Share Email Print
cover

Proceedings Paper

Fast computation of functional networks from fMRI activity: a multi-platform comparison
Author(s): A. Ravishankar Rao; Rajesh Bordawekar; Guillermo Cecchi
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The recent deployment of functional networks to analyze fMRI images has been very promising. In this method, the spatio-temporal fMRI data is converted to a graph-based representation, where the nodes are voxels and edges indicate the relationship between the nodes, such as the strength of correlation or causality. Graph-theoretic measures can then be used to compare different fMRI scans. However, there is a significant computational bottleneck, as the computation of functional networks with directed links takes several hours on conventional machines with single CPUs. The study in this paper shows that a GPU can be advantageously used to accelerate the computation, such that the network computation takes a few minutes. Though GPUs have been used for the purposes of displaying fMRI images, their use in computing functional networks is novel. We describe specific techniques such as load balancing, and the use of a large number of threads to achieve the desired speedup. Our experience in utilizing the GPU for functional network computations should prove useful to the scientific community investigating fMRI as GPUs are a low-cost platform for addressing the computational bottleneck.

Paper Details

Date Published: 15 March 2011
PDF: 10 pages
Proc. SPIE 7962, Medical Imaging 2011: Image Processing, 79624L (15 March 2011); doi: 10.1117/12.878368
Show Author Affiliations
A. Ravishankar Rao, IBM Thomas T.J. Watson Research Ctr. (United States)
Rajesh Bordawekar, IBM Thomas T.J. Watson Research Ctr. (United States)
Guillermo Cecchi, IBM Thomas T.J. Watson Research Ctr. (United States)


Published in SPIE Proceedings Vol. 7962:
Medical Imaging 2011: Image Processing
Benoit M. Dawant; David R. Haynor, Editor(s)

© SPIE. Terms of Use
Back to Top