Spatially Regularized SVM for the Detection of Brain Areas Associated with Stroke Outcome

Abstract : This paper introduces a new method to detect group differences in brain images based on spatially regularized support vector machines (SVM). First, we propose to spatially regularize the SVM using a graph encoding the voxels' proximity. Two examples of regularization graphs are provided. Significant differences between two populations are detected using statistical tests on the margins of the SVM. We first tested our method on synthetic examples. We then applied it to 72 stroke patients to detect brain areas associated with motor outcome at 90 days, based on diffusion-weighted images acquired at the acute stage (one day delay). The proposed method showed that poor motor outcome is associated to changes in the corticospinal bundle and white matter tracts originating from the premotor cortex. Standard mass univariate analyses failed to detect any difference.
Type de document :
Communication dans un congrès
Medical Image Computing and Computer-Assisted Intervention, MICCAI 2010, 2010, Beijing, China. Springer, pp.316 - 323, 2010, Lecture Notes in Computer Science. 〈10.1007/978-3-642-15705-9_39〉
Liste complète des métadonnées

Littérature citée [21 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01439126
Contributeur : Olivier Colliot <>
Soumis le : mercredi 18 janvier 2017 - 12:19:16
Dernière modification le : mercredi 21 mars 2018 - 18:57:51
Document(s) archivé(s) le : mercredi 19 avril 2017 - 13:54:17

Fichier

cuingnet2010-MICCAI-postprint....
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

UPMC | LIB | ICM

Citation

Rémi Cuingnet, Charlotte Rosso, Stéphane Lehéricy, Didier Dormont, Habib Benali, et al.. Spatially Regularized SVM for the Detection of Brain Areas Associated with Stroke Outcome. Medical Image Computing and Computer-Assisted Intervention, MICCAI 2010, 2010, Beijing, China. Springer, pp.316 - 323, 2010, Lecture Notes in Computer Science. 〈10.1007/978-3-642-15705-9_39〉. 〈hal-01439126〉

Partager

Métriques

Consultations de la notice

89

Téléchargements de fichiers

42