Characterization of myocardial motion patterns by unsupervised multiple kernel learning

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Sánchez Martínez, Sergio
• dc.contributor.author Duchateau, Nicolas
• dc.contributor.author Erdei, Tamas
• dc.contributor.author Fraser, Alan G.
• dc.contributor.author Bijnens, Bart
• dc.contributor.author Piella Fenoy, Gemma
• dc.date.accessioned 2019-03-11T14:21:03Z
• dc.date.available 2019-03-11T14:21:03Z
• dc.date.issued 2017
• dc.description.abstract We propose an independent objective method to characterize different patterns of functional responses to stress in the heart failure with preserved ejection fraction (HFPEF) syndrome by combining multiple temporally-aligned myocardial velocity traces at rest and during exercise, together with temporal infor- mation on the occurrence of cardiac events (valves openings/closures and atrial activation). The method builds upon multiple kernel learning, a machine learning technique that allows the combination of data of different nature and the reduction of their dimensionality towards a meaningful representation (out- put space). The learning process is kept unsupervised, to study the variability of the input traces without being conditioned by data labels. To enhance the physiological interpretation of the output space, the variability that it encodes is analyzed in the space of input signals after reconstructing the velocity traces via multiscale kernel regression. The methodology was applied to 2D sequences from a stress echocardio- graphy protocol from 55 subjects (22 healthy, 19 HFPEF and 14 breathless subjects). The results confirm that characterization of the myocardial functional response to stress in the HFPEF syndrome may be im- proved by the joint analysis of multiple relevant features.en
• dc.description.sponsorship The authors acknowledge the European Union’s Seventh Frame- work Programme for research, technological development and demonstration (VP2HF FP7-2013-611823 and MEDIA FP7-HEALTH- 2010-261409), and the Spanish Ministry of Economy and Compet- itiveness (TIN2012-35874). The work of S. Sanchez-Martinez was supported by a fellowship from “la Caixa”Banking Foundation.en
• dc.format.mimetype application/pdf
• dc.identifier.citation Sánchez S, Duchateau N, Erdei T, Fraser AG, Bijnens BH, Piella G. Characterization of myocardial motion patterns by unsupervised multiple Kernel learning. Medical Image Analysis. 2017 Jan;35:70-82. DOI: 10.1016/j.media.2016.06.007
• dc.identifier.doi http://dx.doi.org/10.1016/j.media.2016.06.007
• dc.identifier.issn 1361-8415
• dc.identifier.uri http://hdl.handle.net/10230/36794
• dc.language.iso eng
• dc.publisher Elsevier
• dc.relation.ispartof Medical Image Analysis. 2017 Jan;35:70-82.
• dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/61409
• dc.relation.projectID info:eu-repo/grantAgreement/ES/3PN/TIN2012-35874
• dc.rights © Elsevier https://doi.org/10.1016/j.media.2016.06.007
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Myocardial motionen
• dc.subject.keyword Echocardiographyen
• dc.subject.keyword Multiple kernel learningen
• dc.subject.keyword Pattern analysisen
• dc.title Characterization of myocardial motion patterns by unsupervised multiple kernel learning
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/acceptedVersion