Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities

Abstract The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision makin...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mohsen Ghafoorian, Nico Karssemeijer, Tom Heskes, Inge W. M. van Uden, Clara I. Sanchez, Geert Litjens, Frank-Erik de Leeuw, Bram van Ginneken, Elena Marchiori, Bram Platel
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/c8edbcfcdad649f9906176888436eca7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c8edbcfcdad649f9906176888436eca7
record_format	dspace
spelling	oai:doaj.org-article:c8edbcfcdad649f9906176888436eca72021-12-02T15:05:41ZLocation Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities10.1038/s41598-017-05300-52045-2322https://doaj.org/article/c8edbcfcdad649f9906176888436eca72017-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-05300-5https://doaj.org/toc/2045-2322Abstract The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).Mohsen GhafoorianNico KarssemeijerTom HeskesInge W. M. van UdenClara I. SanchezGeert LitjensFrank-Erik de LeeuwBram van GinnekenElena MarchioriBram PlatelNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-12 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Mohsen Ghafoorian Nico Karssemeijer Tom Heskes Inge W. M. van Uden Clara I. Sanchez Geert Litjens Frank-Erik de Leeuw Bram van Ginneken Elena Marchiori Bram Platel Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities
description	Abstract The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).
format	article
author	Mohsen Ghafoorian Nico Karssemeijer Tom Heskes Inge W. M. van Uden Clara I. Sanchez Geert Litjens Frank-Erik de Leeuw Bram van Ginneken Elena Marchiori Bram Platel
author_facet	Mohsen Ghafoorian Nico Karssemeijer Tom Heskes Inge W. M. van Uden Clara I. Sanchez Geert Litjens Frank-Erik de Leeuw Bram van Ginneken Elena Marchiori Bram Platel
author_sort	Mohsen Ghafoorian
title	Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities
title_short	Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities
title_full	Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities
title_fullStr	Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities
title_full_unstemmed	Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities
title_sort	location sensitive deep convolutional neural networks for segmentation of white matter hyperintensities
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/c8edbcfcdad649f9906176888436eca7
work_keys_str_mv	AT mohsenghafoorian locationsensitivedeepconvolutionalneuralnetworksforsegmentationofwhitematterhyperintensities AT nicokarssemeijer locationsensitivedeepconvolutionalneuralnetworksforsegmentationofwhitematterhyperintensities AT tomheskes locationsensitivedeepconvolutionalneuralnetworksforsegmentationofwhitematterhyperintensities AT ingewmvanuden locationsensitivedeepconvolutionalneuralnetworksforsegmentationofwhitematterhyperintensities AT claraisanchez locationsensitivedeepconvolutionalneuralnetworksforsegmentationofwhitematterhyperintensities AT geertlitjens locationsensitivedeepconvolutionalneuralnetworksforsegmentationofwhitematterhyperintensities AT frankerikdeleeuw locationsensitivedeepconvolutionalneuralnetworksforsegmentationofwhitematterhyperintensities AT bramvanginneken locationsensitivedeepconvolutionalneuralnetworksforsegmentationofwhitematterhyperintensities AT elenamarchiori locationsensitivedeepconvolutionalneuralnetworksforsegmentationofwhitematterhyperintensities AT bramplatel locationsensitivedeepconvolutionalneuralnetworksforsegmentationofwhitematterhyperintensities
_version_	1718388732199960576

Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities

Ejemplares similares