Literature DB >> 31044738

Automated Fundus Image Quality Assessment in Retinopathy of Prematurity Using Deep Convolutional Neural Networks.

Aaron S Coyner1, Ryan Swan1, J Peter Campbell2, Susan Ostmo2, James M Brown3, Jayashree Kalpathy-Cramer4, Sang Jin Kim5, Karyn E Jonas6, R V Paul Chan6, Michael F Chiang7.   

Abstract

PURPOSE: Accurate image-based ophthalmic diagnosis relies on fundus image clarity. This has important implications for the quality of ophthalmic diagnoses and for emerging methods such as telemedicine and computer-based image analysis. The purpose of this study was to implement a deep convolutional neural network (CNN) for automated assessment of fundus image quality in retinopathy of prematurity (ROP).
DESIGN: Experimental study. PARTICIPANTS: Retinal fundus images were collected from preterm infants during routine ROP screenings.
METHODS: Six thousand one hundred thirty-nine retinal fundus images were collected from 9 academic institutions. Each image was graded for quality (acceptable quality [AQ], possibly acceptable quality [PAQ], or not acceptable quality [NAQ]) by 3 independent experts. Quality was defined as the ability to assess an image confidently for the presence of ROP. Of the 6139 images, NAQ, PAQ, and AQ images represented 5.6%, 43.6%, and 50.8% of the image set, respectively. Because of low representation of NAQ images in the data set, images labeled NAQ were grouped into the PAQ category, and a binary CNN classifier was trained using 5-fold cross-validation on 4000 images. A test set of 2109 images was held out for final model evaluation. Additionally, 30 images were ranked from worst to best quality by 6 experts via pairwise comparisons, and the CNN's ability to rank quality, regardless of quality classification, was assessed. MAIN OUTCOME MEASURES: The CNN performance was evaluated using area under the receiver operating characteristic curve (AUC). A Spearman's rank correlation was calculated to evaluate the overall ability of the CNN to rank images from worst to best quality as compared with experts.
RESULTS: The mean AUC for 5-fold cross-validation was 0.958 (standard deviation, 0.005) for the diagnosis of AQ versus PAQ images. The AUC was 0.965 for the test set. The Spearman's rank correlation coefficient on the set of 30 images was 0.90 as compared with the overall expert consensus ranking.
CONCLUSIONS: This model accurately assessed retinal fundus image quality in a comparable manner with that of experts. This fully automated model has potential for application in clinical settings, telemedicine, and computer-based image analysis in ROP and for generalizability to other ophthalmic diseases.
Copyright © 2019 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved.

Entities:  

Mesh:

Year:  2019        PMID: 31044738      PMCID: PMC6501831          DOI: 10.1016/j.oret.2019.01.015

Source DB:  PubMed          Journal:  Ophthalmol Retina        ISSN: 2468-6530


  34 in total

1.  A methodologic issue for ophthalmic telemedicine: image quality and its effect on diagnostic accuracy and confidence.

Authors:  R Briggs; J E Bailey; C Eddy; I Sun
Journal:  J Am Optom Assoc       Date:  1998-09

2.  Quality evaluation of digital fundus images through combined measures.

Authors:  Diana Veiga; Carla Pereira; Manuel Ferreira; Luís Gonçalves; João Monteiro
Journal:  J Med Imaging (Bellingham)       Date:  2014-04-23

3.  PROPELLER technique to improve image quality of MRI of the shoulder.

Authors:  Tobias J Dietrich; Erika J Ulbrich; Marco Zanetti; Sandro F Fucentese; Christian W A Pfirrmann
Journal:  AJR Am J Roentgenol       Date:  2011-12       Impact factor: 3.959

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

Authors:  Aaron S Coyner; Ryan Swan; James M Brown; Jayashree Kalpathy-Cramer; Sang Jin Kim; J Peter Campbell; Karyn E Jonas; Susan Ostmo; R V Paul Chan; Michael F Chiang
Journal:  AMIA Annu Symp Proc       Date:  2018-12-05

5.  Quantitative brain magnetic resonance imaging in attention-deficit hyperactivity disorder.

Authors:  F X Castellanos; J N Giedd; W L Marsh; S D Hamburger; A C Vaituzis; D P Dickstein; S E Sarfatti; Y C Vauss; J W Snell; N Lange; D Kaysen; A L Krain; G F Ritchie; J C Rajapakse; J L Rapoport
Journal:  Arch Gen Psychiatry       Date:  1996-07

6.  Effects on image quality of a 2D antiscatter grid in x-ray digital breast tomosynthesis: Initial experience using the dual modality (x-ray and molecular) breast tomosynthesis scanner.

Authors:  Tushita Patel; Heather Peppard; Mark B Williams
Journal:  Med Phys       Date:  2016-04       Impact factor: 4.071

7.  Human Visual System-Based Fundus Image Quality Assessment of Portable Fundus Camera Photographs.

Authors:  Shaoze Wang; Kai Jin; Haitong Lu; Chuming Cheng; Juan Ye; Dahong Qian
Journal:  IEEE Trans Med Imaging       Date:  2015-12-08       Impact factor: 10.048

8.  Methods for quantitative image quality evaluation of MRI parallel reconstructions: detection and perceptual difference model.

Authors:  Yuhao Jiang; Donglai Huo; David L Wilson
Journal:  Magn Reson Imaging       Date:  2007-02-26       Impact factor: 2.546

9.  Retinopathy of prematurity blindness worldwide: phenotypes in the third epidemic.

Authors:  Graham E Quinn
Journal:  Eye Brain       Date:  2016-05-19

10.  Automatic no-reference image quality assessment.

Authors:  Hongjun Li; Wei Hu; Zi-Neng Xu
Journal:  Springerplus       Date:  2016-07-16
View more
  15 in total

Review 1.  Imaging in Retinopathy of Prematurity.

Authors:  N Valikodath; E Cole; M F Chiang; J P Campbell; R V P Chan
Journal:  Asia Pac J Ophthalmol (Phila)       Date:  2019 Mar-Apr

2.  Age-related Macular Degeneration: Nutrition, Genes and Deep Learning-The LXXVI Edward Jackson Memorial Lecture.

Authors:  Emily Y Chew
Journal:  Am J Ophthalmol       Date:  2020-06-20       Impact factor: 5.258

3.  Demystifying the Jargon: The Bridge between Ophthalmology and Artificial Intelligence.

Authors:  Aaron S Coyner; J Peter Campbell; Michael F Chiang
Journal:  Ophthalmol Retina       Date:  2019-04

4.  Evaluation of artificial intelligence-based telemedicine screening for retinopathy of prematurity.

Authors:  Miles F Greenwald; Ian D Danford; Malika Shahrawat; Susan Ostmo; James Brown; Jayashree Kalpathy-Cramer; Kacy Bradshaw; Robert Schelonka; Howard S Cohen; R V Paul Chan; Michael F Chiang; J Peter Campbell
Journal:  J AAPOS       Date:  2020-04-11       Impact factor: 1.220

5.  Beyond Performance Metrics: Automatic Deep Learning Retinal OCT Analysis Reproduces Clinical Trial Outcome.

Authors:  Jessica Loo; Traci E Clemons; Emily Y Chew; Martin Friedlander; Glenn J Jaffe; Sina Farsiu
Journal:  Ophthalmology       Date:  2019-12-23       Impact factor: 12.079

Review 6.  Artificial intelligence for retinopathy of prematurity.

Authors:  Rebekah H Gensure; Michael F Chiang; John P Campbell
Journal:  Curr Opin Ophthalmol       Date:  2020-09       Impact factor: 3.761

Review 7.  Applications of interpretability in deep learning models for ophthalmology.

Authors:  Adam M Hanif; Sara Beqiri; Pearse A Keane; J Peter Campbell
Journal:  Curr Opin Ophthalmol       Date:  2021-09-01       Impact factor: 4.299

Review 8.  Introduction to Machine Learning, Neural Networks, and Deep Learning.

Authors:  Rene Y Choi; Aaron S Coyner; Jayashree Kalpathy-Cramer; Michael F Chiang; J Peter Campbell
Journal:  Transl Vis Sci Technol       Date:  2020-02-27       Impact factor: 3.283

9.  Impact of Artificial Intelligence on Medical Education in Ophthalmology.

Authors:  Nita G Valikodath; Emily Cole; Daniel S W Ting; J Peter Campbell; Louis R Pasquale; Michael F Chiang; R V Paul Chan
Journal:  Transl Vis Sci Technol       Date:  2021-06-01       Impact factor: 3.283

10.  Evaluation of a Deep Learning-Derived Quantitative Retinopathy of Prematurity Severity Scale.

Authors:  J Peter Campbell; Sang Jin Kim; James M Brown; Susan Ostmo; R V Paul Chan; Jayashree Kalpathy-Cramer; Michael F Chiang
Journal:  Ophthalmology       Date:  2020-10-27       Impact factor: 14.277

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.