Functional MRI Analysis by a Novel Spatiotemporal ICA Algorithm

  • Fabian J. Theis
  • Peter Gruber
  • Ingo R. Keck
  • Elmar W. Lang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3696)

Abstract

Data sets acquired from functional magnetic resonance imaging (fMRI) contain both spatial and temporal structures. In order to blindly extract underlying activities, the common approach however only uses either spatial or temporal independence. More convincing results can be achieved by requiring the transformed data to be as independent as possible in both domains. First introduced by Stone, spatiotemporal independent component analysis (ICA) is a promising algorithm for fMRI decomposition. We propose an algebraic spatiotemporal ICA algorithm with increased performance and robustness. The feasibility of the algorithm is demonstrated in an application to the analysis of an fMRI data sets of a human brain performing an auditory task.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cardoso, J.-F., Souloumiac, A.: Blind beamforming for non gaussian signals. IEE Proceedings - F 140(6), 362–370 (1993)Google Scholar
  2. 2.
    Cardoso, J.-F., Souloumiac, A.: Jacobi angles for simultaneous diagonalization. SIAM J. Mat. Anal. Appl. 17(1), 161–164 (1995)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Comon, P.: Independent component analysis - a new concept? Signal Processing 36, 287–314 (1994)MATHCrossRefGoogle Scholar
  4. 4.
    Stone, J.V., Porrill, J., Porter, N.R., Wilkinson, I.W.: Spatiotemporal independent component analysis of event-related fmri data using skewed probability density functions. NeuroImage 15(2), 407–421 (2002)CrossRefGoogle Scholar
  5. 5.
    Theis, F.J.: A new concept for separability problems in blind source separation. Neural Computation 16, 1827–1850 (2004)MATHCrossRefGoogle Scholar
  6. 6.
    Theis, F.J., Gruber, P., Keck, I.R., Meyer-Bäse, A., Lang, E.W.: Spatiotemporal blind source separation using double-sided approximate joint diagonalization. In: Proc. EUSIPCO 2005 accepted, Antalya, Turkey (2005)Google Scholar
  7. 7.
    Yeredor, A.: Non-orthogonal joint diagonalization in the leastsquares sense with application in blind source separation. IEEE Trans. Signal Processing 50(7), 1545–1553 (2002)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Fabian J. Theis
    • 1
  • Peter Gruber
    • 1
  • Ingo R. Keck
    • 1
  • Elmar W. Lang
    • 1
  1. 1.Institute of BiophysicsUniversity of RegensburgRegensburgGermany

Personalised recommendations