Clustering of the Human Skeletal Muscle Fibers Using Linear Programming and Angular Hilbertian Metrics

Abstract : In this paper, we present a manifold clustering method for the classification of fibers obtained from diffusion tensor images (DTI) of the human skeletal muscle. Using a linear programming formulation of prototype-based clustering, we propose a novel fiber classification algo-rithm over manifolds that circumvents the necessity to embed the data in low dimensional spaces and determines automatically the number of clusters. Furthermore, we propose the use of angular Hilbertian metrics between multivariate normal distributions to define a family of distances between tensors that we generalize to fibers. These metrics are used to approximate the geodesic distances over the fiber manifold. We also discuss the case where only geodesic distances to a reduced set of landmark fibers are available. The experimental validation of the method is done using a manually annotated significant dataset of DTI of the calf muscle for healthy and diseased subjects.
Type de document :
Communication dans un congrès
21st International Conference on Information Processing in Medical Imaging, Jul 2009, Williamsburg (Virginia), United States. pp.14-25, 2009
Liste complète des métadonnées

https://hal-supelec.archives-ouvertes.fr/hal-00424532
Contributeur : Karine El Rassi <>
Soumis le : vendredi 16 octobre 2009 - 15:40:42
Dernière modification le : vendredi 15 février 2019 - 13:58:08
Document(s) archivé(s) le : mercredi 16 juin 2010 - 00:50:06

Fichier

Neji_ipmi09.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00424532, version 1

Collections

Citation

Radhouène Neji, Ahmed Besbes, Nikos Komodakis, Mezri Maatoouk, Jean-François Deux, et al.. Clustering of the Human Skeletal Muscle Fibers Using Linear Programming and Angular Hilbertian Metrics. 21st International Conference on Information Processing in Medical Imaging, Jul 2009, Williamsburg (Virginia), United States. pp.14-25, 2009. 〈hal-00424532〉

Partager

Métriques

Consultations de la notice

792

Téléchargements de fichiers

194