DIMENSIONALITY REDUCTION FOR IMPROVED SOURCE SEPARATION IN FMRI DATA

Rudolph L. Mappus IV, David Minnen, Charles Lee Isbell Jr.

2008

Abstract

Functional magnetic resonance imaging (fMRI) captures brain activity by measuring the hemodynamic response. It is often used to associate specific brain activity with specific behavior or tasks. The analysis of fMRI scans seeks to recover this association by differentiating between task and non-task related activation and by spatially isolating brain activity. In this paper, we frame the association problem as a convolution of activation patterns. We project fMRI scans into a low dimensional space using manifold learning techniques. In this subspace, we transform the time course of each projected fMRI volume into the frequency domain. We use independent component analysis to discover task related activations. The combination of these methods discovers sources that show stronger correlation with the activation reference function than previous methods.

References

  1. Anemuller, J., Sejnowski, T., and Makeig, S. (2003). Complex independent component analysis of frequencydomain electroencephalographic data. Neural Networks, 16:1311-1323.
  2. Belkin, M. and Niyogi, P. (2003). Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation, 15:1373-1396.
  3. Bingham, E. and Hyvarinen, A. (2000). A fast fixedpoint algorithm for independent component analysis of complex valued signals. International Journal of Neural Systems, 10(1):1-8.
  4. Coifman, R. R. and Lafon, S. (2006). Diffusion maps. Applied and Computational Harmonic Analysis, 21:5- 30.
  5. Dogil, G., Ackerman, H., Grodd, W., Haider, H., Kamp, H., Mayer, J., Reicker, A., and Wildgruber, D. (2002). The speaking brain: a tutorial introduction to fmri experiments in the production of speech, prosody, and syntax. Journal of Neurolinguistics, 15(1):59-90.
  6. Friston, K. (2003). Experimental design and statistical parametric mapping. In et al., F., editor, Human brain function. Academic Press, 2nd edition.
  7. Hurd, M. (2000). Functional neuroimaging motor study.
  8. Josephs, O., Turner, R., and Friston, K. (1997). Eventrelated fmri. Human Brain Mapping, 5(4):243-248.
  9. McKeown, M. J., Makeig, S., Brown, G. G., Jung, T. P., Kindermann, S. S., Bell, A. J., and Sejnowski, T. J. (1998). Analysis of fmri data by blind separation into independent spatial components. Human Brain Mapping, 6:160-188.
  10. Pederson, M. S., Larsen, J., Kjerns, U., and Parra, L. C. (2007). Springer handbook on speech processing and speech communication, chapter A survey on convolutive blind source separation methods. Springer Press.
  11. Postle, B. R., Berger, J. S., Taich, A. M., and D'Esposito, M. (2000). Activity in human frontal cortex associated with spatial working memory and saccadic behavior. Journal of Cognitive Neuroscience, 12 Supp. 2:2-14.
  12. Roweis, S. and Ghahramani, Z. (1999). A unifying review of linear gaussian models. Neural Computation, 11:305-345.
  13. Roweis, S. and Saul, L. (2000). Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500):2323-2326.
  14. Shen, X. and Meyer, F. G. (2006). Nonlinear dimension reduction and activation detection for fmri dataset. In IEEE, editor, Proceedings of 2006 conference on computer vision and pattern recognition workshop. IEEE.
  15. Tenenbaum, J., de Silva, V., and Langford, J. (2000). A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500):2319-2323.
Download


Paper Citation


in Harvard Style

L. Mappus IV R., Minnen D. and Lee Isbell Jr. C. (2008). DIMENSIONALITY REDUCTION FOR IMPROVED SOURCE SEPARATION IN FMRI DATA . In Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008) ISBN 978-989-8111-18-0, pages 308-313. DOI: 10.5220/0001068403080313


in Bibtex Style

@conference{biosignals08,
author={Rudolph L. Mappus IV and David Minnen and Charles Lee Isbell Jr.},
title={DIMENSIONALITY REDUCTION FOR IMPROVED SOURCE SEPARATION IN FMRI DATA},
booktitle={Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)},
year={2008},
pages={308-313},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001068403080313},
isbn={978-989-8111-18-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)
TI - DIMENSIONALITY REDUCTION FOR IMPROVED SOURCE SEPARATION IN FMRI DATA
SN - 978-989-8111-18-0
AU - L. Mappus IV R.
AU - Minnen D.
AU - Lee Isbell Jr. C.
PY - 2008
SP - 308
EP - 313
DO - 10.5220/0001068403080313