Combining information from 3 anatomic regions in the diagnosis of glaucoma with time-domain optical coherence tomography

Mingwu Wang, Ake Tzu Hui Lu, Rohit Varma, Joel S. Schuman, David S. Greenfield, David Huang

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

PURPOSE: To improve the diagnosis of glaucoma by combining time-domain optical coherence tomography (TD-OCT) measurements of the optic disc, circumpapillary retinal nerve fiber layer (RNFL), and macular retinal thickness. PATIENTS AND METHODS: Ninety-six age-matched normal and 96 perimetric glaucoma participants were included in this observational, cross-sectional study. Or-logic, support vector machine, relevance vector machine, and linear discrimination function were used to analyze the performances of combined TD-OCT diagnostic variables. RESULTS: The area under the receiver-operating curve (AROC) was used to evaluate the diagnostic accuracy and to compare the diagnostic performance of single and combined anatomic variables. The best RNFL thickness variables were the inferior (AROC=0.900), overall (AROC=0.892), and superior quadrants (AROC=0.850). The best optic disc variables were horizontal integrated rim width (AROC=0.909), vertical integrated rim area (AROC=0.908), and cup/disc vertical ratio (AROC=0.890). All macular retinal thickness variables had AROCs of 0.829 or less. Combining the top 3 RNFL and optic disc variables in optimizing glaucoma diagnosis, support vector machine had the highest AROC, 0.954, followed by or-logic (AROC=0.946), linear discrimination function (AROC=0.946), and relevance vector machine (AROC=0.943). All combination diagnostic variables had significantly larger AROCs than any single diagnostic variable. There are no significant differences among the combination diagnostic indices. CONCLUSIONS: With TD-OCT, RNFL and optic disc variables had better diagnostic accuracy than macular retinal variables. Combining top RNFL and optic disc variables significantly improved diagnostic performance. Clinically, or-logic classification was the most practical analytical tool with sufficient accuracy to diagnose early glaucoma.

Original languageEnglish (US)
Pages (from-to)129-135
Number of pages7
JournalJournal of Glaucoma
Volume23
Issue number3
DOIs
StatePublished - 2014

Fingerprint

Optic Disk
Optical Coherence Tomography
Nerve Fibers
Glaucoma
Cross-Sectional Studies
Support Vector Machine

Keywords

  • Glaucoma
  • Image processing
  • Imaging
  • Optical coherence tomography

ASJC Scopus subject areas

  • Ophthalmology

Cite this

Combining information from 3 anatomic regions in the diagnosis of glaucoma with time-domain optical coherence tomography. / Wang, Mingwu; Lu, Ake Tzu Hui; Varma, Rohit; Schuman, Joel S.; Greenfield, David S.; Huang, David.

In: Journal of Glaucoma, Vol. 23, No. 3, 2014, p. 129-135.

Research output: Contribution to journalArticle

Wang, Mingwu ; Lu, Ake Tzu Hui ; Varma, Rohit ; Schuman, Joel S. ; Greenfield, David S. ; Huang, David. / Combining information from 3 anatomic regions in the diagnosis of glaucoma with time-domain optical coherence tomography. In: Journal of Glaucoma. 2014 ; Vol. 23, No. 3. pp. 129-135.
@article{25bb68630e894744b0f890f926926000,
title = "Combining information from 3 anatomic regions in the diagnosis of glaucoma with time-domain optical coherence tomography",
abstract = "PURPOSE: To improve the diagnosis of glaucoma by combining time-domain optical coherence tomography (TD-OCT) measurements of the optic disc, circumpapillary retinal nerve fiber layer (RNFL), and macular retinal thickness. PATIENTS AND METHODS: Ninety-six age-matched normal and 96 perimetric glaucoma participants were included in this observational, cross-sectional study. Or-logic, support vector machine, relevance vector machine, and linear discrimination function were used to analyze the performances of combined TD-OCT diagnostic variables. RESULTS: The area under the receiver-operating curve (AROC) was used to evaluate the diagnostic accuracy and to compare the diagnostic performance of single and combined anatomic variables. The best RNFL thickness variables were the inferior (AROC=0.900), overall (AROC=0.892), and superior quadrants (AROC=0.850). The best optic disc variables were horizontal integrated rim width (AROC=0.909), vertical integrated rim area (AROC=0.908), and cup/disc vertical ratio (AROC=0.890). All macular retinal thickness variables had AROCs of 0.829 or less. Combining the top 3 RNFL and optic disc variables in optimizing glaucoma diagnosis, support vector machine had the highest AROC, 0.954, followed by or-logic (AROC=0.946), linear discrimination function (AROC=0.946), and relevance vector machine (AROC=0.943). All combination diagnostic variables had significantly larger AROCs than any single diagnostic variable. There are no significant differences among the combination diagnostic indices. CONCLUSIONS: With TD-OCT, RNFL and optic disc variables had better diagnostic accuracy than macular retinal variables. Combining top RNFL and optic disc variables significantly improved diagnostic performance. Clinically, or-logic classification was the most practical analytical tool with sufficient accuracy to diagnose early glaucoma.",
keywords = "Glaucoma, Image processing, Imaging, Optical coherence tomography",
author = "Mingwu Wang and Lu, {Ake Tzu Hui} and Rohit Varma and Schuman, {Joel S.} and Greenfield, {David S.} and David Huang",
year = "2014",
doi = "10.1097/IJG.0b013e318264b941",
language = "English (US)",
volume = "23",
pages = "129--135",
journal = "Journal of Glaucoma",
issn = "1057-0829",
publisher = "Lippincott Williams and Wilkins",
number = "3",

}

TY - JOUR

T1 - Combining information from 3 anatomic regions in the diagnosis of glaucoma with time-domain optical coherence tomography

AU - Wang, Mingwu

AU - Lu, Ake Tzu Hui

AU - Varma, Rohit

AU - Schuman, Joel S.

AU - Greenfield, David S.

AU - Huang, David

PY - 2014

Y1 - 2014

N2 - PURPOSE: To improve the diagnosis of glaucoma by combining time-domain optical coherence tomography (TD-OCT) measurements of the optic disc, circumpapillary retinal nerve fiber layer (RNFL), and macular retinal thickness. PATIENTS AND METHODS: Ninety-six age-matched normal and 96 perimetric glaucoma participants were included in this observational, cross-sectional study. Or-logic, support vector machine, relevance vector machine, and linear discrimination function were used to analyze the performances of combined TD-OCT diagnostic variables. RESULTS: The area under the receiver-operating curve (AROC) was used to evaluate the diagnostic accuracy and to compare the diagnostic performance of single and combined anatomic variables. The best RNFL thickness variables were the inferior (AROC=0.900), overall (AROC=0.892), and superior quadrants (AROC=0.850). The best optic disc variables were horizontal integrated rim width (AROC=0.909), vertical integrated rim area (AROC=0.908), and cup/disc vertical ratio (AROC=0.890). All macular retinal thickness variables had AROCs of 0.829 or less. Combining the top 3 RNFL and optic disc variables in optimizing glaucoma diagnosis, support vector machine had the highest AROC, 0.954, followed by or-logic (AROC=0.946), linear discrimination function (AROC=0.946), and relevance vector machine (AROC=0.943). All combination diagnostic variables had significantly larger AROCs than any single diagnostic variable. There are no significant differences among the combination diagnostic indices. CONCLUSIONS: With TD-OCT, RNFL and optic disc variables had better diagnostic accuracy than macular retinal variables. Combining top RNFL and optic disc variables significantly improved diagnostic performance. Clinically, or-logic classification was the most practical analytical tool with sufficient accuracy to diagnose early glaucoma.

AB - PURPOSE: To improve the diagnosis of glaucoma by combining time-domain optical coherence tomography (TD-OCT) measurements of the optic disc, circumpapillary retinal nerve fiber layer (RNFL), and macular retinal thickness. PATIENTS AND METHODS: Ninety-six age-matched normal and 96 perimetric glaucoma participants were included in this observational, cross-sectional study. Or-logic, support vector machine, relevance vector machine, and linear discrimination function were used to analyze the performances of combined TD-OCT diagnostic variables. RESULTS: The area under the receiver-operating curve (AROC) was used to evaluate the diagnostic accuracy and to compare the diagnostic performance of single and combined anatomic variables. The best RNFL thickness variables were the inferior (AROC=0.900), overall (AROC=0.892), and superior quadrants (AROC=0.850). The best optic disc variables were horizontal integrated rim width (AROC=0.909), vertical integrated rim area (AROC=0.908), and cup/disc vertical ratio (AROC=0.890). All macular retinal thickness variables had AROCs of 0.829 or less. Combining the top 3 RNFL and optic disc variables in optimizing glaucoma diagnosis, support vector machine had the highest AROC, 0.954, followed by or-logic (AROC=0.946), linear discrimination function (AROC=0.946), and relevance vector machine (AROC=0.943). All combination diagnostic variables had significantly larger AROCs than any single diagnostic variable. There are no significant differences among the combination diagnostic indices. CONCLUSIONS: With TD-OCT, RNFL and optic disc variables had better diagnostic accuracy than macular retinal variables. Combining top RNFL and optic disc variables significantly improved diagnostic performance. Clinically, or-logic classification was the most practical analytical tool with sufficient accuracy to diagnose early glaucoma.

KW - Glaucoma

KW - Image processing

KW - Imaging

KW - Optical coherence tomography

UR - http://www.scopus.com/inward/record.url?scp=84896388346&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896388346&partnerID=8YFLogxK

U2 - 10.1097/IJG.0b013e318264b941

DO - 10.1097/IJG.0b013e318264b941

M3 - Article

VL - 23

SP - 129

EP - 135

JO - Journal of Glaucoma

JF - Journal of Glaucoma

SN - 1057-0829

IS - 3

ER -