Cargando…

Application of a deep convolutional neural network in the diagnosis of neonatal ocular fundus hemorrhage

There is a disparity between the increasing application of digital retinal imaging to neonatal ocular screening and slowly growing number of pediatric ophthalmologists. Assistant tools that can automatically detect ocular disorders may be needed. In present study, we develop a deep convolutional neu...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Binbin, Xiao, Li, Liu, Yang, Wang, Jing, Liu, Beihong, Li, Tengyan, Ma, Xu, Zhao, Yi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Portland Press Ltd. 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6435455/
https://www.ncbi.nlm.nih.gov/pubmed/30333258
http://dx.doi.org/10.1042/BSR20180497
_version_ 1783406633967157248
author Wang, Binbin
Xiao, Li
Liu, Yang
Wang, Jing
Liu, Beihong
Li, Tengyan
Ma, Xu
Zhao, Yi
author_facet Wang, Binbin
Xiao, Li
Liu, Yang
Wang, Jing
Liu, Beihong
Li, Tengyan
Ma, Xu
Zhao, Yi
author_sort Wang, Binbin
collection PubMed
description There is a disparity between the increasing application of digital retinal imaging to neonatal ocular screening and slowly growing number of pediatric ophthalmologists. Assistant tools that can automatically detect ocular disorders may be needed. In present study, we develop a deep convolutional neural network (DCNN) for automated classification and grading of retinal hemorrhage. We used 48,996 digital fundus images from 3770 newborns with retinal hemorrhage of different severity (grade 1, 2 and 3) and normal controls from a large cross-sectional investigation in China. The DCNN was trained for automated grading of retinal hemorrhage (multiclass classification problem: hemorrhage-free and grades 1, 2 and 3) and then validated for its performance level. The DCNN yielded an accuracy of 97.85 to 99.96%, and the area under the receiver operating characteristic curve was 0.989–1.000 in the binary classification of neonatal retinal hemorrhage (i.e., one classification vs. the others). The overall accuracy with regard to the multiclass classification problem was 97.44%. This is the first study to show that a DCNN can detect and grade neonatal retinal hemorrhage at high performance levels. Artificial intelligence will play more positive roles in ocular healthcare of newborns and children.
format Online
Article
Text
id pubmed-6435455
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Portland Press Ltd.
record_format MEDLINE/PubMed
spelling pubmed-64354552019-04-12 Application of a deep convolutional neural network in the diagnosis of neonatal ocular fundus hemorrhage Wang, Binbin Xiao, Li Liu, Yang Wang, Jing Liu, Beihong Li, Tengyan Ma, Xu Zhao, Yi Biosci Rep Research Articles There is a disparity between the increasing application of digital retinal imaging to neonatal ocular screening and slowly growing number of pediatric ophthalmologists. Assistant tools that can automatically detect ocular disorders may be needed. In present study, we develop a deep convolutional neural network (DCNN) for automated classification and grading of retinal hemorrhage. We used 48,996 digital fundus images from 3770 newborns with retinal hemorrhage of different severity (grade 1, 2 and 3) and normal controls from a large cross-sectional investigation in China. The DCNN was trained for automated grading of retinal hemorrhage (multiclass classification problem: hemorrhage-free and grades 1, 2 and 3) and then validated for its performance level. The DCNN yielded an accuracy of 97.85 to 99.96%, and the area under the receiver operating characteristic curve was 0.989–1.000 in the binary classification of neonatal retinal hemorrhage (i.e., one classification vs. the others). The overall accuracy with regard to the multiclass classification problem was 97.44%. This is the first study to show that a DCNN can detect and grade neonatal retinal hemorrhage at high performance levels. Artificial intelligence will play more positive roles in ocular healthcare of newborns and children. Portland Press Ltd. 2018-12-07 /pmc/articles/PMC6435455/ /pubmed/30333258 http://dx.doi.org/10.1042/BSR20180497 Text en © 2018 The Author(s). http://creativecommons.org/licenses/by/4.0/This is an open access article published by Portland Press Limited on behalf of the Biochemical Society and distributed under the Creative Commons Attribution License 4.0 (CC BY) (http://creativecommons.org/licenses/by/4.0/) .
spellingShingle Research Articles
Wang, Binbin
Xiao, Li
Liu, Yang
Wang, Jing
Liu, Beihong
Li, Tengyan
Ma, Xu
Zhao, Yi
Application of a deep convolutional neural network in the diagnosis of neonatal ocular fundus hemorrhage
title Application of a deep convolutional neural network in the diagnosis of neonatal ocular fundus hemorrhage
title_full Application of a deep convolutional neural network in the diagnosis of neonatal ocular fundus hemorrhage
title_fullStr Application of a deep convolutional neural network in the diagnosis of neonatal ocular fundus hemorrhage
title_full_unstemmed Application of a deep convolutional neural network in the diagnosis of neonatal ocular fundus hemorrhage
title_short Application of a deep convolutional neural network in the diagnosis of neonatal ocular fundus hemorrhage
title_sort application of a deep convolutional neural network in the diagnosis of neonatal ocular fundus hemorrhage
topic Research Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6435455/
https://www.ncbi.nlm.nih.gov/pubmed/30333258
http://dx.doi.org/10.1042/BSR20180497
work_keys_str_mv AT wangbinbin applicationofadeepconvolutionalneuralnetworkinthediagnosisofneonatalocularfundushemorrhage
AT xiaoli applicationofadeepconvolutionalneuralnetworkinthediagnosisofneonatalocularfundushemorrhage
AT liuyang applicationofadeepconvolutionalneuralnetworkinthediagnosisofneonatalocularfundushemorrhage
AT wangjing applicationofadeepconvolutionalneuralnetworkinthediagnosisofneonatalocularfundushemorrhage
AT liubeihong applicationofadeepconvolutionalneuralnetworkinthediagnosisofneonatalocularfundushemorrhage
AT litengyan applicationofadeepconvolutionalneuralnetworkinthediagnosisofneonatalocularfundushemorrhage
AT maxu applicationofadeepconvolutionalneuralnetworkinthediagnosisofneonatalocularfundushemorrhage
AT zhaoyi applicationofadeepconvolutionalneuralnetworkinthediagnosisofneonatalocularfundushemorrhage