Using an image fusion methodology to improve efficiency and traceability of posterior pole vessel analysis by ROPtool

Sasapin G. Prakalapakorn, Laura A. Vickers, Rolando Estrada, Sharon F. Freedman, Carlo Tomasi, Sina Farsiu, David K. Wallace

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Background: The diagnosis of plus disease in retinopathy of prematurity (ROP) largely determines the need for treatment; however, this diagnosis is subjective. To make the diagnosis of plus disease more objective, semi-automated computer programs (e.g. ROPtool) have been created to quantify vascular dilation and tortuosity. ROPtool can accurately analyze blood vessels only in images with very good quality, but many still images captured by indirect ophthalmoscopy have insufficient image quality for ROPtool analysis. Purpose: To evaluate the ability of an image fusion methodology (robust mosaicing) to increase the efficiency and traceability of posterior pole vessel analysis by ROPtool. Materials and Methodology: We retrospectively reviewed video indirect ophthalmoscopy images acquired during routine ROP examinations and selected the best unenhanced still image from the video for each infant. Robust mosaicing was used to create an enhanced mosaic image from the same video for each eye. We evaluated the time required for ROPtool analysis as well as ROPtool’s ability to analyze vessels in enhanced vs. unenhanced images. Results: We included 39 eyes of 39 infants. ROPtool analysis was faster (125 vs. 152 seconds; p=0.02) in enhanced vs. unenhanced images, respectively. ROPtool was able to trace retinal vessels in more quadrants (143/156, 92% vs 115/156, 74%; p=0.16) in enhanced mosaic vs. unenhanced still images, respectively and in more overall (38/39, 97% vs. 34/39, 87%; p=0.07) enhanced mosaic vs. unenhanced still images, respectively. Conclusion: Retinal image enhancement using robust mosaicing advances efforts to automate grading of posterior pole disease in ROP.

Original languageEnglish (US)
Pages (from-to)143-151
Number of pages9
JournalOpen Ophthalmology Journal
Volume11
DOIs
StatePublished - Jun 1 2017
Externally publishedYes

Fingerprint

Retinopathy of Prematurity
Ophthalmoscopy
Blood Vessels
Image Enhancement
Retinal Vessels
Dilatation
Software
Therapeutics

Keywords

  • Image analysis
  • Retinopathy of prematurity
  • ROPtool
  • Vessel analysis

ASJC Scopus subject areas

  • Ophthalmology

Cite this

Using an image fusion methodology to improve efficiency and traceability of posterior pole vessel analysis by ROPtool. / Prakalapakorn, Sasapin G.; Vickers, Laura A.; Estrada, Rolando; Freedman, Sharon F.; Tomasi, Carlo; Farsiu, Sina; Wallace, David K.

In: Open Ophthalmology Journal, Vol. 11, 01.06.2017, p. 143-151.

Research output: Contribution to journalArticle

Prakalapakorn, Sasapin G. ; Vickers, Laura A. ; Estrada, Rolando ; Freedman, Sharon F. ; Tomasi, Carlo ; Farsiu, Sina ; Wallace, David K. / Using an image fusion methodology to improve efficiency and traceability of posterior pole vessel analysis by ROPtool. In: Open Ophthalmology Journal. 2017 ; Vol. 11. pp. 143-151.
@article{24d2882168af449698bea69ffebf4076,
title = "Using an image fusion methodology to improve efficiency and traceability of posterior pole vessel analysis by ROPtool",
abstract = "Background: The diagnosis of plus disease in retinopathy of prematurity (ROP) largely determines the need for treatment; however, this diagnosis is subjective. To make the diagnosis of plus disease more objective, semi-automated computer programs (e.g. ROPtool) have been created to quantify vascular dilation and tortuosity. ROPtool can accurately analyze blood vessels only in images with very good quality, but many still images captured by indirect ophthalmoscopy have insufficient image quality for ROPtool analysis. Purpose: To evaluate the ability of an image fusion methodology (robust mosaicing) to increase the efficiency and traceability of posterior pole vessel analysis by ROPtool. Materials and Methodology: We retrospectively reviewed video indirect ophthalmoscopy images acquired during routine ROP examinations and selected the best unenhanced still image from the video for each infant. Robust mosaicing was used to create an enhanced mosaic image from the same video for each eye. We evaluated the time required for ROPtool analysis as well as ROPtool’s ability to analyze vessels in enhanced vs. unenhanced images. Results: We included 39 eyes of 39 infants. ROPtool analysis was faster (125 vs. 152 seconds; p=0.02) in enhanced vs. unenhanced images, respectively. ROPtool was able to trace retinal vessels in more quadrants (143/156, 92{\%} vs 115/156, 74{\%}; p=0.16) in enhanced mosaic vs. unenhanced still images, respectively and in more overall (38/39, 97{\%} vs. 34/39, 87{\%}; p=0.07) enhanced mosaic vs. unenhanced still images, respectively. Conclusion: Retinal image enhancement using robust mosaicing advances efforts to automate grading of posterior pole disease in ROP.",
keywords = "Image analysis, Retinopathy of prematurity, ROPtool, Vessel analysis",
author = "Prakalapakorn, {Sasapin G.} and Vickers, {Laura A.} and Rolando Estrada and Freedman, {Sharon F.} and Carlo Tomasi and Sina Farsiu and Wallace, {David K.}",
year = "2017",
month = "6",
day = "1",
doi = "10.2174/1874364101711010143",
language = "English (US)",
volume = "11",
pages = "143--151",
journal = "Open Ophthalmology Journal",
issn = "1874-3641",
publisher = "Bentham Science Publishers B.V.",

}

TY - JOUR

T1 - Using an image fusion methodology to improve efficiency and traceability of posterior pole vessel analysis by ROPtool

AU - Prakalapakorn, Sasapin G.

AU - Vickers, Laura A.

AU - Estrada, Rolando

AU - Freedman, Sharon F.

AU - Tomasi, Carlo

AU - Farsiu, Sina

AU - Wallace, David K.

PY - 2017/6/1

Y1 - 2017/6/1

N2 - Background: The diagnosis of plus disease in retinopathy of prematurity (ROP) largely determines the need for treatment; however, this diagnosis is subjective. To make the diagnosis of plus disease more objective, semi-automated computer programs (e.g. ROPtool) have been created to quantify vascular dilation and tortuosity. ROPtool can accurately analyze blood vessels only in images with very good quality, but many still images captured by indirect ophthalmoscopy have insufficient image quality for ROPtool analysis. Purpose: To evaluate the ability of an image fusion methodology (robust mosaicing) to increase the efficiency and traceability of posterior pole vessel analysis by ROPtool. Materials and Methodology: We retrospectively reviewed video indirect ophthalmoscopy images acquired during routine ROP examinations and selected the best unenhanced still image from the video for each infant. Robust mosaicing was used to create an enhanced mosaic image from the same video for each eye. We evaluated the time required for ROPtool analysis as well as ROPtool’s ability to analyze vessels in enhanced vs. unenhanced images. Results: We included 39 eyes of 39 infants. ROPtool analysis was faster (125 vs. 152 seconds; p=0.02) in enhanced vs. unenhanced images, respectively. ROPtool was able to trace retinal vessels in more quadrants (143/156, 92% vs 115/156, 74%; p=0.16) in enhanced mosaic vs. unenhanced still images, respectively and in more overall (38/39, 97% vs. 34/39, 87%; p=0.07) enhanced mosaic vs. unenhanced still images, respectively. Conclusion: Retinal image enhancement using robust mosaicing advances efforts to automate grading of posterior pole disease in ROP.

AB - Background: The diagnosis of plus disease in retinopathy of prematurity (ROP) largely determines the need for treatment; however, this diagnosis is subjective. To make the diagnosis of plus disease more objective, semi-automated computer programs (e.g. ROPtool) have been created to quantify vascular dilation and tortuosity. ROPtool can accurately analyze blood vessels only in images with very good quality, but many still images captured by indirect ophthalmoscopy have insufficient image quality for ROPtool analysis. Purpose: To evaluate the ability of an image fusion methodology (robust mosaicing) to increase the efficiency and traceability of posterior pole vessel analysis by ROPtool. Materials and Methodology: We retrospectively reviewed video indirect ophthalmoscopy images acquired during routine ROP examinations and selected the best unenhanced still image from the video for each infant. Robust mosaicing was used to create an enhanced mosaic image from the same video for each eye. We evaluated the time required for ROPtool analysis as well as ROPtool’s ability to analyze vessels in enhanced vs. unenhanced images. Results: We included 39 eyes of 39 infants. ROPtool analysis was faster (125 vs. 152 seconds; p=0.02) in enhanced vs. unenhanced images, respectively. ROPtool was able to trace retinal vessels in more quadrants (143/156, 92% vs 115/156, 74%; p=0.16) in enhanced mosaic vs. unenhanced still images, respectively and in more overall (38/39, 97% vs. 34/39, 87%; p=0.07) enhanced mosaic vs. unenhanced still images, respectively. Conclusion: Retinal image enhancement using robust mosaicing advances efforts to automate grading of posterior pole disease in ROP.

KW - Image analysis

KW - Retinopathy of prematurity

KW - ROPtool

KW - Vessel analysis

UR - http://www.scopus.com/inward/record.url?scp=85027149195&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027149195&partnerID=8YFLogxK

U2 - 10.2174/1874364101711010143

DO - 10.2174/1874364101711010143

M3 - Article

VL - 11

SP - 143

EP - 151

JO - Open Ophthalmology Journal

JF - Open Ophthalmology Journal

SN - 1874-3641

ER -