A Comparison of Metrics and Algorithms for Fiber Clustering

Abstract : Diffusion-weighted Magnetic Resonance Imaging (dMRI) can unveil the microstructure of the brain white matter. The analysis of the anisotropy observed in the dMRI contrast with tractography methods can help to understand the pattern of connections between brain regions and characterize neurological diseases. Because of the amount of information produced by such analyses and the errors carried by the reconstruction step, it is necessary to simplify this output. Clustering algorithms can be used to group samples that are similar according to a given metric. We propose to explore the well-known clustering algorithm k-means and a recently available one, QuickBundles [1]. We propose an efficient procedure to associate k-means with Point Density Model, a recently proposed metric to analyze geometric structures. We analyze the performance and usability of these algorithms on manually labeled data and a database a 10 subjects.
Type de document :
Communication dans un congrès
Pattern Recognition in NeuroImaging, Jun 2013, Philadelphia, United States. 2013
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00858115
Contributeur : Viviana Siless <>
Soumis le : mercredi 4 septembre 2013 - 16:31:36
Dernière modification le : lundi 4 juin 2018 - 15:42:02
Document(s) archivé(s) le : jeudi 6 avril 2017 - 15:18:38

Fichier

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

Identifiants

  • HAL Id : hal-00858115, version 1

Collections

Citation

Viviana Siless, Sergio Medina, Gaël Varoquaux, Bertrand Thirion. A Comparison of Metrics and Algorithms for Fiber Clustering. Pattern Recognition in NeuroImaging, Jun 2013, Philadelphia, United States. 2013. 〈hal-00858115〉

Partager

Métriques

Consultations de la notice

1054

Téléchargements de fichiers

404