may result in partial or consummate vision loss. Higher intraocular pressure is the leading cause for this condition. Screening for glaucoma and early detection can avert vision loss. Computer aided diagnosis (CAD) is an automated process with the potential to identify glaucoma early through quantitative analysis of digital fundus images. Preparing an effective model for CAD requires a large database. This study presents a CAD tool for the precise detection of glaucoma using a machine learning approach. An autoencoder is trained to determine effective and important features from fundus images. These features are used to develop classes of glaucoma for testing. The method achieved an F − measure value of 0.95 utilizing 1426 digital fundus images (589 control and 837 glaucoma). The efficacy of the system is evident, and is suggestive of its possible utility as an additional tool for verification of clinical decisions.

Original languageEnglish
Article number299
JournalJournal of Medical Systems
Volume43
Issue number9
DOIs
Publication statusPublished - 01-09-2019

Fingerprint

Computer aided diagnosis
Glaucoma
Learning systems
Screening
Testing
Chemical analysis
Intraocular Pressure
Computer Simulation
Databases

All Science Journal Classification (ASJC) codes

  • Medicine (miscellaneous)
  • Information Systems
  • Health Informatics
  • Health Information Management

Cite this

@article{a0e28a4657164b219385ad51c31ef38a,
title = "A Two Layer Sparse Autoencoder for Glaucoma Identification with Fundus Images",
abstract = "Glaucoma is a type of eye condition which may result in partial or consummate vision loss. Higher intraocular pressure is the leading cause for this condition. Screening for glaucoma and early detection can avert vision loss. Computer aided diagnosis (CAD) is an automated process with the potential to identify glaucoma early through quantitative analysis of digital fundus images. Preparing an effective model for CAD requires a large database. This study presents a CAD tool for the precise detection of glaucoma using a machine learning approach. An autoencoder is trained to determine effective and important features from fundus images. These features are used to develop classes of glaucoma for testing. The method achieved an F − measure value of 0.95 utilizing 1426 digital fundus images (589 control and 837 glaucoma). The efficacy of the system is evident, and is suggestive of its possible utility as an additional tool for verification of clinical decisions.",
author = "U. Raghavendra and Anjan Gudigar and Bhandary, {Sulatha V.} and Rao, {Tejaswi N.} and Ciaccio, {Edward J.} and Acharya, {U. Rajendra}",
year = "2019",
month = "9",
day = "1",
doi = "10.1007/s10916-019-1427-x",
language = "English",
volume = "43",
journal = "Journal of Medical Systems",
issn = "0148-5598",
publisher = "Springer New York",
number = "9",

}

A Two Layer Sparse Autoencoder for Glaucoma Identification with Fundus Images. / Raghavendra, U.; Gudigar, Anjan; Bhandary, Sulatha V.; Rao, Tejaswi N.; Ciaccio, Edward J.; Acharya, U. Rajendra.

In: Journal of Medical Systems, Vol. 43, No. 9, 299, 01.09.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Two Layer Sparse Autoencoder for Glaucoma Identification with Fundus Images

AU - Raghavendra, U.

AU - Gudigar, Anjan

AU - Bhandary, Sulatha V.

AU - Rao, Tejaswi N.

AU - Ciaccio, Edward J.

AU - Acharya, U. Rajendra

PY - 2019/9/1

Y1 - 2019/9/1

N2 - Glaucoma is a type of eye condition which may result in partial or consummate vision loss. Higher intraocular pressure is the leading cause for this condition. Screening for glaucoma and early detection can avert vision loss. Computer aided diagnosis (CAD) is an automated process with the potential to identify glaucoma early through quantitative analysis of digital fundus images. Preparing an effective model for CAD requires a large database. This study presents a CAD tool for the precise detection of glaucoma using a machine learning approach. An autoencoder is trained to determine effective and important features from fundus images. These features are used to develop classes of glaucoma for testing. The method achieved an F − measure value of 0.95 utilizing 1426 digital fundus images (589 control and 837 glaucoma). The efficacy of the system is evident, and is suggestive of its possible utility as an additional tool for verification of clinical decisions.

AB - Glaucoma is a type of eye condition which may result in partial or consummate vision loss. Higher intraocular pressure is the leading cause for this condition. Screening for glaucoma and early detection can avert vision loss. Computer aided diagnosis (CAD) is an automated process with the potential to identify glaucoma early through quantitative analysis of digital fundus images. Preparing an effective model for CAD requires a large database. This study presents a CAD tool for the precise detection of glaucoma using a machine learning approach. An autoencoder is trained to determine effective and important features from fundus images. These features are used to develop classes of glaucoma for testing. The method achieved an F − measure value of 0.95 utilizing 1426 digital fundus images (589 control and 837 glaucoma). The efficacy of the system is evident, and is suggestive of its possible utility as an additional tool for verification of clinical decisions.

UR - http://www.scopus.com/inward/record.url?scp=85069929355&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069929355&partnerID=8YFLogxK

U2 - 10.1007/s10916-019-1427-x

DO - 10.1007/s10916-019-1427-x

M3 - Article

VL - 43

JO - Journal of Medical Systems

JF - Journal of Medical Systems

SN - 0148-5598

IS - 9

M1 - 299

ER -