Deep learning for classification of pediatric chest radiographs by WHO's standardized methodology.

<h4>Background</h4>The World Health Organization (WHO)-defined radiological pneumonia is a preferred endpoint in pneumococcal vaccine efficacy and effectiveness studies in children. Automating the WHO methodology may support more widespread application of this endpoint.<h4>Methods&...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yiyun Chen, Craig S Roberts, Wanmei Ou, Tanaz Petigara, Gregory V Goldmacher, Nicholas Fancourt, Maria Deloria Knoll
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/d3aeeb4c0d1d4d3785f5d9e10f7bb335
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d3aeeb4c0d1d4d3785f5d9e10f7bb335
record_format	dspace
spelling	oai:doaj.org-article:d3aeeb4c0d1d4d3785f5d9e10f7bb3352021-12-02T20:10:18ZDeep learning for classification of pediatric chest radiographs by WHO's standardized methodology.1932-620310.1371/journal.pone.0253239https://doaj.org/article/d3aeeb4c0d1d4d3785f5d9e10f7bb3352021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0253239https://doaj.org/toc/1932-6203<h4>Background</h4>The World Health Organization (WHO)-defined radiological pneumonia is a preferred endpoint in pneumococcal vaccine efficacy and effectiveness studies in children. Automating the WHO methodology may support more widespread application of this endpoint.<h4>Methods</h4>We trained a deep learning model to classify pneumonia CXRs in children using the World Health Organization (WHO)'s standardized methodology. The model was pretrained on CheXpert, a dataset containing 224,316 adult CXRs, and fine-tuned on PERCH, a pediatric dataset containing 4,172 CXRs. The model was then tested on two pediatric CXR datasets released by WHO. We also compared the model's performance to that of radiologists and pediatricians.<h4>Results</h4>The average area under the receiver operating characteristic curve (AUC) for primary endpoint pneumonia (PEP) across 10-fold validation of PERCH images was 0.928; average AUC after testing on WHO images was 0.977. The model's classification performance was better on test images with high inter-observer agreement; however, the model still outperformed human assessments in AUC and precision-recall spaces on low agreement images.<h4>Conclusion</h4>A deep learning model can classify pneumonia CXR images in children at a performance comparable to human readers. Our method lays a strong foundation for the potential inclusion of computer-aided readings of pediatric CXRs in vaccine trials and epidemiology studies.Yiyun ChenCraig S RobertsWanmei OuTanaz PetigaraGregory V GoldmacherNicholas FancourtMaria Deloria KnollPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 6, p e0253239 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Yiyun Chen Craig S Roberts Wanmei Ou Tanaz Petigara Gregory V Goldmacher Nicholas Fancourt Maria Deloria Knoll Deep learning for classification of pediatric chest radiographs by WHO's standardized methodology.
description	<h4>Background</h4>The World Health Organization (WHO)-defined radiological pneumonia is a preferred endpoint in pneumococcal vaccine efficacy and effectiveness studies in children. Automating the WHO methodology may support more widespread application of this endpoint.<h4>Methods</h4>We trained a deep learning model to classify pneumonia CXRs in children using the World Health Organization (WHO)'s standardized methodology. The model was pretrained on CheXpert, a dataset containing 224,316 adult CXRs, and fine-tuned on PERCH, a pediatric dataset containing 4,172 CXRs. The model was then tested on two pediatric CXR datasets released by WHO. We also compared the model's performance to that of radiologists and pediatricians.<h4>Results</h4>The average area under the receiver operating characteristic curve (AUC) for primary endpoint pneumonia (PEP) across 10-fold validation of PERCH images was 0.928; average AUC after testing on WHO images was 0.977. The model's classification performance was better on test images with high inter-observer agreement; however, the model still outperformed human assessments in AUC and precision-recall spaces on low agreement images.<h4>Conclusion</h4>A deep learning model can classify pneumonia CXR images in children at a performance comparable to human readers. Our method lays a strong foundation for the potential inclusion of computer-aided readings of pediatric CXRs in vaccine trials and epidemiology studies.
format	article
author	Yiyun Chen Craig S Roberts Wanmei Ou Tanaz Petigara Gregory V Goldmacher Nicholas Fancourt Maria Deloria Knoll
author_facet	Yiyun Chen Craig S Roberts Wanmei Ou Tanaz Petigara Gregory V Goldmacher Nicholas Fancourt Maria Deloria Knoll
author_sort	Yiyun Chen
title	Deep learning for classification of pediatric chest radiographs by WHO's standardized methodology.
title_short	Deep learning for classification of pediatric chest radiographs by WHO's standardized methodology.
title_full	Deep learning for classification of pediatric chest radiographs by WHO's standardized methodology.
title_fullStr	Deep learning for classification of pediatric chest radiographs by WHO's standardized methodology.
title_full_unstemmed	Deep learning for classification of pediatric chest radiographs by WHO's standardized methodology.
title_sort	deep learning for classification of pediatric chest radiographs by who's standardized methodology.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/d3aeeb4c0d1d4d3785f5d9e10f7bb335
work_keys_str_mv	AT yiyunchen deeplearningforclassificationofpediatricchestradiographsbywhosstandardizedmethodology AT craigsroberts deeplearningforclassificationofpediatricchestradiographsbywhosstandardizedmethodology AT wanmeiou deeplearningforclassificationofpediatricchestradiographsbywhosstandardizedmethodology AT tanazpetigara deeplearningforclassificationofpediatricchestradiographsbywhosstandardizedmethodology AT gregoryvgoldmacher deeplearningforclassificationofpediatricchestradiographsbywhosstandardizedmethodology AT nicholasfancourt deeplearningforclassificationofpediatricchestradiographsbywhosstandardizedmethodology AT mariadeloriaknoll deeplearningforclassificationofpediatricchestradiographsbywhosstandardizedmethodology
_version_	1718375027092488192

Deep learning for classification of pediatric chest radiographs by WHO's standardized methodology.

Ejemplares similares