ICA-based sparse feature recovery from fMRI datasets

Abstract : Spatial Independent Components Analysis (ICA) is increasingly used in the context of functional Magnetic Resonance Imaging (fMRI) to study cognition and brain pathologies. Salient features present in some of the extracted Independent Components (ICs) can be interpreted as brain networks, but the segmentation of the corresponding regions from ICs is still ill-controlled. Here we propose a new ICA-based procedure for extraction of sparse features from fMRI datasets. Specifically, we introduce a new thresholding procedure that controls the deviation from isotropy in the ICA mixing model. Unlike current heuristics, our procedure guarantees an exact, possibly conservative, level of specificity in feature detection. We evaluate the sensitivity and specificity of the method on synthetic and fMRI data and show that it outperforms state-of-the-art approaches.
Type de document :
Communication dans un congrès
Biomedical Imaging, IEEE International Symposium on, Apr 2010, Rotterdam, Netherlands. IEEE, pp.1177, 2010
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00489506
Contributeur : Gaël Varoquaux <>
Soumis le : samedi 5 juin 2010 - 13:26:41
Dernière modification le : jeudi 7 février 2019 - 16:49:07
Document(s) archivé(s) le : vendredi 17 septembre 2010 - 13:26:01

Fichiers

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

Identifiants

  • HAL Id : hal-00489506, version 1
  • ARXIV : 1006.2302

Collections

Citation

Gaël Varoquaux, Merlin Keller, Jean Baptiste Poline, Philippe Ciuciu, Bertrand Thirion. ICA-based sparse feature recovery from fMRI datasets. Biomedical Imaging, IEEE International Symposium on, Apr 2010, Rotterdam, Netherlands. IEEE, pp.1177, 2010. 〈hal-00489506〉

Partager

Métriques

Consultations de la notice

587

Téléchargements de fichiers

304