Automatic Multiple Sclerosis lesion segmentation from Intensity-Normalized multi-channel MRI

Jeremy Beaumont 1 Olivier Commowick 1 Christian Barillot 1
1 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
Abstract : In the context of the FLI MICCAI 2016 MSSEG challenge for lesion segmentation, we present a fully automated algorithm for Multiple Sclerosis (MS) lesion segmentation. Our method is composed of three main steps. First, the MS patient images are registered and intensity normalized. Then, the lesion segmentation is done using a voxel-wise comparison of multi-channel Magnetic Resonance Images (MRI) against a set of controls. Finally, the segmentation is refined by applying several lesion appearance rules.
Keywords : MRI Statistics Multiple Sclerosis Intensity Normalization
Type de document :
Communication dans un congrès
Proceedings of the 1st MICCAI Challenge on Multiple Sclerosis Lesions Segmentation Challenge Using a Data Management and Processing Infrastructure - MICCAI-MSSEG, Oct 2016, Athens, Greece
Liste complète des métadonnées
https://www.hal.inserm.fr/inserm-01424802
Contributeur : Olivier Commowick <>
Soumis le : lundi 2 janvier 2017 - 21:59:02
Dernière modification le : vendredi 11 janvier 2019 - 15:15:05
Document(s) archivé(s) le : mardi 4 avril 2017 - 01:41:51

Fichier

MSSEG_Beaumont_2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inserm-01424802, version 1

Collections

INRIA | IRISA | UR1-UFR-ISTIC | UNIV-RENNES | IRISA-D5

Citation

Jeremy Beaumont, Olivier Commowick, Christian Barillot. Automatic Multiple Sclerosis lesion segmentation from Intensity-Normalized multi-channel MRI. Proceedings of the 1st MICCAI Challenge on Multiple Sclerosis Lesions Segmentation Challenge Using a Data Management and Processing Infrastructure - MICCAI-MSSEG, Oct 2016, Athens, Greece. 〈inserm-01424802〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

350

Téléchargements de fichiers

463

Contact

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