Transport on Riemannian Manifold for Functional Connectivity-based Classification - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

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.

Domains

Medical Imaging
Fichier principal
Vignette du fichier
camReady.pdf (171.11 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01058521 , version 1 (27-08-2014)

Identifiers

  • HAL Id : hal-01058521 , version 1

Cite

Bernard Ng, Martin Dressler, Gaël Varoquaux, Jean-Baptiste Poline, Michael D. Greicius, et al.. Transport on Riemannian Manifold for Functional Connectivity-based Classification. MICCAI - 17th International Conference on Medical Image Computing and Computer Assisted Intervention, Polina Golland, Sep 2014, Boston, United States. ⟨hal-01058521⟩
487 View
665 Download

Share

Gmail Facebook X LinkedIn More