Variational Solution to the Joint Detection Estimation of Brain Activity in fMRI

  • Lotfi Chaari
  • Florence Forbes
  • Thomas Vincent
  • Michel Dojat
  • Philippe Ciuciu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6892)

Abstract

We address the issue of jointly detecting brain activity and estimating underlying brain hemodynamics from functional MRI data. We adopt the so-called Joint Detection Estimation (JDE) framework that takes spatial dependencies between voxels into account. We recast the JDE into a missing data framework and derive a Variational Expectation-Maximization (VEM) algorithm for its inference. It follows a new algorithm that has interesting advantages over the previously used intensive simulation methods (Markov Chain Monte Carlo, MCMC): tests on artificial data show that the VEM-JDE is more robust to model mis-specification while additional tests on real data confirm that it achieves similar performance in much less computation time.

Keywords

Markov Chain Monte Carlo Hemodynamic Response Function fMRI Time Series Canonical Hemodynamic Response Function Markov Chain Monte Carlo Scheme 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Download to read the full conference paper text

References

  1. 1.
    Badillo, S., Vincent, T., Ciuciu, P.: Impact of the joint detection-estimation approach on random effects group studies in fMRI. In: 7th International Symposium on Biomedical Imaging, Chicago, IL, pp. 376–380 (April 2011)Google Scholar
  2. 2.
    Beal, M., Ghahramani, Z.: The variational Bayesian EM algorithm for incomplete data: with application to scoring graphical model structures. Bayesian Statistics, vol. 7, pp. 453–464. University of Oxford Press, Oxford (2003)Google Scholar
  3. 3.
    Casanova, R., Ryali, S., Serences, J., Yang, L., Kraft, R., Laurienti, P., Maldjian, J.: The impact of temporal regularization on estimates of the BOLD hemodynamic response function: a comparative analysis. Neuroimage 40(4), 1606–1618 (2008)CrossRefGoogle Scholar
  4. 4.
    Celeux, G., Forbes, F., Peyrard, N.: EM procedures using mean field-like approximations for Markov model-based image segmentation. Pat. Rec. 36, 131–144 (2003)CrossRefMATHGoogle Scholar
  5. 5.
    Friston, K., Jezzard, P., Turner, R.: Analysis of functional MRI time-series. Hum. Brain Mapp. 1, 153–171 (1994)CrossRefGoogle Scholar
  6. 6.
    Handwerker, D.A., Ollinger, J.M., D’Esposito, M.: Variation of BOLD hemodynamic responses across subjects and brain regions and their effects on statistical analyses. Neuroimage 21(4), 1639–1651 (2004)CrossRefGoogle Scholar
  7. 7.
    Kershaw, J., Ardekani, B.A., Kanno, I.: Application of Bayesian inference to fMRI data analysis. IEEE Trans. Med. Imag. 18(12), 1138–1153 (1999)CrossRefGoogle Scholar
  8. 8.
    Makni, S., Beckmann, C., Smith, S., Woolrich, M.: Bayesian deconvolution of fMRI data using bilinear dynamical systems. Neuroimage 42(4), 1381–1396 (2008)CrossRefGoogle Scholar
  9. 9.
    Makni, S., Idier, J., Vincent, T., Thirion, B., Dehaene-Lambertz, G., Ciuciu, P.: A fully Bayesian approach to the parcel-based detection-estimation of brain activity in fMRI. Neuroimage 41(3), 941–969 (2008)CrossRefGoogle Scholar
  10. 10.
    Ogawa, S., Lee, T.M., Kay, A.R., Tank, D.W.: Brain magnetic resonance imaging with contrast dependent on blood oxygenation. Nat. Acad. Sci. 87, 9868–9872 (1990)CrossRefGoogle Scholar
  11. 11.
    Penny, W.D., Kiebel, S., Friston, K.J.: Variational Bayesian inference for fMRI time series. Neuroimage 19(3), 727–741 (2003)CrossRefGoogle Scholar
  12. 12.
    Pinel, P., Thirion, B., Mériaux, S., Jobert, A., Serres, J., Le Bihan, D., Poline, J.B., Dehaene, S.: Fast reproducible identification and large-scale databasing of individual functional cognitive networks. BMC Neurosci. 8(1), 91 (2007)CrossRefGoogle Scholar
  13. 13.
    Vincent, T., Risser, L., Ciuciu, P.: Spatially adaptive mixture modeling for analysis of within-subject fMRI time series. IEEE Trans. Med. Imag. 29, 1059–1074 (2010)CrossRefGoogle Scholar
  14. 14.
    Woolrich, M., Behrens, T.: Variational Bayes inference of spatial mixture models for segmentation. IEEE Trans. Med. Imag. 25(10), 1380–1391 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Lotfi Chaari
    • 1
    • 2
  • Florence Forbes
    • 1
    • 2
  • Thomas Vincent
    • 3
  • Michel Dojat
    • 2
    • 4
  • Philippe Ciuciu
    • 3
  1. 1.INRIA, MISTISGrenobleFrance
  2. 2.Grenoble University, LJKGrenobleFrance
  3. 3.CEA/DSV/I2BM/Neurospin, LNAOFrance
  4. 4.INSERM, U836, GINGrenobleFrance

Personalised recommendations