Deep Learning for Image Quality Assessment of Fundus Images in Retinopathy of Prematurity

Aaron S. Coyner, Ryan Swan, James M. Brown, Jayashree Kalpathy-Cramer, Sang Jin Kim, John Campbell, Karyn E. Jonas, Susan Ostmo, R. V.Paul Chan, Michael Chiang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Accurate image-based medical diagnosis relies upon adequate image quality and clarity. This has important implications for clinical diagnosis, and for emerging methods such as telemedicine and computer-based image analysis. In this study, we trained a convolutional neural network (CNN) to automatically assess the quality of retinal fundus images in a representative ophthalmic disease, retinopathy of prematurity (ROP). 6,043 wide-angle fundus images were collected from preterm infants during routine ROP screening examinations. Images were assessed by clinical experts for quality regarding ability to diagnose ROP accurately, and were labeled "acceptable" or "not acceptable." The CNN training, validation and test sets consisted of 2,770 images, 200 images, and 3,073 images, respectively. Test set accuracy was 89.1%, with area under the receiver operating curve equal to 0.964, and area under the precision-recall curve equal to 0.966. Taken together, our CNN shows promise as a useful prescreening method for telemedicine and computer-based image analysis applications. We feel this methodology is generalizable to all clinical domains involving image-based diagnosis.

Original languageEnglish (US)
Pages (from-to)1224-1232
Number of pages9
JournalAMIA ... Annual Symposium proceedings. AMIA Symposium
Volume2018
StatePublished - Jan 1 2018

Fingerprint

Retinopathy of Prematurity
Learning
Telemedicine
Aptitude
Eye Diseases
Premature Infants

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Deep Learning for Image Quality Assessment of Fundus Images in Retinopathy of Prematurity. / Coyner, Aaron S.; Swan, Ryan; Brown, James M.; Kalpathy-Cramer, Jayashree; Kim, Sang Jin; Campbell, John; Jonas, Karyn E.; Ostmo, Susan; Chan, R. V.Paul; Chiang, Michael.

In: AMIA ... Annual Symposium proceedings. AMIA Symposium, Vol. 2018, 01.01.2018, p. 1224-1232.

Research output: Contribution to journalArticle

Coyner, AS, Swan, R, Brown, JM, Kalpathy-Cramer, J, Kim, SJ, Campbell, J, Jonas, KE, Ostmo, S, Chan, RVP & Chiang, M 2018, 'Deep Learning for Image Quality Assessment of Fundus Images in Retinopathy of Prematurity', AMIA ... Annual Symposium proceedings. AMIA Symposium, vol. 2018, pp. 1224-1232.
Coyner, Aaron S. ; Swan, Ryan ; Brown, James M. ; Kalpathy-Cramer, Jayashree ; Kim, Sang Jin ; Campbell, John ; Jonas, Karyn E. ; Ostmo, Susan ; Chan, R. V.Paul ; Chiang, Michael. / Deep Learning for Image Quality Assessment of Fundus Images in Retinopathy of Prematurity. In: AMIA ... Annual Symposium proceedings. AMIA Symposium. 2018 ; Vol. 2018. pp. 1224-1232.
@article{826aee00940a4efba44ec2416f7f44e8,
title = "Deep Learning for Image Quality Assessment of Fundus Images in Retinopathy of Prematurity",
abstract = "Accurate image-based medical diagnosis relies upon adequate image quality and clarity. This has important implications for clinical diagnosis, and for emerging methods such as telemedicine and computer-based image analysis. In this study, we trained a convolutional neural network (CNN) to automatically assess the quality of retinal fundus images in a representative ophthalmic disease, retinopathy of prematurity (ROP). 6,043 wide-angle fundus images were collected from preterm infants during routine ROP screening examinations. Images were assessed by clinical experts for quality regarding ability to diagnose ROP accurately, and were labeled {"}acceptable{"} or {"}not acceptable.{"} The CNN training, validation and test sets consisted of 2,770 images, 200 images, and 3,073 images, respectively. Test set accuracy was 89.1{\%}, with area under the receiver operating curve equal to 0.964, and area under the precision-recall curve equal to 0.966. Taken together, our CNN shows promise as a useful prescreening method for telemedicine and computer-based image analysis applications. We feel this methodology is generalizable to all clinical domains involving image-based diagnosis.",
author = "Coyner, {Aaron S.} and Ryan Swan and Brown, {James M.} and Jayashree Kalpathy-Cramer and Kim, {Sang Jin} and John Campbell and Jonas, {Karyn E.} and Susan Ostmo and Chan, {R. V.Paul} and Michael Chiang",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
volume = "2018",
pages = "1224--1232",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - Deep Learning for Image Quality Assessment of Fundus Images in Retinopathy of Prematurity

AU - Coyner, Aaron S.

AU - Swan, Ryan

AU - Brown, James M.

AU - Kalpathy-Cramer, Jayashree

AU - Kim, Sang Jin

AU - Campbell, John

AU - Jonas, Karyn E.

AU - Ostmo, Susan

AU - Chan, R. V.Paul

AU - Chiang, Michael

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Accurate image-based medical diagnosis relies upon adequate image quality and clarity. This has important implications for clinical diagnosis, and for emerging methods such as telemedicine and computer-based image analysis. In this study, we trained a convolutional neural network (CNN) to automatically assess the quality of retinal fundus images in a representative ophthalmic disease, retinopathy of prematurity (ROP). 6,043 wide-angle fundus images were collected from preterm infants during routine ROP screening examinations. Images were assessed by clinical experts for quality regarding ability to diagnose ROP accurately, and were labeled "acceptable" or "not acceptable." The CNN training, validation and test sets consisted of 2,770 images, 200 images, and 3,073 images, respectively. Test set accuracy was 89.1%, with area under the receiver operating curve equal to 0.964, and area under the precision-recall curve equal to 0.966. Taken together, our CNN shows promise as a useful prescreening method for telemedicine and computer-based image analysis applications. We feel this methodology is generalizable to all clinical domains involving image-based diagnosis.

AB - Accurate image-based medical diagnosis relies upon adequate image quality and clarity. This has important implications for clinical diagnosis, and for emerging methods such as telemedicine and computer-based image analysis. In this study, we trained a convolutional neural network (CNN) to automatically assess the quality of retinal fundus images in a representative ophthalmic disease, retinopathy of prematurity (ROP). 6,043 wide-angle fundus images were collected from preterm infants during routine ROP screening examinations. Images were assessed by clinical experts for quality regarding ability to diagnose ROP accurately, and were labeled "acceptable" or "not acceptable." The CNN training, validation and test sets consisted of 2,770 images, 200 images, and 3,073 images, respectively. Test set accuracy was 89.1%, with area under the receiver operating curve equal to 0.964, and area under the precision-recall curve equal to 0.966. Taken together, our CNN shows promise as a useful prescreening method for telemedicine and computer-based image analysis applications. We feel this methodology is generalizable to all clinical domains involving image-based diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=85062380580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062380580&partnerID=8YFLogxK

M3 - Article

C2 - 30815164

AN - SCOPUS:85062380580

VL - 2018

SP - 1224

EP - 1232

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1559-4076

ER -