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
SN - 1559-4076
VL - 2018
SP - 1224
EP - 1232
JO - AMIA ... Annual Symposium proceedings. AMIA Symposium
JF - AMIA ... Annual Symposium proceedings. AMIA Symposium
ER -