Accuracy of ROPtool vs individual examiners in assessing retinal vascular tortuosity

David K. Wallace, Sharon F. Freedman, Zheen Zhao, Sin Ho Jung

Research output: Contribution to journalArticle

56 Citations (Scopus)

Abstract

Objective: To prospectively determine if tortuosity assessment by a computer program (ROPtool) that traces retinal blood vessels and measures their tortuosity was more accurate than that of individual pediatric ophthalmologists. Methods: One hundred eighty-five high-quality RetCam images from premature infants were circulated to 3 retinopathy of prematurity (ROP) experts and 3 other pediatric ophthalmologists ("examiners") who graded the tortuosity in each quadrant as normal, pre-plus, or plus. These same images were analyzed using ROPtool. Results: Using expert consensus as the standard, ROPtool's overall accuracy of 95% (175 of 185) for identifying tortuosity sufficient for plus disease was similar to that of examiner 1 (93%; 172 of 185; P = .50), examiner 2 (93%; 172 of 185; P = .50), and examiner 3 (91%; 168 of 185; P = .10). ROPtool's sensitivity of 97% (36 of 37) compared favorably with that of examiner 1 (65%; 24 of 37; P < .001), examiner 2 (70%; 26 of 37; P < .001), and examiner 3 (81%; 30 of 37; P = .06). Conclusion: Computer-assisted analysis of retinal images can potentially reduce subjectivity in the diagnosis of plus disease and optimize timing of follow-up and treatment for ROP.

Original languageEnglish (US)
Pages (from-to)1523-1530
Number of pages8
JournalArchives of Ophthalmology
Volume125
Issue number11
DOIs
StatePublished - Nov 1 2007
Externally publishedYes

Fingerprint

Retinal Vessels
Retinopathy of Prematurity
Pediatrics
Computer-Assisted Image Processing
Premature Infants
Software
Ophthalmologists
Therapeutics

ASJC Scopus subject areas

  • Ophthalmology

Cite this

Accuracy of ROPtool vs individual examiners in assessing retinal vascular tortuosity. / Wallace, David K.; Freedman, Sharon F.; Zhao, Zheen; Jung, Sin Ho.

In: Archives of Ophthalmology, Vol. 125, No. 11, 01.11.2007, p. 1523-1530.

Research output: Contribution to journalArticle

Wallace, David K. ; Freedman, Sharon F. ; Zhao, Zheen ; Jung, Sin Ho. / Accuracy of ROPtool vs individual examiners in assessing retinal vascular tortuosity. In: Archives of Ophthalmology. 2007 ; Vol. 125, No. 11. pp. 1523-1530.
@article{3d9fbe8195f64efa8b51bceaec4dcc37,
title = "Accuracy of ROPtool vs individual examiners in assessing retinal vascular tortuosity",
abstract = "Objective: To prospectively determine if tortuosity assessment by a computer program (ROPtool) that traces retinal blood vessels and measures their tortuosity was more accurate than that of individual pediatric ophthalmologists. Methods: One hundred eighty-five high-quality RetCam images from premature infants were circulated to 3 retinopathy of prematurity (ROP) experts and 3 other pediatric ophthalmologists ({"}examiners{"}) who graded the tortuosity in each quadrant as normal, pre-plus, or plus. These same images were analyzed using ROPtool. Results: Using expert consensus as the standard, ROPtool's overall accuracy of 95{\%} (175 of 185) for identifying tortuosity sufficient for plus disease was similar to that of examiner 1 (93{\%}; 172 of 185; P = .50), examiner 2 (93{\%}; 172 of 185; P = .50), and examiner 3 (91{\%}; 168 of 185; P = .10). ROPtool's sensitivity of 97{\%} (36 of 37) compared favorably with that of examiner 1 (65{\%}; 24 of 37; P < .001), examiner 2 (70{\%}; 26 of 37; P < .001), and examiner 3 (81{\%}; 30 of 37; P = .06). Conclusion: Computer-assisted analysis of retinal images can potentially reduce subjectivity in the diagnosis of plus disease and optimize timing of follow-up and treatment for ROP.",
author = "Wallace, {David K.} and Freedman, {Sharon F.} and Zheen Zhao and Jung, {Sin Ho}",
year = "2007",
month = "11",
day = "1",
doi = "10.1001/archopht.125.11.1523",
language = "English (US)",
volume = "125",
pages = "1523--1530",
journal = "JAMA Ophthalmology",
issn = "2168-6165",
publisher = "American Medical Association",
number = "11",

}

TY - JOUR

T1 - Accuracy of ROPtool vs individual examiners in assessing retinal vascular tortuosity

AU - Wallace, David K.

AU - Freedman, Sharon F.

AU - Zhao, Zheen

AU - Jung, Sin Ho

PY - 2007/11/1

Y1 - 2007/11/1

N2 - Objective: To prospectively determine if tortuosity assessment by a computer program (ROPtool) that traces retinal blood vessels and measures their tortuosity was more accurate than that of individual pediatric ophthalmologists. Methods: One hundred eighty-five high-quality RetCam images from premature infants were circulated to 3 retinopathy of prematurity (ROP) experts and 3 other pediatric ophthalmologists ("examiners") who graded the tortuosity in each quadrant as normal, pre-plus, or plus. These same images were analyzed using ROPtool. Results: Using expert consensus as the standard, ROPtool's overall accuracy of 95% (175 of 185) for identifying tortuosity sufficient for plus disease was similar to that of examiner 1 (93%; 172 of 185; P = .50), examiner 2 (93%; 172 of 185; P = .50), and examiner 3 (91%; 168 of 185; P = .10). ROPtool's sensitivity of 97% (36 of 37) compared favorably with that of examiner 1 (65%; 24 of 37; P < .001), examiner 2 (70%; 26 of 37; P < .001), and examiner 3 (81%; 30 of 37; P = .06). Conclusion: Computer-assisted analysis of retinal images can potentially reduce subjectivity in the diagnosis of plus disease and optimize timing of follow-up and treatment for ROP.

AB - Objective: To prospectively determine if tortuosity assessment by a computer program (ROPtool) that traces retinal blood vessels and measures their tortuosity was more accurate than that of individual pediatric ophthalmologists. Methods: One hundred eighty-five high-quality RetCam images from premature infants were circulated to 3 retinopathy of prematurity (ROP) experts and 3 other pediatric ophthalmologists ("examiners") who graded the tortuosity in each quadrant as normal, pre-plus, or plus. These same images were analyzed using ROPtool. Results: Using expert consensus as the standard, ROPtool's overall accuracy of 95% (175 of 185) for identifying tortuosity sufficient for plus disease was similar to that of examiner 1 (93%; 172 of 185; P = .50), examiner 2 (93%; 172 of 185; P = .50), and examiner 3 (91%; 168 of 185; P = .10). ROPtool's sensitivity of 97% (36 of 37) compared favorably with that of examiner 1 (65%; 24 of 37; P < .001), examiner 2 (70%; 26 of 37; P < .001), and examiner 3 (81%; 30 of 37; P = .06). Conclusion: Computer-assisted analysis of retinal images can potentially reduce subjectivity in the diagnosis of plus disease and optimize timing of follow-up and treatment for ROP.

UR - http://www.scopus.com/inward/record.url?scp=36148984913&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36148984913&partnerID=8YFLogxK

U2 - 10.1001/archopht.125.11.1523

DO - 10.1001/archopht.125.11.1523

M3 - Article

VL - 125

SP - 1523

EP - 1530

JO - JAMA Ophthalmology

JF - JAMA Ophthalmology

SN - 2168-6165

IS - 11

ER -