Title: Unsupervised spatio-functional clustering of fMRI data based on new functional feature

Authors: S Emeriau; F Blanchard; J.B. Poline; L. Pierot; E Bittar

Addresses: CReSTIC, EA3804, Université de Reims Champagne-Ardennes, Reims, France ' CReSTIC, EA3804, Université de Reims Champagne-Ardennes, Reims, France ' CEA, DSV/I2BM, NeuroSpin Center, Gif-sur-Yvette, France ' Neuroradiology, University Hospital of Reims, Reims, France ' CReSTIC, EA3804, Université de Reims Champagne-Ardennes, Reims, France

Abstract: As fMRI data is high dimensional, applications like connectivity studies, normalisation or multivariate analyses, need to reduce data dimension while minimising the loss of functional information. In our study we use connectivity profiles as a new functional feature to aggregate voxels into clusters. This offers two major advantages in comparison with the current clustering methods. It allows the analyst to deal with the spatial correlation of noise problem, that can lead to bad mergings in the functional domain, and it is based on the whole data independently of a priori information like the General Linear Model (GLM) regressors. We validated that the resulting clusters form a partition of the data in homogeneous regions according to both spatial and functional criteria.

Keywords: fMRI; magnetic resonance imaging; functional MRI; unsupervised clustering; feature extraction; connectivity profiles; noise.

DOI: 10.1504/IJSISE.2012.047781

International Journal of Signal and Imaging Systems Engineering, 2012 Vol.5 No.2, pp.93 - 100

Received: 08 Sep 2011
Accepted: 12 Jan 2012
Published online: 31 Dec 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article