Clustering inter-subject correlation matrices in functional magnetic resonance imaging

Jukka Pekka Kauppi*, Iiro P. Jääskeläinen, Mikko Sams, Jussi Tohka

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

6 Citations (Scopus)

Abstract

We present a novel clustering method to probe inter-subject variability in functional magnetic resonance imaging (tMRI) data acquired in complex audiovisual stimulus environments, such as during watching movies. We calculate voxel-wise inter-subject correlation matrices across individual subject tMRI time-series and cluster them over the cerebral cortex. We address correlation matrix clustering problem and modify a standard K-means algorithm to cope better with spurious observations. We investigate suitability of the modified K-means with hierarchical clustering based postprocessing to correlation matrix clustering with several artificially generated data sets. We also present clustering of tMRI movie data. Preliminary results suggest that our methodology can be a valuable tool to investigate inter-subject variability in brain activity in different brain regions, such as prefrontal cortex.

Original languageEnglish
Title of host publicationITAB 2010 - 10th International Conference on Information Technology and Applications in Biomedicine
Subtitle of host publicationEmerging Technologies for Patient Specific Healthcare
DOIs
Publication statusPublished - 1 Dec 2010
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Information Technology and Applications in Biomedicine: Emerging Technologies for Patient Specific Healthcare - Corfu, Greece
Duration: 2 Nov 20105 Nov 2010
Conference number: 10

Conference

ConferenceInternational Conference on Information Technology and Applications in Biomedicine
Abbreviated titleITAB 2010
Country/TerritoryGreece
CityCorfu
Period02/11/201005/11/2010

Fingerprint

Dive into the research topics of 'Clustering inter-subject correlation matrices in functional magnetic resonance imaging'. Together they form a unique fingerprint.

Cite this