A tool for computer-aided diagnosis of retinopathy of prematurity

Zheen Zhao, David K. Wallace, Sharon F. Freedman, Stephen R. Aylward

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In this paper we present improvements to a software application, named ROPtool, that aids in the timely and accurate detection and diagnosis of retinopathy of prematurity (ROP). ROP occurs in 68% of infants less than 1251 grams at birth, and it is a leading cause of blindness for prematurely born infants. The standard of care for its diagnosis is the subjective assessment of retinal vessel dilation and tortuosity. There is significant inter-observer variation in those assessments. ROPtool analyzes retinal images, extracts user-selected blood vessels from those images, and quantifies the tortuosity of those vessels. The presence of ROP is then gauged by comparing the tortuosity of an infant's retinal vessels with measures made from a clinical-standard image of severely tortuous retinal vessels. The presence of such tortuous retinal vessels is referred to as 'plus disease'. In this paper, a novel metric of tortuosity is proposed. From the ophthalmologist's point of view, the new metric is an improvement from our previously published algorithm, since it uses smooth curves instead of straight lines to simulate 'normal vessels'. Another advantage of the new ROPtool is that minimal user interactions are required. ROPtool utilizes a ridge traversal algorithm to extract retinal vessels. The algorithm reconstructs connectivity along a vessel automatically. This paper supports its claims by reporting ROC curves from a pilot study involving 20 retinal images. The areas under two ROC curves, from two experts in ROP, using the new metric to diagnose 'tortuosity sufficient for plus disease', varied from 0.86 to 0.91.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2008 - Computer-Aided Diagnosis
DOIs
StatePublished - Jun 2 2008
Externally publishedYes
EventMedical Imaging 2008 - Computer-Aided Diagnosis - San Diego, CA, United States
Duration: Feb 19 2008Feb 21 2008

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume6915
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2008 - Computer-Aided Diagnosis
CountryUnited States
CitySan Diego, CA
Period2/19/082/21/08

Fingerprint

Computer aided diagnosis
Retinal Vessels
Retinopathy of Prematurity
vessels
ROC Curve
Blood vessels
retinal images
Application programs
Observer Variation
Blindness
Standard of Care
curves
blindness
Blood Vessels
Dilatation
Software
Parturition
blood vessels
ridges
computer programs

Keywords

  • Diagnosis
  • Feature extraction
  • Optical imaging
  • Quantitative image analysis

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Zhao, Z., Wallace, D. K., Freedman, S. F., & Aylward, S. R. (2008). A tool for computer-aided diagnosis of retinopathy of prematurity. In Medical Imaging 2008 - Computer-Aided Diagnosis [69152W] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 6915). https://doi.org/10.1117/12.769030

A tool for computer-aided diagnosis of retinopathy of prematurity. / Zhao, Zheen; Wallace, David K.; Freedman, Sharon F.; Aylward, Stephen R.

Medical Imaging 2008 - Computer-Aided Diagnosis. 2008. 69152W (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 6915).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhao, Z, Wallace, DK, Freedman, SF & Aylward, SR 2008, A tool for computer-aided diagnosis of retinopathy of prematurity. in Medical Imaging 2008 - Computer-Aided Diagnosis., 69152W, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 6915, Medical Imaging 2008 - Computer-Aided Diagnosis, San Diego, CA, United States, 2/19/08. https://doi.org/10.1117/12.769030
Zhao Z, Wallace DK, Freedman SF, Aylward SR. A tool for computer-aided diagnosis of retinopathy of prematurity. In Medical Imaging 2008 - Computer-Aided Diagnosis. 2008. 69152W. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.769030
Zhao, Zheen ; Wallace, David K. ; Freedman, Sharon F. ; Aylward, Stephen R. / A tool for computer-aided diagnosis of retinopathy of prematurity. Medical Imaging 2008 - Computer-Aided Diagnosis. 2008. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{b547a08b0090480cb78c2afb3334f749,
title = "A tool for computer-aided diagnosis of retinopathy of prematurity",
abstract = "In this paper we present improvements to a software application, named ROPtool, that aids in the timely and accurate detection and diagnosis of retinopathy of prematurity (ROP). ROP occurs in 68{\%} of infants less than 1251 grams at birth, and it is a leading cause of blindness for prematurely born infants. The standard of care for its diagnosis is the subjective assessment of retinal vessel dilation and tortuosity. There is significant inter-observer variation in those assessments. ROPtool analyzes retinal images, extracts user-selected blood vessels from those images, and quantifies the tortuosity of those vessels. The presence of ROP is then gauged by comparing the tortuosity of an infant's retinal vessels with measures made from a clinical-standard image of severely tortuous retinal vessels. The presence of such tortuous retinal vessels is referred to as 'plus disease'. In this paper, a novel metric of tortuosity is proposed. From the ophthalmologist's point of view, the new metric is an improvement from our previously published algorithm, since it uses smooth curves instead of straight lines to simulate 'normal vessels'. Another advantage of the new ROPtool is that minimal user interactions are required. ROPtool utilizes a ridge traversal algorithm to extract retinal vessels. The algorithm reconstructs connectivity along a vessel automatically. This paper supports its claims by reporting ROC curves from a pilot study involving 20 retinal images. The areas under two ROC curves, from two experts in ROP, using the new metric to diagnose 'tortuosity sufficient for plus disease', varied from 0.86 to 0.91.",
keywords = "Diagnosis, Feature extraction, Optical imaging, Quantitative image analysis",
author = "Zheen Zhao and Wallace, {David K.} and Freedman, {Sharon F.} and Aylward, {Stephen R.}",
year = "2008",
month = "6",
day = "2",
doi = "10.1117/12.769030",
language = "English (US)",
isbn = "9780819470997",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
booktitle = "Medical Imaging 2008 - Computer-Aided Diagnosis",

}

TY - GEN

T1 - A tool for computer-aided diagnosis of retinopathy of prematurity

AU - Zhao, Zheen

AU - Wallace, David K.

AU - Freedman, Sharon F.

AU - Aylward, Stephen R.

PY - 2008/6/2

Y1 - 2008/6/2

N2 - In this paper we present improvements to a software application, named ROPtool, that aids in the timely and accurate detection and diagnosis of retinopathy of prematurity (ROP). ROP occurs in 68% of infants less than 1251 grams at birth, and it is a leading cause of blindness for prematurely born infants. The standard of care for its diagnosis is the subjective assessment of retinal vessel dilation and tortuosity. There is significant inter-observer variation in those assessments. ROPtool analyzes retinal images, extracts user-selected blood vessels from those images, and quantifies the tortuosity of those vessels. The presence of ROP is then gauged by comparing the tortuosity of an infant's retinal vessels with measures made from a clinical-standard image of severely tortuous retinal vessels. The presence of such tortuous retinal vessels is referred to as 'plus disease'. In this paper, a novel metric of tortuosity is proposed. From the ophthalmologist's point of view, the new metric is an improvement from our previously published algorithm, since it uses smooth curves instead of straight lines to simulate 'normal vessels'. Another advantage of the new ROPtool is that minimal user interactions are required. ROPtool utilizes a ridge traversal algorithm to extract retinal vessels. The algorithm reconstructs connectivity along a vessel automatically. This paper supports its claims by reporting ROC curves from a pilot study involving 20 retinal images. The areas under two ROC curves, from two experts in ROP, using the new metric to diagnose 'tortuosity sufficient for plus disease', varied from 0.86 to 0.91.

AB - In this paper we present improvements to a software application, named ROPtool, that aids in the timely and accurate detection and diagnosis of retinopathy of prematurity (ROP). ROP occurs in 68% of infants less than 1251 grams at birth, and it is a leading cause of blindness for prematurely born infants. The standard of care for its diagnosis is the subjective assessment of retinal vessel dilation and tortuosity. There is significant inter-observer variation in those assessments. ROPtool analyzes retinal images, extracts user-selected blood vessels from those images, and quantifies the tortuosity of those vessels. The presence of ROP is then gauged by comparing the tortuosity of an infant's retinal vessels with measures made from a clinical-standard image of severely tortuous retinal vessels. The presence of such tortuous retinal vessels is referred to as 'plus disease'. In this paper, a novel metric of tortuosity is proposed. From the ophthalmologist's point of view, the new metric is an improvement from our previously published algorithm, since it uses smooth curves instead of straight lines to simulate 'normal vessels'. Another advantage of the new ROPtool is that minimal user interactions are required. ROPtool utilizes a ridge traversal algorithm to extract retinal vessels. The algorithm reconstructs connectivity along a vessel automatically. This paper supports its claims by reporting ROC curves from a pilot study involving 20 retinal images. The areas under two ROC curves, from two experts in ROP, using the new metric to diagnose 'tortuosity sufficient for plus disease', varied from 0.86 to 0.91.

KW - Diagnosis

KW - Feature extraction

KW - Optical imaging

KW - Quantitative image analysis

UR - http://www.scopus.com/inward/record.url?scp=44349110011&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44349110011&partnerID=8YFLogxK

U2 - 10.1117/12.769030

DO - 10.1117/12.769030

M3 - Conference contribution

SN - 9780819470997

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2008 - Computer-Aided Diagnosis

ER -