Validating deep learning inference during chest X-ray classification for COVID-19 screening

Abstract The new coronavirus unleashed a worldwide pandemic in early 2020, and a fatality rate several times that of the flu. As the number of infections soared, and capabilities for testing lagged behind, chest X-ray (CXR) imaging became more relevant in the early diagnosis and treatment planning f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Robbie Sadre, Baskaran Sundaram, Sharmila Majumdar, Daniela Ushizima
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/3246dbb682e345e39da31ce624579942
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3246dbb682e345e39da31ce624579942
record_format	dspace
spelling	oai:doaj.org-article:3246dbb682e345e39da31ce6245799422021-12-02T18:51:01ZValidating deep learning inference during chest X-ray classification for COVID-19 screening10.1038/s41598-021-95561-y2045-2322https://doaj.org/article/3246dbb682e345e39da31ce6245799422021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-95561-yhttps://doaj.org/toc/2045-2322Abstract The new coronavirus unleashed a worldwide pandemic in early 2020, and a fatality rate several times that of the flu. As the number of infections soared, and capabilities for testing lagged behind, chest X-ray (CXR) imaging became more relevant in the early diagnosis and treatment planning for patients with suspected or confirmed COVID-19 infection. In a few weeks, proposed new methods for lung screening using deep learning rapidly appeared, while quality assurance discussions lagged behind. This paper proposes a set of protocols to validate deep learning algorithms, including our ROI Hide-and-Seek protocol, which emphasizes or hides key regions of interest from CXR data. Our protocol allows assessing the classification performance for anomaly detection and its correlation to radiological signatures, an important issue overlooked in several deep learning approaches proposed so far. By running a set of systematic tests over CXR representations using public image datasets, we demonstrate the weaknesses of current techniques and offer perspectives on the advantages and limitations of automated radiography analysis when using heterogeneous data sources.Robbie SadreBaskaran SundaramSharmila MajumdarDaniela UshizimaNature 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 Robbie Sadre Baskaran Sundaram Sharmila Majumdar Daniela Ushizima Validating deep learning inference during chest X-ray classification for COVID-19 screening
description	Abstract The new coronavirus unleashed a worldwide pandemic in early 2020, and a fatality rate several times that of the flu. As the number of infections soared, and capabilities for testing lagged behind, chest X-ray (CXR) imaging became more relevant in the early diagnosis and treatment planning for patients with suspected or confirmed COVID-19 infection. In a few weeks, proposed new methods for lung screening using deep learning rapidly appeared, while quality assurance discussions lagged behind. This paper proposes a set of protocols to validate deep learning algorithms, including our ROI Hide-and-Seek protocol, which emphasizes or hides key regions of interest from CXR data. Our protocol allows assessing the classification performance for anomaly detection and its correlation to radiological signatures, an important issue overlooked in several deep learning approaches proposed so far. By running a set of systematic tests over CXR representations using public image datasets, we demonstrate the weaknesses of current techniques and offer perspectives on the advantages and limitations of automated radiography analysis when using heterogeneous data sources.
format	article
author	Robbie Sadre Baskaran Sundaram Sharmila Majumdar Daniela Ushizima
author_facet	Robbie Sadre Baskaran Sundaram Sharmila Majumdar Daniela Ushizima
author_sort	Robbie Sadre
title	Validating deep learning inference during chest X-ray classification for COVID-19 screening
title_short	Validating deep learning inference during chest X-ray classification for COVID-19 screening
title_full	Validating deep learning inference during chest X-ray classification for COVID-19 screening
title_fullStr	Validating deep learning inference during chest X-ray classification for COVID-19 screening
title_full_unstemmed	Validating deep learning inference during chest X-ray classification for COVID-19 screening
title_sort	validating deep learning inference during chest x-ray classification for covid-19 screening
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/3246dbb682e345e39da31ce624579942
work_keys_str_mv	AT robbiesadre validatingdeeplearninginferenceduringchestxrayclassificationforcovid19screening AT baskaransundaram validatingdeeplearninginferenceduringchestxrayclassificationforcovid19screening AT sharmilamajumdar validatingdeeplearninginferenceduringchestxrayclassificationforcovid19screening AT danielaushizima validatingdeeplearninginferenceduringchestxrayclassificationforcovid19screening
_version_	1718377438324457472

Validating deep learning inference during chest X-ray classification for COVID-19 screening

Ejemplares similares