Handling confounding variables in statistical shape analysis - application to cardiac remodelling

Statistical shape analysis is a powerful tool to assess organ morphologies and find shape changes associated to a particular disease. However, imbalance in confounding factors, such as demographics might invalidate the analysis if not taken into consideration. Despite the methodological advances in...

Full description

Bibliographic Details
Authors: Bernardino Perez, Gabriel, Benkarim, Oualid M., Sanz de la Garza, Maria, Prat Gonzàlez, Susanna, Sepúlveda-Martínez, Álvaro, Crispi Brillas, Fàtima, Sitges, Marta, Butakoff, Constantine, Craene, Mathieu de, Bijnens, Bart, González Ballester, Miguel Ángel, 1973-
Format: article
Status:Versión aceptada para publicación
Publication Date:2020
Country:España
Institution:Universitat Pompeu Fabra
Repository:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/45146
Online Access:http://hdl.handle.net/10230/45146
http://dx.doi.org/10.1016/j.media.2020.101792
Access Level:Open access
Keyword:Confounder correction
Statistical shape analysis
Computational anatomy
Cardiac remodelling
id ES_7dae01150aa2da74ae2f957dc875f3ee
oai_identifier_str oai:repositori.upf.edu:10230/45146
network_acronym_str ES
network_name_str España
repository_id_str
spelling Handling confounding variables in statistical shape analysis - application to cardiac remodellingBernardino Perez, GabrielBenkarim, Oualid M.Sanz de la Garza, MariaPrat Gonzàlez, SusannaSepúlveda-Martínez, ÁlvaroCrispi Brillas, FàtimaSitges, MartaButakoff, ConstantineCraene, Mathieu deBijnens, BartGonzález Ballester, Miguel Ángel, 1973-Confounder correctionStatistical shape analysisComputational anatomyCardiac remodellingStatistical shape analysis is a powerful tool to assess organ morphologies and find shape changes associated to a particular disease. However, imbalance in confounding factors, such as demographics might invalidate the analysis if not taken into consideration. Despite the methodological advances in the field, providing new methods that are able to capture complex and regional shape differences, the relationship between non-imaging information and shape variability has been overlooked. We present a linear statistical shape analysis framework that finds shape differences unassociated to a controlled set of confounding variables. It includes two confounding correction methods: confounding deflation and adjustment. We applied our framework to a cardiac magnetic resonance imaging dataset, consisting of the cardiac ventricles of 89 triathletes and 77 controls, to identify cardiac remodelling due to the practice of endurance exercise. To test robustness to confounders, subsets of this dataset were generated by randomly removing controls with low body mass index, thus introducing imbalance. The analysis of the whole dataset indicates an increase of ventricular volumes and myocardial mass in athletes, which is consistent with the clinical literature. However, when confounders are not taken into consideration no increase of myocardial mass is found. Using the downsampled datasets, we find that confounder adjustment methods are needed to find the real remodelling patterns in imbalanced datasets.This study was partially supported by the Spanish Ministry of Economy and Competitiveness (grant DEP2013-44923- P, TIN2014-52923-R; Maria de Maeztu Units of Excellence Programme - MDM-2015-0502), el Fondo Europeo de Desarrollo Regional (FEDER) , the European Union under the Horizon 2020 Programme for Research, Innovation (grant agreement No. 642676 CardioFunXion) and Erasmus+ Programme (Framework Agreement number: 2013-0040), la Caixa Foundation (LCF/PR/GN14/10270005, LCF/PR/GN18/10310003), Instituto de Salud Carlos III (PI14/00226, PI17/00675) integrated in the Plan Nacional I+D+I and AGAUR 2017 SGR grant n 1531.Elsevier20202020info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/45146http://dx.doi.org/10.1016/j.media.2020.101792reponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésMedical Image Analysis. 2020 Jul 19:101792info:eu-repo/grantAgreement/ES/1PE/DEP2013-44923- Pinfo:eu-repo/grantAgreement/ES/1PE/TIN2014-52923-Rinfo:eu-repo/grantAgreement/EC/H2020/642676© Elsevier http://dx.doi.org/10.1016/j.media.2020.101792info:eu-repo/semantics/openAccessoai:repositori.upf.edu:10230/451462026-06-12T07:21:37Z
dc.title.none.fl_str_mv Handling confounding variables in statistical shape analysis - application to cardiac remodelling
title Handling confounding variables in statistical shape analysis - application to cardiac remodelling
spellingShingle Handling confounding variables in statistical shape analysis - application to cardiac remodelling
Bernardino Perez, Gabriel
Confounder correction
Statistical shape analysis
Computational anatomy
Cardiac remodelling
title_short Handling confounding variables in statistical shape analysis - application to cardiac remodelling
title_full Handling confounding variables in statistical shape analysis - application to cardiac remodelling
title_fullStr Handling confounding variables in statistical shape analysis - application to cardiac remodelling
title_full_unstemmed Handling confounding variables in statistical shape analysis - application to cardiac remodelling
title_sort Handling confounding variables in statistical shape analysis - application to cardiac remodelling
dc.creator.none.fl_str_mv Bernardino Perez, Gabriel
Benkarim, Oualid M.
Sanz de la Garza, Maria
Prat Gonzàlez, Susanna
Sepúlveda-Martínez, Álvaro
Crispi Brillas, Fàtima
Sitges, Marta
Butakoff, Constantine
Craene, Mathieu de
Bijnens, Bart
González Ballester, Miguel Ángel, 1973-
author Bernardino Perez, Gabriel
author_facet Bernardino Perez, Gabriel
Benkarim, Oualid M.
Sanz de la Garza, Maria
Prat Gonzàlez, Susanna
Sepúlveda-Martínez, Álvaro
Crispi Brillas, Fàtima
Sitges, Marta
Butakoff, Constantine
Craene, Mathieu de
Bijnens, Bart
González Ballester, Miguel Ángel, 1973-
author_role author
author2 Benkarim, Oualid M.
Sanz de la Garza, Maria
Prat Gonzàlez, Susanna
Sepúlveda-Martínez, Álvaro
Crispi Brillas, Fàtima
Sitges, Marta
Butakoff, Constantine
Craene, Mathieu de
Bijnens, Bart
González Ballester, Miguel Ángel, 1973-
author2_role author
author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Confounder correction
Statistical shape analysis
Computational anatomy
Cardiac remodelling
topic Confounder correction
Statistical shape analysis
Computational anatomy
Cardiac remodelling
description Statistical shape analysis is a powerful tool to assess organ morphologies and find shape changes associated to a particular disease. However, imbalance in confounding factors, such as demographics might invalidate the analysis if not taken into consideration. Despite the methodological advances in the field, providing new methods that are able to capture complex and regional shape differences, the relationship between non-imaging information and shape variability has been overlooked. We present a linear statistical shape analysis framework that finds shape differences unassociated to a controlled set of confounding variables. It includes two confounding correction methods: confounding deflation and adjustment. We applied our framework to a cardiac magnetic resonance imaging dataset, consisting of the cardiac ventricles of 89 triathletes and 77 controls, to identify cardiac remodelling due to the practice of endurance exercise. To test robustness to confounders, subsets of this dataset were generated by randomly removing controls with low body mass index, thus introducing imbalance. The analysis of the whole dataset indicates an increase of ventricular volumes and myocardial mass in athletes, which is consistent with the clinical literature. However, when confounders are not taken into consideration no increase of myocardial mass is found. Using the downsampled datasets, we find that confounder adjustment methods are needed to find the real remodelling patterns in imbalanced datasets.
publishDate 2020
dc.date.none.fl_str_mv 2020
2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/45146
http://dx.doi.org/10.1016/j.media.2020.101792
url http://hdl.handle.net/10230/45146
http://dx.doi.org/10.1016/j.media.2020.101792
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Medical Image Analysis. 2020 Jul 19:101792
info:eu-repo/grantAgreement/ES/1PE/DEP2013-44923- P
info:eu-repo/grantAgreement/ES/1PE/TIN2014-52923-R
info:eu-repo/grantAgreement/EC/H2020/642676
dc.rights.none.fl_str_mv © Elsevier http://dx.doi.org/10.1016/j.media.2020.101792
info:eu-repo/semantics/openAccess
rights_invalid_str_mv © Elsevier http://dx.doi.org/10.1016/j.media.2020.101792
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869411681751269376
score 15,812429

Similar Items