DL-based classification of LV wall motion in cardiac MRI with a parametric approach

Abstract : In this paper, we propose an automated method to assess wall motion in Left Ventricle (LV) function in cardiac cine-Magnetic Resonance Imaging (MRI) based on Dictionary Learning (DL) classification with a parametric approach. Time-signal intensity curves (TSICs) are identified in spatio-temporal profiles extracted from differents anatomical segments in a cardiac MRI study. Parameters are extracted from TSICs that present a decreasing then increasing shape reflecting dynamic information of the LV contraction. Several parameter combinations are used as input atoms to train a sparse classifier based on kernel DL and results are compared with Support Vector Machines. Best classification performance is obtained with an accuracy about 94%.
Type de document :
Communication dans un congrès
Journées RITS 2015, Mar 2015, Dourdan, France. Actes des Journées RITS 2015, pp 180-181, 2015
Liste complète des métadonnées

Littérature citée [4 références]  Voir  Masquer  Télécharger

http://www.hal.inserm.fr/inserm-01155024
Contributeur : Frédérique Frouin <>
Soumis le : mardi 26 mai 2015 - 08:14:54
Dernière modification le : mercredi 16 mai 2018 - 11:23:41
Document(s) archivé(s) le : jeudi 20 avril 2017 - 08:15:13

Fichier

ACTES-RITS2015-HAL-p180-1.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

  • HAL Id : inserm-01155024, version 1

Collections

Citation

Juan Mantilla, Mireille Garreau, Jean-Jacques Bellanger, Christophe Leclercq, José Paredes. DL-based classification of LV wall motion in cardiac MRI with a parametric approach. Journées RITS 2015, Mar 2015, Dourdan, France. Actes des Journées RITS 2015, pp 180-181, 2015. 〈inserm-01155024〉

Partager

Métriques

Consultations de la notice

283

Téléchargements de fichiers

115