Adaptive weighted fusion of multiple MR sequences for brain lesion segmentation

Florence Forbes 1, * Senan Doyle 1 Daniel Garcia-Lorenzo 2 Christian Barillot 2 Michel Dojat 3
* Auteur correspondant
1 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 VisAGeS - Vision, Action et Gestion d'informations en Santé
INSERM - Institut National de la Santé et de la Recherche Médicale : U746, Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
3 GIN - Grenoble Institut des Neurosciences
Abstract : We propose a technique for fusing the output of multiple Magnetic Resonance (MR) sequences to robustly and accurately segment brain lesions. It is based on a Bayesian multi-sequence Markov model that includes weight parameters to account for the relative importance and control the impact of each sequence. The Bayesian framework has the advantage of allowing 1) the incorporation of expert knowledge on the a priori relevant information content of each sequence and 2) a weighting scheme which is modified adaptively according to the data and the segmentation task under consideration. The model, applied to the detection of multiple sclerosis and stroke lesions shows promising results.
Keywords : Bayesian methods Brain modeling Lesions Magnetic resonance Magnetic resonance imaging Markov random fields Multiple sclerosis Pathology Robustness State-space methods
Type de document :
Communication dans un congrès
2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Apr 2010, Rotterdam, Netherlands. IEEE, pp.69-72, 2010, 〈10.1109/ISBI.2010.5490413〉
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger
https://www.hal.inserm.fr/inserm-00723807
Contributeur : Christian Barillot <>
Soumis le : mardi 14 août 2012 - 11:55:25
Dernière modification le : lundi 4 mars 2019 - 14:08:22
Document(s) archivé(s) le : jeudi 15 novembre 2012 - 02:21:55

Fichier

isbi2010_FF.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

INRIA | LJK_PS_MISTIS | LJK_PS | LJK | UNIV-RENNES1 | UGA | IRISA-D5 | INSTITUT-TELECOM | IRISA | UR1-UFR-ISTIC | UNIV-RENNES

Citation

Florence Forbes, Senan Doyle, Daniel Garcia-Lorenzo, Christian Barillot, Michel Dojat. Adaptive weighted fusion of multiple MR sequences for brain lesion segmentation. 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Apr 2010, Rotterdam, Netherlands. IEEE, pp.69-72, 2010, 〈10.1109/ISBI.2010.5490413〉. 〈inserm-00723807〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

802

Téléchargements de fichiers

511

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD