Characterization of Anatomical Shape Based on Random Walk Hitting Times

Abstract : This paper presents an implicit shape representation for describing anatomical shapes with high inter-patient variability based on the expected boundary hitting time of a random walk, which happens to be the solution to the Poisson equation. The main contribution of this paper is to test the validity of the Poisson-based mapping for learning anatomical shape variability, comparing its compactness and completeness with the commonly used Signed Distance Transform and using the liver and the caudate nucleus as examples. Based on these findings, we discuss its use as a shape prior for image segmentation.
Type de document :
Communication dans un congrès
Xavier Pennec. 2nd MICCAI Workshop on Mathematical Foundations of Computational Anatomy, Oct 2008, New-York, United States. pp.117-127, 2008
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00632880
Contributeur : Alain Monteil <>
Soumis le : dimanche 16 octobre 2011 - 22:34:13
Dernière modification le : lundi 17 octobre 2011 - 10:06:37
Document(s) archivé(s) le : jeudi 15 novembre 2012 - 09:46:32

Fichier

mfca08_4_2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00632880, version 1

Collections

Citation

Grace Vesom, Nathan Cahill, Lena Gorelick, Alison Noble. Characterization of Anatomical Shape Based on Random Walk Hitting Times. Xavier Pennec. 2nd MICCAI Workshop on Mathematical Foundations of Computational Anatomy, Oct 2008, New-York, United States. pp.117-127, 2008. 〈inria-00632880〉

Partager

Métriques

Consultations de la notice

99

Téléchargements de fichiers

36