A Functional Connectivity Inspired Approach to Non-Local fMRI Analysis
2012 (English)In: Proceedings of the 19th IEEE International Conference on Image Processing (ICIP), 2012, IEEE conference proceedings, 2012, 1245-1248 p.Conference paper (Other academic)
We propose non-local analysis of functional magnetic resonanceimaging (fMRI) data in order to detect more brain activity.Our non-local approach combines the ideas of regularfMRI analysis with those of functional connectivity analysis,and was inspired by the non-local means algorithm thatcommonly is used for image denoising. We extend canonicalcorrelation analysis (CCA) based fMRI analysis to handlemore than one activity area, such that information fromdifferent parts of the brain can be combined. Our non-localapproach is compared to fMRI analysis by the general linearmodel (GLM) and local CCA, by using simulated as well asreal data.
Place, publisher, year, edition, pages
IEEE conference proceedings, 2012. 1245-1248 p.
, Image Processing, ISSN 1522-4880 ; 2012
fMRI, non-local, CCA, functional connectivity, GPU
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-76119DOI: 10.1109/ICIP.2012.6467092ISBN: 978-1-4673-2532-5 (online)ISBN: 978-1-4673-2534-9 (print)OAI: oai:DiVA.org:liu-76119DiVA: diva2:512489
19th IEEE International Conference on Image Processing (ICIP), 2012, Sept. 30 2012-Oct. 3, Orlando, FL, USA