Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/1822/49901 |
Resumo: | Cardiovascular diseases are among the leading causes of death and frequently result in local myocardial dysfunction. Among the numerous imaging modalities available to detect these dysfunctional regions, cardiac deformation imaging through tagged magnetic resonance imaging (t-MRI) has been an attractive approach. Nevertheless, fully automatic analysis of these data sets is still challenging. In this work, we present a fully automatic framework to estimate left ventricular myocardial deformation from t-MRI. This strategy performs automatic myocardial segmentation based on B-spline explicit active surfaces, which are initialized using an annular model. A non-rigid image-registration technique is then used to assess myocardial deformation. Three experiments were set up to validate the proposed framework using a clinical database of 75 patients. First, automatic segmentation accuracy was evaluated by comparing against manual delineations at one specific cardiac phase. The proposed solution showed an average perpendicular distance error of 2.35 +/- 1.21 mm and 2.27 +/- 1.02 mm for the endo- and epicardium, respectively. Second, starting from either manual or automatic segmentation, myocardial tracking was performed and the resulting strain curves were compared. It is shown that the automatic segmentation adds negligible differences during the strain-estimation stage, corroborating its accuracy. Finally, segmental strain was compared with scar tissue extent determined by delay-enhanced MRI. The results proved that both strain components were able to distinguish between normal and infarct regions. Overall, the proposed framework was shown to be accurate, robust, and attractive for clinical practice, as it overcomes several limitations of a manual analysis. |
id |
RCAP_4d3ac1ac9fff6529c7111dd74bcc7379 |
---|---|
oai_identifier_str |
oai:repositorium.sdum.uminho.pt:1822/49901 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imagingtagged magnetic resonance imagingfully automatic segmentationnon-rigid image registrationstrain estimationCiências Médicas::Medicina BásicaScience & TechnologyCardiovascular diseases are among the leading causes of death and frequently result in local myocardial dysfunction. Among the numerous imaging modalities available to detect these dysfunctional regions, cardiac deformation imaging through tagged magnetic resonance imaging (t-MRI) has been an attractive approach. Nevertheless, fully automatic analysis of these data sets is still challenging. In this work, we present a fully automatic framework to estimate left ventricular myocardial deformation from t-MRI. This strategy performs automatic myocardial segmentation based on B-spline explicit active surfaces, which are initialized using an annular model. A non-rigid image-registration technique is then used to assess myocardial deformation. Three experiments were set up to validate the proposed framework using a clinical database of 75 patients. First, automatic segmentation accuracy was evaluated by comparing against manual delineations at one specific cardiac phase. The proposed solution showed an average perpendicular distance error of 2.35 +/- 1.21 mm and 2.27 +/- 1.02 mm for the endo- and epicardium, respectively. Second, starting from either manual or automatic segmentation, myocardial tracking was performed and the resulting strain curves were compared. It is shown that the automatic segmentation adds negligible differences during the strain-estimation stage, corroborating its accuracy. Finally, segmental strain was compared with scar tissue extent determined by delay-enhanced MRI. The results proved that both strain components were able to distinguish between normal and infarct regions. Overall, the proposed framework was shown to be accurate, robust, and attractive for clinical practice, as it overcomes several limitations of a manual analysis.FCT—Fundacão para a Ciência e a Tecnologia, Portugal, and the European Social Found, European Union, for funding support through the Programa Operacional Capital Humano (POCH) in the scope of the PhD grants SFRH/BD/95438/2013 (P Morais) and SFRH/BD/93443/2013 (S Queirós). This work was supported by the projects NORTE-07-0124-FEDER-000017 and NORTE-01-0145-FEDER-000013, co-funded by Programa Operacional Regional do Norte, Quadro de Referência Estratégico Nacional, through Fundo Europeu de Desenvolvimento Regional (FEDER). The authors would also like to acknowledge the EU (FP7) framework program, for the financial support of the DOPPLER-CIP project (grant no. 223615)info:eu-repo/semantics/publishedVersionIOP PublishingUniversidade do MinhoMorais, Pedro André GonçalvesQueirós, Sandro Filipe MonteiroHeyde, BrechtEngvall, JanD’ hooge, JanVilaça, João L.2017-08-032017-08-03T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/1822/49901engMorais, P., Queirós, S., Heyde, B., Engvall, J., D’hooge, J., & Vilaça, J. L. (2017). Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging. Physics in Medicine & Biology, 62(17)0031-915510.1088/1361-6560/aa7dc228783715http://iopscience.iop.org/article/10.1088/1361-6560/aa7dc2/metainfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-21T12:38:13Zoai:repositorium.sdum.uminho.pt:1822/49901Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T19:34:36.984758Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging |
title |
Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging |
spellingShingle |
Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging Morais, Pedro André Gonçalves tagged magnetic resonance imaging fully automatic segmentation non-rigid image registration strain estimation Ciências Médicas::Medicina Básica Science & Technology |
title_short |
Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging |
title_full |
Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging |
title_fullStr |
Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging |
title_full_unstemmed |
Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging |
title_sort |
Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging |
author |
Morais, Pedro André Gonçalves |
author_facet |
Morais, Pedro André Gonçalves Queirós, Sandro Filipe Monteiro Heyde, Brecht Engvall, Jan D’ hooge, Jan Vilaça, João L. |
author_role |
author |
author2 |
Queirós, Sandro Filipe Monteiro Heyde, Brecht Engvall, Jan D’ hooge, Jan Vilaça, João L. |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade do Minho |
dc.contributor.author.fl_str_mv |
Morais, Pedro André Gonçalves Queirós, Sandro Filipe Monteiro Heyde, Brecht Engvall, Jan D’ hooge, Jan Vilaça, João L. |
dc.subject.por.fl_str_mv |
tagged magnetic resonance imaging fully automatic segmentation non-rigid image registration strain estimation Ciências Médicas::Medicina Básica Science & Technology |
topic |
tagged magnetic resonance imaging fully automatic segmentation non-rigid image registration strain estimation Ciências Médicas::Medicina Básica Science & Technology |
description |
Cardiovascular diseases are among the leading causes of death and frequently result in local myocardial dysfunction. Among the numerous imaging modalities available to detect these dysfunctional regions, cardiac deformation imaging through tagged magnetic resonance imaging (t-MRI) has been an attractive approach. Nevertheless, fully automatic analysis of these data sets is still challenging. In this work, we present a fully automatic framework to estimate left ventricular myocardial deformation from t-MRI. This strategy performs automatic myocardial segmentation based on B-spline explicit active surfaces, which are initialized using an annular model. A non-rigid image-registration technique is then used to assess myocardial deformation. Three experiments were set up to validate the proposed framework using a clinical database of 75 patients. First, automatic segmentation accuracy was evaluated by comparing against manual delineations at one specific cardiac phase. The proposed solution showed an average perpendicular distance error of 2.35 +/- 1.21 mm and 2.27 +/- 1.02 mm for the endo- and epicardium, respectively. Second, starting from either manual or automatic segmentation, myocardial tracking was performed and the resulting strain curves were compared. It is shown that the automatic segmentation adds negligible differences during the strain-estimation stage, corroborating its accuracy. Finally, segmental strain was compared with scar tissue extent determined by delay-enhanced MRI. The results proved that both strain components were able to distinguish between normal and infarct regions. Overall, the proposed framework was shown to be accurate, robust, and attractive for clinical practice, as it overcomes several limitations of a manual analysis. |
publishDate |
2017 |
dc.date.none.fl_str_mv |
2017-08-03 2017-08-03T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/1822/49901 |
url |
http://hdl.handle.net/1822/49901 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Morais, P., Queirós, S., Heyde, B., Engvall, J., D’hooge, J., & Vilaça, J. L. (2017). Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging. Physics in Medicine & Biology, 62(17) 0031-9155 10.1088/1361-6560/aa7dc2 28783715 http://iopscience.iop.org/article/10.1088/1361-6560/aa7dc2/meta |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
IOP Publishing |
publisher.none.fl_str_mv |
IOP Publishing |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799132868839997440 |