Toward understanding COVID-19 pneumonia: a deep-learning-based approach for severity analysis and monitoring the disease

Abstract We report a new approach using artificial intelligence (AI) to study and classify the severity of COVID-19 using 1208 chest X-rays (CXRs) of 396 COVID-19 patients obtained through the course of the disease at Emory Healthcare affiliated hospitals (Atlanta, GA, USA). Using a two-stage transf...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mohammadreza Zandehshahvar, Marly van Assen, Hossein Maleki, Yashar Kiarashi, Carlo N. De Cecco, Ali Adibi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/fc928e9f3dcc40d7a9ded637eb102963
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fc928e9f3dcc40d7a9ded637eb102963
record_format	dspace
spelling	oai:doaj.org-article:fc928e9f3dcc40d7a9ded637eb1029632021-12-02T14:47:31ZToward understanding COVID-19 pneumonia: a deep-learning-based approach for severity analysis and monitoring the disease10.1038/s41598-021-90411-32045-2322https://doaj.org/article/fc928e9f3dcc40d7a9ded637eb1029632021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-90411-3https://doaj.org/toc/2045-2322Abstract We report a new approach using artificial intelligence (AI) to study and classify the severity of COVID-19 using 1208 chest X-rays (CXRs) of 396 COVID-19 patients obtained through the course of the disease at Emory Healthcare affiliated hospitals (Atlanta, GA, USA). Using a two-stage transfer learning technique to train a convolutional neural network (CNN), we show that the algorithm is able to classify four classes of disease severity (normal, mild, moderate, and severe) with the average Area Under the Curve (AUC) of 0.93. In addition, we show that the outputs of different layers of the CNN under dominant filters provide valuable insight about the subtle patterns in the CXRs, which can improve the accuracy in the reading of CXRs by a radiologist. Finally, we show that our approach can be used for studying the disease progression in a single patient and its influencing factors. The results suggest that our technique can form the foundation of a more concrete clinical model to predict the evolution of COVID-19 severity and the efficacy of different treatments for each patient through using CXRs and clinical data in the early stages of the disease. This use of AI to assess the severity and possibly predicting the future stages of the disease early on, will be essential in dealing with the upcoming waves of COVID-19 and optimizing resource allocation and treatment.Mohammadreza ZandehshahvarMarly van AssenHossein MalekiYashar KiarashiCarlo N. De CeccoAli AdibiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Mohammadreza Zandehshahvar Marly van Assen Hossein Maleki Yashar Kiarashi Carlo N. De Cecco Ali Adibi Toward understanding COVID-19 pneumonia: a deep-learning-based approach for severity analysis and monitoring the disease
description	Abstract We report a new approach using artificial intelligence (AI) to study and classify the severity of COVID-19 using 1208 chest X-rays (CXRs) of 396 COVID-19 patients obtained through the course of the disease at Emory Healthcare affiliated hospitals (Atlanta, GA, USA). Using a two-stage transfer learning technique to train a convolutional neural network (CNN), we show that the algorithm is able to classify four classes of disease severity (normal, mild, moderate, and severe) with the average Area Under the Curve (AUC) of 0.93. In addition, we show that the outputs of different layers of the CNN under dominant filters provide valuable insight about the subtle patterns in the CXRs, which can improve the accuracy in the reading of CXRs by a radiologist. Finally, we show that our approach can be used for studying the disease progression in a single patient and its influencing factors. The results suggest that our technique can form the foundation of a more concrete clinical model to predict the evolution of COVID-19 severity and the efficacy of different treatments for each patient through using CXRs and clinical data in the early stages of the disease. This use of AI to assess the severity and possibly predicting the future stages of the disease early on, will be essential in dealing with the upcoming waves of COVID-19 and optimizing resource allocation and treatment.
format	article
author	Mohammadreza Zandehshahvar Marly van Assen Hossein Maleki Yashar Kiarashi Carlo N. De Cecco Ali Adibi
author_facet	Mohammadreza Zandehshahvar Marly van Assen Hossein Maleki Yashar Kiarashi Carlo N. De Cecco Ali Adibi
author_sort	Mohammadreza Zandehshahvar
title	Toward understanding COVID-19 pneumonia: a deep-learning-based approach for severity analysis and monitoring the disease
title_short	Toward understanding COVID-19 pneumonia: a deep-learning-based approach for severity analysis and monitoring the disease
title_full	Toward understanding COVID-19 pneumonia: a deep-learning-based approach for severity analysis and monitoring the disease
title_fullStr	Toward understanding COVID-19 pneumonia: a deep-learning-based approach for severity analysis and monitoring the disease
title_full_unstemmed	Toward understanding COVID-19 pneumonia: a deep-learning-based approach for severity analysis and monitoring the disease
title_sort	toward understanding covid-19 pneumonia: a deep-learning-based approach for severity analysis and monitoring the disease
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/fc928e9f3dcc40d7a9ded637eb102963
work_keys_str_mv	AT mohammadrezazandehshahvar towardunderstandingcovid19pneumoniaadeeplearningbasedapproachforseverityanalysisandmonitoringthedisease AT marlyvanassen towardunderstandingcovid19pneumoniaadeeplearningbasedapproachforseverityanalysisandmonitoringthedisease AT hosseinmaleki towardunderstandingcovid19pneumoniaadeeplearningbasedapproachforseverityanalysisandmonitoringthedisease AT yasharkiarashi towardunderstandingcovid19pneumoniaadeeplearningbasedapproachforseverityanalysisandmonitoringthedisease AT carlondececco towardunderstandingcovid19pneumoniaadeeplearningbasedapproachforseverityanalysisandmonitoringthedisease AT aliadibi towardunderstandingcovid19pneumoniaadeeplearningbasedapproachforseverityanalysisandmonitoringthedisease
_version_	1718389546761060352

Toward understanding COVID-19 pneumonia: a deep-learning-based approach for severity analysis and monitoring the disease

Ejemplares similares