Advertisement

Monte Carlo Expectation Maximization with Hidden Markov Models to Detect Functional Networks in Resting-State fMRI

  • Wei Liu
  • Suyash P. Awate
  • Jeffrey S. Anderson
  • Deborah Yurgelun-Todd
  • P. Thomas Fletcher
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7009)

Abstract

We propose a novel Bayesian framework for partitioning the cortex into distinct functional networks based on resting-state fMRI. Spatial coherence within the network clusters is modeled using a hidden Markov random field prior. The normalized time-series data, which lie on a high-dimensional sphere, are modeled with a mixture of von Mises-Fisher distributions. To estimate the parameters of this model, we maximize the posterior using a Monte Carlo expectation maximization (MCEM) algorithm in which the intractable expectation over all possible labelings is approximated using Monte Carlo integration. We show that MCEM solutions on synthetic data are superior to those computed using a mode approximation of the expectation step. Finally, we demonstrate on real fMRI data that our method is able to identify visual, motor, salience, and default mode networks with considerable consistency between subjects.

Keywords

Default Mode Network Functional Network Posterior Cingulate Cortex Monte Carlo Integration Iterate Conditional Mode 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Banerjee, A., Dhillon, I., Ghosh, J., Sra, S.: Clustering on the unit hypersphere using von Mises-Fisher distributions. J. Machine Learning Res. 6(2), 1345 (2006)MathSciNetzbMATHGoogle Scholar
  2. 2.
    Beckmann, C., Smith, S.: Tensorial extensions of independent component analysis for multisubject fMRI analysis. Neuroimage 25(1), 294–311 (2005)CrossRefGoogle Scholar
  3. 3.
    Descombes, X., Kruggel, F., Cramon, D.V.: Spatio-temporal fMRI analysis using Markov random fields. IEEE Trans. on Medical Imaging 17(6), 1028–1039 (1998)CrossRefGoogle Scholar
  4. 4.
    Fox, M., Greicius, M.: Clinical Applications of Resting State Functional Connectivity. Frontiers in Systems Neuroscience 4 (2010)Google Scholar
  5. 5.
    Golland, P., Lashkari, D., Venkataraman, A.: Spatial patterns and functional profiles for discovering structure in fMRI data. In: 42nd Asilomar Conference on Signals, Systems and Computers, pp. 1402–1409 (2008)Google Scholar
  6. 6.
    Li, S.Z.: Markov random field modeling in computer vision. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  7. 7.
    Liu, W., Zhu, P., Anderson, J., Yurgelun-Todd, D., Fletcher, P.: Spatial regularization of functional connectivity using high-dimensional markov random fields. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6362, pp. 363–370. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  8. 8.
    Raichle, M.E., MacLeod, A.M., Snyder, A.Z., Powers, W.J., Gusnard, D.A., Shulman, G.L.: A default mode of brain function. PNAS 98(2), 676–682 (2001)CrossRefGoogle Scholar
  9. 9.
    Thirion, B., Dodel, S., Poline, J.: Detection of signal synchronizations in resting-state fMRI datasets. Neuroimage 29(1), 321–327 (2006)CrossRefGoogle Scholar
  10. 10.
    Wei, G., Tanner, M.: A Monte Carlo implementation of the EM algorithm and the poor man’s data augmentation algorithms. Journal of the American Statistical Association 85(411), 699–704 (1990)CrossRefGoogle Scholar
  11. 11.
    Whitfield-Gabrieli, S.: Conn Matlab toolbox (March 2011), http://web.mit.edu/swg/software.htm

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Wei Liu
    • 1
  • Suyash P. Awate
    • 1
  • Jeffrey S. Anderson
    • 2
  • Deborah Yurgelun-Todd
    • 3
  • P. Thomas Fletcher
    • 1
  1. 1.Scientific Computing and Imaging InstituteUniversity of UtahUSA
  2. 2.Department of RadiologyUniversity of UtahUSA
  3. 3.Department of PsychiatryUniversity of UtahUSA

Personalised recommendations