Image analysis for retinopathy of prematurity diagnosis

Michael Chiang, Rony Gelman, M. Elena Martinez-Perez, Yunling E. Du, Daniel S. Casper, Leanne M. Currie, Payal D. Shah, Justin Starren, John T. Flynn

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Purpose: To review findings from the authors' published studies involving telemedicine and image analysis for retinopathy of prematurity (ROP) diagnosis. Methods: Twenty-two ROP experts interpreted a set of 34 wide-angle retinal images for presence of plus disease. For each image, a reference standard diagnosis was defined from expert consensus. A computer-based system was used to measure individual and linear combinations of image parameters for arteries and veins: integrated curvature (IC), diameter, and tortuosity index (TI). Sensitivity, specificity, and receiver operating characteristic areas under the curve (AUC) for plus disease diagnosis were determined for each expert. Sensitivity and specificity curves were calculated for the computer-based system by varying the diagnostic cutoffs for arterial IC and venous diameter. Individual vessels from the original 34 images were identified with particular diagnostic cutoffs, and combined into composite wide-angle images using graphics editing software. Results: For plus disease diagnosis, expert sensitivity ranged from 0.308-1.000, specificity from 0.571-1.000, and AUC from 0.784 to 1.000. Among computer system parameters, one linear combination had AUC 0.967, which was greater than that of 18 of 22 (81.8%) experts. Composite computer-generated images were produced using the arterial IC and venous diameter values associated with 75% under-diagnosis of plus disease (ie, 25% sensitivity cutoff), 50% under-diagnosis of plus disease (ie, 50% sensitivity cutoff), and 25% under-diagnosis of plus disease (ie, 75% sensitivity cutoff). Conclusions: Computer-based image analysis has the potential to diagnose severe ROP with comparable or better accuracy than experts, and could provide added value to telemedicine systems. Future quantitative definitions of plus disease might improve diagnostic objectivity.{A figure is presented}.

Original languageEnglish (US)
Pages (from-to)438-445
Number of pages8
JournalJournal of AAPOS
Volume13
Issue number5
DOIs
StatePublished - Oct 2009
Externally publishedYes

Fingerprint

Retinopathy of Prematurity
Computer Systems
Area Under Curve
Telemedicine
Sensitivity and Specificity
ROC Curve
Veins
Software
Arteries

ASJC Scopus subject areas

  • Ophthalmology
  • Pediatrics, Perinatology, and Child Health

Cite this

Chiang, M., Gelman, R., Martinez-Perez, M. E., Du, Y. E., Casper, D. S., Currie, L. M., ... Flynn, J. T. (2009). Image analysis for retinopathy of prematurity diagnosis. Journal of AAPOS, 13(5), 438-445. https://doi.org/10.1016/j.jaapos.2009.08.011

Image analysis for retinopathy of prematurity diagnosis. / Chiang, Michael; Gelman, Rony; Martinez-Perez, M. Elena; Du, Yunling E.; Casper, Daniel S.; Currie, Leanne M.; Shah, Payal D.; Starren, Justin; Flynn, John T.

In: Journal of AAPOS, Vol. 13, No. 5, 10.2009, p. 438-445.

Research output: Contribution to journalArticle

Chiang, M, Gelman, R, Martinez-Perez, ME, Du, YE, Casper, DS, Currie, LM, Shah, PD, Starren, J & Flynn, JT 2009, 'Image analysis for retinopathy of prematurity diagnosis', Journal of AAPOS, vol. 13, no. 5, pp. 438-445. https://doi.org/10.1016/j.jaapos.2009.08.011
Chiang M, Gelman R, Martinez-Perez ME, Du YE, Casper DS, Currie LM et al. Image analysis for retinopathy of prematurity diagnosis. Journal of AAPOS. 2009 Oct;13(5):438-445. https://doi.org/10.1016/j.jaapos.2009.08.011
Chiang, Michael ; Gelman, Rony ; Martinez-Perez, M. Elena ; Du, Yunling E. ; Casper, Daniel S. ; Currie, Leanne M. ; Shah, Payal D. ; Starren, Justin ; Flynn, John T. / Image analysis for retinopathy of prematurity diagnosis. In: Journal of AAPOS. 2009 ; Vol. 13, No. 5. pp. 438-445.
@article{c1913c719dfb4c2faef90ef932648ee7,
title = "Image analysis for retinopathy of prematurity diagnosis",
abstract = "Purpose: To review findings from the authors' published studies involving telemedicine and image analysis for retinopathy of prematurity (ROP) diagnosis. Methods: Twenty-two ROP experts interpreted a set of 34 wide-angle retinal images for presence of plus disease. For each image, a reference standard diagnosis was defined from expert consensus. A computer-based system was used to measure individual and linear combinations of image parameters for arteries and veins: integrated curvature (IC), diameter, and tortuosity index (TI). Sensitivity, specificity, and receiver operating characteristic areas under the curve (AUC) for plus disease diagnosis were determined for each expert. Sensitivity and specificity curves were calculated for the computer-based system by varying the diagnostic cutoffs for arterial IC and venous diameter. Individual vessels from the original 34 images were identified with particular diagnostic cutoffs, and combined into composite wide-angle images using graphics editing software. Results: For plus disease diagnosis, expert sensitivity ranged from 0.308-1.000, specificity from 0.571-1.000, and AUC from 0.784 to 1.000. Among computer system parameters, one linear combination had AUC 0.967, which was greater than that of 18 of 22 (81.8{\%}) experts. Composite computer-generated images were produced using the arterial IC and venous diameter values associated with 75{\%} under-diagnosis of plus disease (ie, 25{\%} sensitivity cutoff), 50{\%} under-diagnosis of plus disease (ie, 50{\%} sensitivity cutoff), and 25{\%} under-diagnosis of plus disease (ie, 75{\%} sensitivity cutoff). Conclusions: Computer-based image analysis has the potential to diagnose severe ROP with comparable or better accuracy than experts, and could provide added value to telemedicine systems. Future quantitative definitions of plus disease might improve diagnostic objectivity.{A figure is presented}.",
author = "Michael Chiang and Rony Gelman and Martinez-Perez, {M. Elena} and Du, {Yunling E.} and Casper, {Daniel S.} and Currie, {Leanne M.} and Shah, {Payal D.} and Justin Starren and Flynn, {John T.}",
year = "2009",
month = "10",
doi = "10.1016/j.jaapos.2009.08.011",
language = "English (US)",
volume = "13",
pages = "438--445",
journal = "Journal of AAPOS",
issn = "1091-8531",
publisher = "Mosby Inc.",
number = "5",

}

TY - JOUR

T1 - Image analysis for retinopathy of prematurity diagnosis

AU - Chiang, Michael

AU - Gelman, Rony

AU - Martinez-Perez, M. Elena

AU - Du, Yunling E.

AU - Casper, Daniel S.

AU - Currie, Leanne M.

AU - Shah, Payal D.

AU - Starren, Justin

AU - Flynn, John T.

PY - 2009/10

Y1 - 2009/10

N2 - Purpose: To review findings from the authors' published studies involving telemedicine and image analysis for retinopathy of prematurity (ROP) diagnosis. Methods: Twenty-two ROP experts interpreted a set of 34 wide-angle retinal images for presence of plus disease. For each image, a reference standard diagnosis was defined from expert consensus. A computer-based system was used to measure individual and linear combinations of image parameters for arteries and veins: integrated curvature (IC), diameter, and tortuosity index (TI). Sensitivity, specificity, and receiver operating characteristic areas under the curve (AUC) for plus disease diagnosis were determined for each expert. Sensitivity and specificity curves were calculated for the computer-based system by varying the diagnostic cutoffs for arterial IC and venous diameter. Individual vessels from the original 34 images were identified with particular diagnostic cutoffs, and combined into composite wide-angle images using graphics editing software. Results: For plus disease diagnosis, expert sensitivity ranged from 0.308-1.000, specificity from 0.571-1.000, and AUC from 0.784 to 1.000. Among computer system parameters, one linear combination had AUC 0.967, which was greater than that of 18 of 22 (81.8%) experts. Composite computer-generated images were produced using the arterial IC and venous diameter values associated with 75% under-diagnosis of plus disease (ie, 25% sensitivity cutoff), 50% under-diagnosis of plus disease (ie, 50% sensitivity cutoff), and 25% under-diagnosis of plus disease (ie, 75% sensitivity cutoff). Conclusions: Computer-based image analysis has the potential to diagnose severe ROP with comparable or better accuracy than experts, and could provide added value to telemedicine systems. Future quantitative definitions of plus disease might improve diagnostic objectivity.{A figure is presented}.

AB - Purpose: To review findings from the authors' published studies involving telemedicine and image analysis for retinopathy of prematurity (ROP) diagnosis. Methods: Twenty-two ROP experts interpreted a set of 34 wide-angle retinal images for presence of plus disease. For each image, a reference standard diagnosis was defined from expert consensus. A computer-based system was used to measure individual and linear combinations of image parameters for arteries and veins: integrated curvature (IC), diameter, and tortuosity index (TI). Sensitivity, specificity, and receiver operating characteristic areas under the curve (AUC) for plus disease diagnosis were determined for each expert. Sensitivity and specificity curves were calculated for the computer-based system by varying the diagnostic cutoffs for arterial IC and venous diameter. Individual vessels from the original 34 images were identified with particular diagnostic cutoffs, and combined into composite wide-angle images using graphics editing software. Results: For plus disease diagnosis, expert sensitivity ranged from 0.308-1.000, specificity from 0.571-1.000, and AUC from 0.784 to 1.000. Among computer system parameters, one linear combination had AUC 0.967, which was greater than that of 18 of 22 (81.8%) experts. Composite computer-generated images were produced using the arterial IC and venous diameter values associated with 75% under-diagnosis of plus disease (ie, 25% sensitivity cutoff), 50% under-diagnosis of plus disease (ie, 50% sensitivity cutoff), and 25% under-diagnosis of plus disease (ie, 75% sensitivity cutoff). Conclusions: Computer-based image analysis has the potential to diagnose severe ROP with comparable or better accuracy than experts, and could provide added value to telemedicine systems. Future quantitative definitions of plus disease might improve diagnostic objectivity.{A figure is presented}.

UR - http://www.scopus.com/inward/record.url?scp=70349943982&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349943982&partnerID=8YFLogxK

U2 - 10.1016/j.jaapos.2009.08.011

DO - 10.1016/j.jaapos.2009.08.011

M3 - Article

C2 - 19840720

AN - SCOPUS:70349943982

VL - 13

SP - 438

EP - 445

JO - Journal of AAPOS

JF - Journal of AAPOS

SN - 1091-8531

IS - 5

ER -