Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization

Unmasking the decision making process of machine learning models is essential for implementing diagnostic support systems in clinical practice. Here, the authors demonstrate that adversarially trained models can significantly enhance the usability of pathology detection as compared to their standard...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tianyu Han, Sven Nebelung, Federico Pedersoli, Markus Zimmermann, Maximilian Schulze-Hagen, Michael Ho, Christoph Haarburger, Fabian Kiessling, Christiane Kuhl, Volkmar Schulz, Daniel Truhn
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/5746063469c74a20ae5ebc74b05a7231
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5746063469c74a20ae5ebc74b05a7231
record_format	dspace
spelling	oai:doaj.org-article:5746063469c74a20ae5ebc74b05a72312021-12-02T18:37:05ZAdvancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization10.1038/s41467-021-24464-32041-1723https://doaj.org/article/5746063469c74a20ae5ebc74b05a72312021-07-01T00:00:00Zhttps://doi.org/10.1038/s41467-021-24464-3https://doaj.org/toc/2041-1723Unmasking the decision making process of machine learning models is essential for implementing diagnostic support systems in clinical practice. Here, the authors demonstrate that adversarially trained models can significantly enhance the usability of pathology detection as compared to their standard counterparts.Tianyu HanSven NebelungFederico PedersoliMarkus ZimmermannMaximilian Schulze-HagenMichael HoChristoph HaarburgerFabian KiesslingChristiane KuhlVolkmar SchulzDaniel TruhnNature PortfolioarticleScienceQENNature Communications, Vol 12, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Tianyu Han Sven Nebelung Federico Pedersoli Markus Zimmermann Maximilian Schulze-Hagen Michael Ho Christoph Haarburger Fabian Kiessling Christiane Kuhl Volkmar Schulz Daniel Truhn Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
description	Unmasking the decision making process of machine learning models is essential for implementing diagnostic support systems in clinical practice. Here, the authors demonstrate that adversarially trained models can significantly enhance the usability of pathology detection as compared to their standard counterparts.
format	article
author	Tianyu Han Sven Nebelung Federico Pedersoli Markus Zimmermann Maximilian Schulze-Hagen Michael Ho Christoph Haarburger Fabian Kiessling Christiane Kuhl Volkmar Schulz Daniel Truhn
author_facet	Tianyu Han Sven Nebelung Federico Pedersoli Markus Zimmermann Maximilian Schulze-Hagen Michael Ho Christoph Haarburger Fabian Kiessling Christiane Kuhl Volkmar Schulz Daniel Truhn
author_sort	Tianyu Han
title	Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
title_short	Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
title_full	Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
title_fullStr	Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
title_full_unstemmed	Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
title_sort	advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/5746063469c74a20ae5ebc74b05a7231
work_keys_str_mv	AT tianyuhan advancingdiagnosticperformanceandclinicalusabilityofneuralnetworksviaadversarialtraininganddualbatchnormalization AT svennebelung advancingdiagnosticperformanceandclinicalusabilityofneuralnetworksviaadversarialtraininganddualbatchnormalization AT federicopedersoli advancingdiagnosticperformanceandclinicalusabilityofneuralnetworksviaadversarialtraininganddualbatchnormalization AT markuszimmermann advancingdiagnosticperformanceandclinicalusabilityofneuralnetworksviaadversarialtraininganddualbatchnormalization AT maximilianschulzehagen advancingdiagnosticperformanceandclinicalusabilityofneuralnetworksviaadversarialtraininganddualbatchnormalization AT michaelho advancingdiagnosticperformanceandclinicalusabilityofneuralnetworksviaadversarialtraininganddualbatchnormalization AT christophhaarburger advancingdiagnosticperformanceandclinicalusabilityofneuralnetworksviaadversarialtraininganddualbatchnormalization AT fabiankiessling advancingdiagnosticperformanceandclinicalusabilityofneuralnetworksviaadversarialtraininganddualbatchnormalization AT christianekuhl advancingdiagnosticperformanceandclinicalusabilityofneuralnetworksviaadversarialtraininganddualbatchnormalization AT volkmarschulz advancingdiagnosticperformanceandclinicalusabilityofneuralnetworksviaadversarialtraininganddualbatchnormalization AT danieltruhn advancingdiagnosticperformanceandclinicalusabilityofneuralnetworksviaadversarialtraininganddualbatchnormalization
_version_	1718377861193138176

Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization

Ejemplares similares