Shape and Appearance based Spatiotemporal Constraint for LV Segmentation in 4D cardiac SPECT

Abstract : We propose a novel shape and appearance based spatiotem- poral constraint and combine it with a level set based deformable model, which can be used for Left Ventricle segmentation in 4D gated cardiac SPECT, particularly in the presence of perfusion defects. The model incorporates appearance in addition to shape information into a soft-to- hard probabilistic constraint, and utilizes spatiotemporal regularization via a Maximum A Posteriori framework. This constraint force allows more flexibility than the rigid forces of shape constraint-only schemes, as well as other state-of-the-art joint shape and appearance constraints. We present comparative results to illustrate the improvement gain.
Type de document :
Communication dans un congrès
CI2BM09 - MICCAI Workshop on Cardiovascular Interventional Imaging and Biophysical Modelling, Sep 2009, London, United Kingdom. 10 p., 2009
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00418378
Contributeur : Alain Monteil <>
Soumis le : vendredi 18 septembre 2009 - 11:30:41
Dernière modification le : vendredi 18 septembre 2009 - 11:39:31
Document(s) archivé(s) le : mardi 15 juin 2010 - 23:52:19

Fichier

3_4_paper105.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00418378, version 1

Collections

Citation

Ronghua Yang, Majid Mirmehdi, Xianghua Xie, David Hall. Shape and Appearance based Spatiotemporal Constraint for LV Segmentation in 4D cardiac SPECT. CI2BM09 - MICCAI Workshop on Cardiovascular Interventional Imaging and Biophysical Modelling, Sep 2009, London, United Kingdom. 10 p., 2009. 〈inria-00418378〉

Partager

Métriques

Consultations de la notice

92

Téléchargements de fichiers

55