Identifying predictive regions from fMRI with TV-L1 prior

Abstract : Decoding, i.e. predicting stimulus related quantities from functional brain images, is a powerful tool to demonstrate differences between brain activity across conditions. However, unlike standard brain mapping, it offers no guaranties on the localization of this information. Here, we consider decoding as a statistical estimation problem and show that injecting a spatial segmentation prior leads to unmatched performance in recovering predictive regions. Specifically, we use L1 penalization to set voxels to zero and Total-Variation (TV) penalization to segment regions. Our contribution is two-fold. On the one hand, we show via extensive experiments that, amongst a large selection of decoding and brain-mapping strategies, TV+L1 leads to best region recovery. On the other hand, we consider implementation issues related to this estimator. To tackle efficiently this joint prediction-segmentation problem we introduce a fast optimization algorithm based on a primal-dual approach. We also tackle automatic setting of hyper-parameters and fast computation of image operation on the irregular masks that arise in brain imaging.
Type de document :
Communication dans un congrès
Pattern Recognition in Neuroimaging (PRNI), Jun 2013, Philadelphia, United States. IEEE, 2013
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00839984
Contributeur : Alexandre Gramfort <>
Soumis le : lundi 1 juillet 2013 - 12:11:59
Dernière modification le : jeudi 9 février 2017 - 15:18:26
Document(s) archivé(s) le : mercredi 2 octobre 2013 - 04:12:23

Fichiers

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

Identifiants

  • HAL Id : hal-00839984, version 1

Collections

Citation

Alexandre Gramfort, Bertrand Thirion, Gaël Varoquaux. Identifying predictive regions from fMRI with TV-L1 prior. Pattern Recognition in Neuroimaging (PRNI), Jun 2013, Philadelphia, United States. IEEE, 2013. 〈hal-00839984〉

Partager

Métriques

Consultations de
la notice

2268

Téléchargements du document

578