A spatially constrained low-rank matrix factorization for the functional parcellation of the brain


Benichoux, A. and Blumensath, T. (2014) A spatially constrained low-rank matrix factorization for the functional parcellation of the brain Proc. 22nd European Signal Processing Conference, pp. 1-5.

Download

[img] PDF BBS14.pdf - Other
Download (640kB)

Description/Abstract

We propose a new matrix recovery framework to partition brain activity using time series of resting-state functional Magnetic Resonance Imaging (fMRI). Spatial clusters are obtained with a new low-rank factorization algorithm that offers the ability to add different types of constraints. As an example we add a total variation type cost function in order to exploit neighborhood constraints.
We first validate the performance of our algorithm on sim- ulated data, which allows us to show that the neighborhood constraint improves the recovery in noisy or undersampled set-ups. Then we conduct experiments on real-world data, where we simulated an accelerated acquisition by randomly undersampling the time series. The obtained parcellation are reproducible when analysing data from different sets of indi- viduals, and the estimation is robust to undersampling.

Item Type: Article
Subjects: Q Science > QC Physics
R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Organisations: Signal Processing & Control Grp
ePrint ID: 363425
Date :
Date Event
1 September 2014Submitted
October 2014Published
Date Deposited: 25 Mar 2014 11:50
Last Modified: 19 May 2017 07:14
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/363425

Actions (login required)

View Item View Item