A conditional random field approach for coupling local registration with robust tissue and structure segmentation

Benoît Scherrer; Florence Forbes; Michel Dojat

doi:10.1007/978-3-642-04271-3_66

A conditional random field approach for coupling local registration with robust tissue and structure segmentation: A CRF Approach for Coupling Local Registration

Benoît Scherrer ¹ Florence Forbes ² Michel Dojat ^{1, *}

* Auteur correspondant

1 INSERM U836, équipe 5, Neuro-imagerie fonctionnelle et métabolique

GIN - Grenoble Institut des Neurosciences

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 consider a general modelling strategy to handle in a unified way a number of tasks essential to MR brain scan analysis. Our approach is based on the explicit definition of a Conditional Random Field (CRF) model decomposed into components to be specified according to the targeted tasks. For a specific illustration, we define a CRF model that combines robust-to-noise and to nonuniformity Markovian tissue and structure segmentations with local affine atlas registration. The evaluation performed on both phantoms and real 3T images shows good results and, in particular, points out the gain in introducing registration as a model component. Besides, our modeling and estimation scheme provide general guidelines to deal with complex joint processes for medical image analysis.

Type de document :

Communication dans un congrès

Guang-Zhong Yang, David Hawkes, Daniel Rueckert, Alison Noble, and Chris Taylor. MICCAI 2009 - 12th International Conference on Medical Image Computing and Computer Assisted Intervention, Sep 2009, London, United Kingdom. Springer, 5762, pp.540-548, 2009, Lecture Notes in Computer Science. 〈10.1007/978-3-642-04271-3_66〉

Domaine :

Informatique [cs] / Traitement des images

Sciences du Vivant [q-bio] / Neurosciences [q-bio.NC]

Liste complète des métadonnées

Littérature citée [9 références] Voir Masquer Télécharger

http://www.hal.inserm.fr/inserm-00517880
Contributeur : Michel Dojat <>
Soumis le : mercredi 15 septembre 2010 - 18:44:10
Dernière modification le : mercredi 11 avril 2018 - 01:58:31
Document(s) archivé(s) le : vendredi 2 décembre 2016 - 10:44:42

Benoît Scherrer, Florence Forbes, Michel Dojat. A conditional random field approach for coupling local registration with robust tissue and structure segmentation: A CRF Approach for Coupling Local Registration. Guang-Zhong Yang, David Hawkes, Daniel Rueckert, Alison Noble, and Chris Taylor. MICCAI 2009 - 12th International Conference on Medical Image Computing and Computer Assisted Intervention, Sep 2009, London, United Kingdom. Springer, 5762, pp.540-548, 2009, Lecture Notes in Computer Science. 〈10.1007/978-3-642-04271-3_66〉. 〈inserm-00517880〉

A conditional random field approach for coupling local registration with robust tissue and structure segmentation: A CRF Approach for Coupling Local Registration

Fichier

Accès restreint

Identifiants

Collections

Citation

Exporter

Métriques

507

Contact

A conditional random field approach for coupling local registration with robust tissue and structure segmentation: A CRF Approach for Coupling Local Registration

Fichier

Accès restreint

Identifiants

Collections

Citation

Exporter

Partager

Métriques

507

Contact