Characterization of myocardial motion patterns by unsupervised multiple kernel learning

Sanchez-Martinez, Sergio, Duchateau, Nicolas, Erdei, Tamas, Fraser, Alan Gordon, Bijnens, Bart H. and Piella, Gemma 2017. Characterization of myocardial motion patterns by unsupervised multiple kernel learning. Medical Image Analysis 35 , pp. 70-82. 10.1016/j.media.2016.06.007

Full text not available from this repository.

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 information 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 (output 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 echocardiography 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 improved by the joint analysis of multiple relevant features.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Medicine
Publisher:	Elsevier
ISSN:	1361-8415
Date of Acceptance:	9 June 2016
Last Modified:	23 May 2018 14:41
URI:	https://orca.cardiff.ac.uk/id/eprint/102388

Citation Data

Cited 36 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item