Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance Imaging

Accurate brain tissue segmentation in magnetic resonance imaging (MRI) has attracted the attention of medical doctors and researchers since variations in tissue volume and shape permit diagnosing and monitoring neurological diseases. Several proposals have been designed throughout the years comprisi...

ver descrição completa

Detalhes bibliográficos
Autores: Bernal Moyano, Jose, Kushibar, Kaisar, Cabezas Grebol, Mariano, Valverde Valverde, Sergi, Oliver i Malagelada, Arnau, Lladó Bardera, Xavier
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2019
País:España
Recursos:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10256/18097
Acesso em linha:http://hdl.handle.net/10256/18097
Access Level:acceso abierto
Palavra-chave:Imatges -- Processament
Image processing
Cervell -- Imatgeria per ressonància magnètica
Brain -- Magnetic resonance imaging
Imatges -- Segmentació
Imaging segmentation
Imatgeria mèdica
Imaging systems in medicine
id ES_f9efbd47d7d39b6fa85b45a937c5a6f2
oai_identifier_str oai:recercat.cat:10256/18097
network_acronym_str ES
network_name_str España
repository_id_str
spelling Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance ImagingBernal Moyano, JoseKushibar, KaisarCabezas Grebol, MarianoValverde Valverde, SergiOliver i Malagelada, ArnauLladó Bardera, XavierImatges -- ProcessamentImage processingCervell -- Imatgeria per ressonància magnèticaBrain -- Magnetic resonance imagingImatges -- SegmentacióImaging segmentationImatgeria mèdicaImaging systems in medicineAccurate brain tissue segmentation in magnetic resonance imaging (MRI) has attracted the attention of medical doctors and researchers since variations in tissue volume and shape permit diagnosing and monitoring neurological diseases. Several proposals have been designed throughout the years comprising conventional machine learning strategies as well as convolutional neural networks (CNNs) approaches. In particular, in this paper, we analyze a sub-group of deep learning methods producing dense predictions. This branch, referred in the literature as fully CNN (FCNN), is of interest as these architectures can process an input volume in less time than CNNs. Our study focuses on understanding the architectural strengths and weaknesses of literature-like approaches. We implement eight FCNN architectures inspired by robust state-of-the-art methods on brain segmentation related tasks and use them within a standard pipeline. We evaluate them using the IBSR18, MICCAI2012, and iSeg2017 datasets as they contain infant and adult data and exhibit different voxel spacing, image quality, number of scans, and available imaging modalities. The discussion is driven in four directions: comparison between 2D and 3D approaches, the relevance of multiple imaging sequences, the effect of patch size, and the impact of patch overlap as a sampling strategy for training and testing models. Besides the aforementioned analysis, we show that the methods under evaluation can yield top performance on the three data collections. A public version is accessible to download from our research website to encourage other researchers to explore the evaluation frameworkThis work was supported in part by the La Fundació la Marató de TV3 and in part by the Retos de Investigació under Grant TIN2014-55710-R, Grant TIN2015-73563-JIN, and Grant DPI2017-86696-R from the Ministerio de Ciencia y Tecnología. The work of J. Bernal and K. Kushibar was supported by the Catalan Government under Grant FI-DGR2017, Grant 2017FI B00476, and Grant 2017FI B00372. The work of M. Cabezas was supported by the Juan de la Cierva–Incorporación Grant from the Spanish Government under Grant IJCI-2016-29240Institute of Electrical and Electronics Engineers (IEEE)Ministerio de Economía y Competitividad (Espanya)2019info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionpeer-reviewedapplication/pdfhttp://hdl.handle.net/10256/18097http://hdl.handle.net/10256/18097IEEE Access, 2019, vol. 7, p. 89986 - 90002Articles publicats (D-ATC)reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)Inglésinfo:eu-repo/semantics/altIdentifier/doi/10.1109/ACCESS.2019.2926697info:eu-repo/semantics/altIdentifier/issn/2169-3536info:eu-repo/grantAgreement/MINECO//TIN2014-55710-Rinfo:eu-repo/grantAgreement/MINECO//TIN2015-73563-JINinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/DPI2017-86696-RAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:recercat.cat:10256/180972026-05-29T05:05:01Z
dc.title.none.fl_str_mv Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance Imaging
title Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance Imaging
spellingShingle Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance Imaging
Bernal Moyano, Jose
Imatges -- Processament
Image processing
Cervell -- Imatgeria per ressonància magnètica
Brain -- Magnetic resonance imaging
Imatges -- Segmentació
Imaging segmentation
Imatgeria mèdica
Imaging systems in medicine
title_short Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance Imaging
title_full Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance Imaging
title_fullStr Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance Imaging
title_full_unstemmed Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance Imaging
title_sort Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance Imaging
dc.creator.none.fl_str_mv Bernal Moyano, Jose
Kushibar, Kaisar
Cabezas Grebol, Mariano
Valverde Valverde, Sergi
Oliver i Malagelada, Arnau
Lladó Bardera, Xavier
author Bernal Moyano, Jose
author_facet Bernal Moyano, Jose
Kushibar, Kaisar
Cabezas Grebol, Mariano
Valverde Valverde, Sergi
Oliver i Malagelada, Arnau
Lladó Bardera, Xavier
author_role author
author2 Kushibar, Kaisar
Cabezas Grebol, Mariano
Valverde Valverde, Sergi
Oliver i Malagelada, Arnau
Lladó Bardera, Xavier
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Ministerio de Economía y Competitividad (Espanya)
dc.subject.none.fl_str_mv Imatges -- Processament
Image processing
Cervell -- Imatgeria per ressonància magnètica
Brain -- Magnetic resonance imaging
Imatges -- Segmentació
Imaging segmentation
Imatgeria mèdica
Imaging systems in medicine
topic Imatges -- Processament
Image processing
Cervell -- Imatgeria per ressonància magnètica
Brain -- Magnetic resonance imaging
Imatges -- Segmentació
Imaging segmentation
Imatgeria mèdica
Imaging systems in medicine
description Accurate brain tissue segmentation in magnetic resonance imaging (MRI) has attracted the attention of medical doctors and researchers since variations in tissue volume and shape permit diagnosing and monitoring neurological diseases. Several proposals have been designed throughout the years comprising conventional machine learning strategies as well as convolutional neural networks (CNNs) approaches. In particular, in this paper, we analyze a sub-group of deep learning methods producing dense predictions. This branch, referred in the literature as fully CNN (FCNN), is of interest as these architectures can process an input volume in less time than CNNs. Our study focuses on understanding the architectural strengths and weaknesses of literature-like approaches. We implement eight FCNN architectures inspired by robust state-of-the-art methods on brain segmentation related tasks and use them within a standard pipeline. We evaluate them using the IBSR18, MICCAI2012, and iSeg2017 datasets as they contain infant and adult data and exhibit different voxel spacing, image quality, number of scans, and available imaging modalities. The discussion is driven in four directions: comparison between 2D and 3D approaches, the relevance of multiple imaging sequences, the effect of patch size, and the impact of patch overlap as a sampling strategy for training and testing models. Besides the aforementioned analysis, we show that the methods under evaluation can yield top performance on the three data collections. A public version is accessible to download from our research website to encourage other researchers to explore the evaluation framework
publishDate 2019
dc.date.none.fl_str_mv 2019
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
peer-reviewed
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10256/18097
http://hdl.handle.net/10256/18097
url http://hdl.handle.net/10256/18097
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1109/ACCESS.2019.2926697
info:eu-repo/semantics/altIdentifier/issn/2169-3536
info:eu-repo/grantAgreement/MINECO//TIN2014-55710-R
info:eu-repo/grantAgreement/MINECO//TIN2015-73563-JIN
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/DPI2017-86696-R
dc.rights.none.fl_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
dc.source.none.fl_str_mv IEEE Access, 2019, vol. 7, p. 89986 - 90002
Articles publicats (D-ATC)
reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425139143147520
score 15,811543

Registos relacionados