LOCUS: local cooperative unified segmentation of MRI brain scans

Benoît Scherrer 1 Michel Dojat 1, * Florence Forbes 2 Catherine Garbay 3
* Auteur correspondant
2 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We propose to carry out cooperatively both tissue and structure segmentations by distributing a set of local and cooperative models in a unified MRF framework. Tissue segmentation is performed by partitionning the volume into subvolumes where local MRFs are estimated in cooperation with their neighbors to ensure consistency. Local estimation fits precisely to the local intensity distribution and thus handles nonuniformity of intensity without any bias field modelization. Structure segmentation is performed via local MRFs that integrate localization constraints provided by a priori general fuzzy description of brain anatomy. Structure segmentation is not reduced to a postprocessing step but cooperates with tissue segmentation to gradually and conjointly improve models accuracy. The evaluation was performed using phantoms and real 3T brain scans. It shows good results and in particular robustness to nonuniformity and noise with a low computational cost.
Type de document :
Communication dans un congrès
Nicholas Ayache, Sébastien Ourselin, and Anthony Maeder. MICCAI07 - 10th International Conference on Medical Image Computing and Computer Assisted Intervention, Oct 2007, Brisbane, Australia. Springer, 4791, pp.219-227, 2007, Lecture Notes in Computer Science. 〈10.1007/978-3-540-75757-3_27〉
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

http://www.hal.inserm.fr/inserm-00402276
Contributeur : Michel Dojat <>
Soumis le : mardi 7 juillet 2009 - 10:31:43
Dernière modification le : vendredi 20 juillet 2018 - 16:03:31
Document(s) archivé(s) le : mardi 15 juin 2010 - 19:35:59

Fichiers

MICCAI2007_bscherrer.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Benoît Scherrer, Michel Dojat, Florence Forbes, Catherine Garbay. LOCUS: local cooperative unified segmentation of MRI brain scans. Nicholas Ayache, Sébastien Ourselin, and Anthony Maeder. MICCAI07 - 10th International Conference on Medical Image Computing and Computer Assisted Intervention, Oct 2007, Brisbane, Australia. Springer, 4791, pp.219-227, 2007, Lecture Notes in Computer Science. 〈10.1007/978-3-540-75757-3_27〉. 〈inserm-00402276〉

Partager

Métriques

Consultations de la notice

779

Téléchargements de fichiers

571