Clinical evaluation of the proper orthogonal decomposition framework for detecting glaucomatous changes in human subjects

Madhusudhanan Balasubramanian, Christopher Bowd, Robert N. Weinreb, Gianmarco Vizzeri, Luciana M. Alencar, Pamela A. Sample, Neil O'Leary, Linda M. Zangwill

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

PURPOSE. To evaluate the new proper orthogonal decomposition (POD) framework for detecting glaucomatous progression from HRT topographies of human subjects and compare it with HRT topographic change analysis (TCA). METHODS. Of 267 eyes of 187 participants with ≥4 retinal tomographic examinations in the University of California, San Diego Diagnostic Innovations in Glaucoma Study (DIGS), 21 eyes were of longitudinally normal subjects and 36 eyes progressed by stereophotographs or visual field- guided progression analysis (progressors). All others were considered nonprogressing (nonprogressors; n = 210 eyes). POD parameters of Euclidean distance (L2 norm), image Euclidean distance, and correlation were computed, and their area under receiver operating characteristic curves (AUC) in differentiating progressors from nonprogressors and normal subjects were compared to the TCA parameters of the number of superpixels with significant decrease in retinal height (red pixels), size of the largest cluster of red pixels (CSIZE), and CSIZE% of disc size, all within the optic disc margin. RESULTS. AUCs of the best performing POD L2 norm and TCA red pixel parameters in differentiating progressors from normal subjects were both 0.86 and in differentiating progressors from nonprogressors were 0.68 and 0.64, respectively; the AUC differences were not statistically significant. CONCLUSIONS. The POD framework, which can detect and confirm glaucomatous changes in a single follow-up visit, provides a performance similar to that of TCA in differentiating progressors from normal subjects and nonprogressors.

Original languageEnglish (US)
Pages (from-to)264-271
Number of pages8
JournalInvestigative Ophthalmology and Visual Science
Volume51
Issue number1
DOIs
StatePublished - Jan 2010
Externally publishedYes

Fingerprint

Area Under Curve
Optic Disk
Visual Fields
ROC Curve
Glaucoma

ASJC Scopus subject areas

  • Ophthalmology
  • Sensory Systems
  • Cellular and Molecular Neuroscience
  • Medicine(all)

Cite this

Clinical evaluation of the proper orthogonal decomposition framework for detecting glaucomatous changes in human subjects. / Balasubramanian, Madhusudhanan; Bowd, Christopher; Weinreb, Robert N.; Vizzeri, Gianmarco; Alencar, Luciana M.; Sample, Pamela A.; O'Leary, Neil; Zangwill, Linda M.

In: Investigative Ophthalmology and Visual Science, Vol. 51, No. 1, 01.2010, p. 264-271.

Research output: Contribution to journalArticle

Balasubramanian, Madhusudhanan ; Bowd, Christopher ; Weinreb, Robert N. ; Vizzeri, Gianmarco ; Alencar, Luciana M. ; Sample, Pamela A. ; O'Leary, Neil ; Zangwill, Linda M. / Clinical evaluation of the proper orthogonal decomposition framework for detecting glaucomatous changes in human subjects. In: Investigative Ophthalmology and Visual Science. 2010 ; Vol. 51, No. 1. pp. 264-271.
@article{9a3b50cbd2a44e8dafac57e0dccb9e93,
title = "Clinical evaluation of the proper orthogonal decomposition framework for detecting glaucomatous changes in human subjects",
abstract = "PURPOSE. To evaluate the new proper orthogonal decomposition (POD) framework for detecting glaucomatous progression from HRT topographies of human subjects and compare it with HRT topographic change analysis (TCA). METHODS. Of 267 eyes of 187 participants with ≥4 retinal tomographic examinations in the University of California, San Diego Diagnostic Innovations in Glaucoma Study (DIGS), 21 eyes were of longitudinally normal subjects and 36 eyes progressed by stereophotographs or visual field- guided progression analysis (progressors). All others were considered nonprogressing (nonprogressors; n = 210 eyes). POD parameters of Euclidean distance (L2 norm), image Euclidean distance, and correlation were computed, and their area under receiver operating characteristic curves (AUC) in differentiating progressors from nonprogressors and normal subjects were compared to the TCA parameters of the number of superpixels with significant decrease in retinal height (red pixels), size of the largest cluster of red pixels (CSIZE), and CSIZE{\%} of disc size, all within the optic disc margin. RESULTS. AUCs of the best performing POD L2 norm and TCA red pixel parameters in differentiating progressors from normal subjects were both 0.86 and in differentiating progressors from nonprogressors were 0.68 and 0.64, respectively; the AUC differences were not statistically significant. CONCLUSIONS. The POD framework, which can detect and confirm glaucomatous changes in a single follow-up visit, provides a performance similar to that of TCA in differentiating progressors from normal subjects and nonprogressors.",
author = "Madhusudhanan Balasubramanian and Christopher Bowd and Weinreb, {Robert N.} and Gianmarco Vizzeri and Alencar, {Luciana M.} and Sample, {Pamela A.} and Neil O'Leary and Zangwill, {Linda M.}",
year = "2010",
month = "1",
doi = "10.1167/iovs.08-2014",
language = "English (US)",
volume = "51",
pages = "264--271",
journal = "Investigative Ophthalmology and Visual Science",
issn = "0146-0404",
publisher = "Association for Research in Vision and Ophthalmology Inc.",
number = "1",

}

TY - JOUR

T1 - Clinical evaluation of the proper orthogonal decomposition framework for detecting glaucomatous changes in human subjects

AU - Balasubramanian, Madhusudhanan

AU - Bowd, Christopher

AU - Weinreb, Robert N.

AU - Vizzeri, Gianmarco

AU - Alencar, Luciana M.

AU - Sample, Pamela A.

AU - O'Leary, Neil

AU - Zangwill, Linda M.

PY - 2010/1

Y1 - 2010/1

N2 - PURPOSE. To evaluate the new proper orthogonal decomposition (POD) framework for detecting glaucomatous progression from HRT topographies of human subjects and compare it with HRT topographic change analysis (TCA). METHODS. Of 267 eyes of 187 participants with ≥4 retinal tomographic examinations in the University of California, San Diego Diagnostic Innovations in Glaucoma Study (DIGS), 21 eyes were of longitudinally normal subjects and 36 eyes progressed by stereophotographs or visual field- guided progression analysis (progressors). All others were considered nonprogressing (nonprogressors; n = 210 eyes). POD parameters of Euclidean distance (L2 norm), image Euclidean distance, and correlation were computed, and their area under receiver operating characteristic curves (AUC) in differentiating progressors from nonprogressors and normal subjects were compared to the TCA parameters of the number of superpixels with significant decrease in retinal height (red pixels), size of the largest cluster of red pixels (CSIZE), and CSIZE% of disc size, all within the optic disc margin. RESULTS. AUCs of the best performing POD L2 norm and TCA red pixel parameters in differentiating progressors from normal subjects were both 0.86 and in differentiating progressors from nonprogressors were 0.68 and 0.64, respectively; the AUC differences were not statistically significant. CONCLUSIONS. The POD framework, which can detect and confirm glaucomatous changes in a single follow-up visit, provides a performance similar to that of TCA in differentiating progressors from normal subjects and nonprogressors.

AB - PURPOSE. To evaluate the new proper orthogonal decomposition (POD) framework for detecting glaucomatous progression from HRT topographies of human subjects and compare it with HRT topographic change analysis (TCA). METHODS. Of 267 eyes of 187 participants with ≥4 retinal tomographic examinations in the University of California, San Diego Diagnostic Innovations in Glaucoma Study (DIGS), 21 eyes were of longitudinally normal subjects and 36 eyes progressed by stereophotographs or visual field- guided progression analysis (progressors). All others were considered nonprogressing (nonprogressors; n = 210 eyes). POD parameters of Euclidean distance (L2 norm), image Euclidean distance, and correlation were computed, and their area under receiver operating characteristic curves (AUC) in differentiating progressors from nonprogressors and normal subjects were compared to the TCA parameters of the number of superpixels with significant decrease in retinal height (red pixels), size of the largest cluster of red pixels (CSIZE), and CSIZE% of disc size, all within the optic disc margin. RESULTS. AUCs of the best performing POD L2 norm and TCA red pixel parameters in differentiating progressors from normal subjects were both 0.86 and in differentiating progressors from nonprogressors were 0.68 and 0.64, respectively; the AUC differences were not statistically significant. CONCLUSIONS. The POD framework, which can detect and confirm glaucomatous changes in a single follow-up visit, provides a performance similar to that of TCA in differentiating progressors from normal subjects and nonprogressors.

UR - http://www.scopus.com/inward/record.url?scp=75749147682&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=75749147682&partnerID=8YFLogxK

U2 - 10.1167/iovs.08-2014

DO - 10.1167/iovs.08-2014

M3 - Article

C2 - 19661228

AN - SCOPUS:75749147682

VL - 51

SP - 264

EP - 271

JO - Investigative Ophthalmology and Visual Science

JF - Investigative Ophthalmology and Visual Science

SN - 0146-0404

IS - 1

ER -