Welcome to the UPF Digital Repository

Analysis of nonstandardized stress echocardiography sequences using multiview dimensionality reduction

Show simple item record

dc.contributor.author Nogueira, Mariana
dc.contributor.author Craene, Mathieu de
dc.contributor.author Sanchez Martinez, Sergio
dc.contributor.author Chowdhury, Devyani
dc.contributor.author Bijnens, Bart
dc.contributor.author Piella Fenoy, Gemma
dc.date.accessioned 2019-11-26T10:44:02Z
dc.date.issued 2020
dc.identifier.citation Nogueira M, De Craene M, sanchez-Martinez S, Chowdhury D, Bijnens B, Piella G. Analysis of nonstandardized stress echocardiography sequences using multiview dimensionality reduction. Medical Image Analysis. 2020 Feb;60:101594. DOI: 10.1016/j.media.2019.101594
dc.identifier.issn 1361-8415
dc.identifier.uri http://hdl.handle.net/10230/42981
dc.description.abstract Alternative stress echocardiography protocols such as handgrip exercise are potentially more favorable towards large-scale screening scenarios than those currently adopted in clinical practice. However, these are still underexplored because the maximal exercise levels are not easily quantified and regulated, requiring the analysis of the complete data sequences (thousands of images), which represents a challenging task for the clinician. We propose a framework for the analysis of these complex datasets, and illustrate it on a handgrip exercise dataset including complete acquisitions of 10 healthy controls and 5 ANT1 mutation patients (1377 cardiac cycles). The framework is based on an unsupervised formulation of multiple kernel learning, which is used to integrate information coming from myocardial velocity traces and heart rate to obtain a lower-dimensional representation of the data. Such simplified representation is then explored to discriminate groups of response and understand the underlying pathophysiological mechanisms. The analysis pipeline involves the reconstruction of population-specific signatures using multiscale kernel regression, and the clustering of subjects based on the trajectories defined by their projected sequences. The results confirm that the proposed framework is able to detect distinctive clusters of response and to provide insight regarding the underlying pathophysiology.
dc.description.sponsorship This work is supported by the European Union’s Horizon 2020 Programme for Research and Innovation, under grant agreement No. 642676 (CardioFunXion), by the Fundació La Marató de TV3 (No. 20154031), and by the Spanish Ministry of Economy and Competitiveness under the María de Maeztu Units of Excellence Program (MDM-2015-0502).
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher Elsevier
dc.relation.ispartof Medical Image Analysis. 2020 Feb;60:101594
dc.rights © Elsevier http://dx.doi.org/10.1016/j.media.2019.101594
dc.title Analysis of nonstandardized stress echocardiography sequences using multiview dimensionality reduction
dc.type info:eu-repo/semantics/article
dc.identifier.doi http://dx.doi.org/10.1016/j.media.2019.101594
dc.subject.keyword Multiview dimensionality reduction
dc.subject.keyword Multiple kernel learning
dc.subject.keyword Stress echocardiography
dc.subject.keyword Pattern analysis
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/642676
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/acceptedVersion


This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account


In collaboration with Compliant to Partaking