Variational solution to the joint detection estimation of brain activity in fMRI - Archive ouverte HAL Access content directly
Conference Papers Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Year : 2011

Variational solution to the joint detection estimation of brain activity in fMRI

(1) , (1) , (2) , (3) , (2)
1
2
3

Abstract

We address the issue of jointly detecting brain activity and estimating underlying brain hemodynamics from functional MRI data. We adopt the so-called Joint Detection Estimation (JDE) framework that takes spatial dependencies between voxels into account. We recast the JDE into a missing data framework and derive a Variational Expectation-Maximization (VEM) algorithm for its inference. It follows a new algorithm that has interesting advantages over the previously used intensive simulation methods (Markov Chain Monte Carlo, MCMC): tests on artificial data show that the VEM-JDE is more robust to model mis-specification while additional tests on real data confirm that it achieves similar performance in much less computation time.
Embargoed file
Embargoed file
Ne sera jamais visible
Loading...

Dates and versions

inserm-00635384 , version 1 (25-10-2011)

Identifiers

Cite

Lotfi Chaari, Florence Forbes, Thomas Vincent, Michel Dojat, Philippe Ciuciu. Variational solution to the joint detection estimation of brain activity in fMRI. MICCAI 2011 - 14th International Conference on Medical Image Computing and Computer-Assisted Intervention, Sep 2011, Toronto, Canada. pp.260-268, ⟨10.1007/978-3-642-23629-7_32⟩. ⟨inserm-00635384⟩
273 View
2 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More