Diffusion Maps Clustering for Magnetic Resonance Q-Ball Imaging Segmentation

Demian Wassermann 1 Maxime Descoteaux 2 Rachid Deriche 1
1 ODYSSEE - Computer and biological vision
DI-ENS - Département d'informatique de l'École normale supérieure, CRISAM - Inria Sophia Antipolis - Méditerranée , ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, ENPC - École des Ponts ParisTech
Abstract : White matter fiber clustering aims to get insight about anatomical structures in order to generate atlases, perform clear visualizations, and compute statistics across subjects, all important and current neuroimaging problems. In this work, we present a diffusion maps clustering method applied to diffusion MRI in order to segment complex white matter fiber bundles. It is well known that diffusion tensor imaging (DTI) is restricted in complex fiber regions with crossings and this is why recent high-angular resolution diffusion imaging (HARDI) such as Q-Ball imaging (QBI) has been introduced to overcome these limitations. QBI reconstructs the diffusion orientation distribution function (ODF), a spherical function that has its maxima agreeing with the underlying fiber populations. In this paper, we use a spherical harmonic ODF representation as input to the diffusion maps clustering method.We first show the advantage of using diffusion maps clustering over classical methods such as N-Cuts and Laplacian eigenmaps. In particular, our ODF diffusion maps requires a smaller number of hypothesis from the input data, reduces the number of artifacts in the segmentation, and automatically exhibits the number of clusters segmenting the Q-Ball image by using an adaptive scalespace parameter.We also show that our ODF diffusion maps clustering can reproduce published results using the diffusion tensor (DT) clustering with N-Cuts on simple synthetic images without crossings. On more complex data with crossings, we show that our ODF-based method succeeds to separate fiber bundles and crossing regions whereas the DT-based methods generate artifacts and exhibit wrong number of clusters. Finally, we show results on a real-brain dataset where we segment well-known fiber bundles.
Type de document :
Article dans une revue
International Journal of Biomedical Imaging, Hindawi Publishing Corporation, 2008, 2008 (ID 526906), 12pp. 〈10.1155/2008/526906〉
Liste complète des métadonnées

Littérature citée [39 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00429948
Contributeur : Alain Monteil <>
Soumis le : jeudi 5 novembre 2009 - 11:58:34
Dernière modification le : vendredi 25 mai 2018 - 12:02:04
Document(s) archivé(s) le : mardi 16 octobre 2012 - 13:20:08

Fichier

wassermann-descoteaux-etal_08....
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

Demian Wassermann, Maxime Descoteaux, Rachid Deriche. Diffusion Maps Clustering for Magnetic Resonance Q-Ball Imaging Segmentation. International Journal of Biomedical Imaging, Hindawi Publishing Corporation, 2008, 2008 (ID 526906), 12pp. 〈10.1155/2008/526906〉. 〈inria-00429948〉

Partager

Métriques

Consultations de la notice

471

Téléchargements de fichiers

308