Transport on Riemannian Manifold for Functional Connectivity-based Classification

Abstract : We present a Riemannian approach for classifying fMRI connectivity patterns before and after intervention in longitudinal studies. A fundamental difficulty with using connectivity as features is that covariance matrices live on the positive semi-definite cone, which renders their elements inter-related. The implicit independent feature assumption in most classifier learning algorithms is thus violated. In this paper, we propose a matrix whitening transport for projecting the covariance estimates onto a common tangent space to reduce the statistical dependencies between their elements. We show on real data that our approach provides significantly higher classification accuracy than directly using Pearson's correlation. We further propose a non-parametric scheme for identifying significantly discriminative connections from classifier weights. Using this scheme, a number of neuroanatomically meaningful connections are found, whereas no significant connections are detected with pure permutation testing.
Type de document :
Communication dans un congrès
MICCAI - 17th International Conference on Medical Image Computing and Computer Assisted Intervention, Sep 2014, Boston, United States. Springer, 2014
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01058521
Contributeur : Bertrand Thirion <>
Soumis le : mercredi 27 août 2014 - 10:09:05
Dernière modification le : lundi 4 juin 2018 - 15:42:02
Document(s) archivé(s) le : mardi 11 avril 2017 - 20:37:11

Fichier

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

Identifiants

  • HAL Id : hal-01058521, version 1

Collections

Citation

Bernard Ng, Martin Dressler, Gaël Varoquaux, Jean-Baptiste Poline, Michael Greicius, et al.. Transport on Riemannian Manifold for Functional Connectivity-based Classification. MICCAI - 17th International Conference on Medical Image Computing and Computer Assisted Intervention, Sep 2014, Boston, United States. Springer, 2014. 〈hal-01058521〉

Partager

Métriques

Consultations de la notice

663

Téléchargements de fichiers

584