Unsupervised Learning of Functional Network Dynamics in Resting State fMRI

  • Harini Eavani
  • Theodore D. Satterthwaite
  • Raquel E. Gur
  • Ruben C. Gur
  • Christos Davatzikos
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7917)


Research in recent years has provided some evidence of temporal non-stationarity of functional connectivity in resting state fMRI. In this paper, we present a novel methodology that can decode connectivity dynamics into a temporal sequence of hidden network “states” for each subject, using a Hidden Markov Modeling (HMM) framework. Each state is characterized by a unique covariance matrix or whole-brain network. Our model generates these covariance matrices from a common but unknown set of sparse basis networks, which capture the range of functional activity co-variations of regions of interest (ROIs). Distinct hidden states arise due to a variation in the strengths of these basis networks. Thus, our generative model combines a HMM framework with sparse basis learning of positive definite matrices. Results on simulated fMRI data show that our method can effectively recover underlying basis networks as well as hidden states. We apply this method on a normative dataset of resting state fMRI scans. Results indicate that the functional activity of a subject at any point during the scan is composed of combinations of overlapping task-positive/negative pairs of networks as revealed by our basis. Distinct hidden temporal states are produced due to a different set of basis networks dominating the covariance pattern in each state.


resting state fMRI functional connectivity temporal network dynamics 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Raichle, M.E., MacLeod, A.M., Snyder, A.Z., Powers, W.J., Gusnard, D.A., Shulman, G.L.: A default mode of brain function. Proceedings of the National Academy of Sciences 98(2), 676–682 (2001)CrossRefGoogle Scholar
  2. 2.
    Broyd, S.J., Demanuele, C., Debener, S., Helps, S.K., James, C.J., Sonuga-Barke, E.J.S., et al.: Default-mode brain dysfunction in mental disorders: a systematic review. Neuroscience and Biobehavioral Reviews 33(3), 279 (2009)CrossRefGoogle Scholar
  3. 3.
    Chang, C., Glover, G.H.: Time-frequency dynamics of resting-state brain connectivity measured with fMRI. Neuroimage 50(1), 81–98 (2010)CrossRefGoogle Scholar
  4. 4.
    Majeed, W., Magnuson, M., Hasenkamp, W., Schwarb, H., Schumacher, E.H., Barsalou, L., Keilholz, S.D.: Spatiotemporal dynamics of low frequency bold fluctuations in rats and humans. Neuroimage 54(2), 1140–1150 (2011)CrossRefGoogle Scholar
  5. 5.
    Hutchison, R.M., Womelsdorf, T., Gati, J.S., Everling, S., Menon, R.S.: Resting-state networks show dynamic functional connectivity in awake humans and anesthetized macaques. Human Brain Mapping (2012)Google Scholar
  6. 6.
    Buckner, R.L., Vincent, J.L., et al.: Unrest at rest: default activity and spontaneous network correlations. Neuroimage 37(4), 1091–1096 (2007)CrossRefGoogle Scholar
  7. 7.
    Sra, S., Cherian, A.: Generalized dictionary learning for symmetric positive definite matrices with application to nearest neighbor retrieval. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.) ECML PKDD 2011, Part III. LNCS (LNAI), vol. 6913, pp. 318–332. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  8. 8.
    Sivalingam, R., Boley, D., Morellas, V., Papanikolopoulos, N.: Positive definite dictionary learning for region covariances. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 1013–1019. IEEE (2011)Google Scholar
  9. 9.
    Baum, L.E., Petrie, T., Soules, G., Weiss, N.: A maximization technique occurring in the statistical analysis of probabilistic functions of markov chains. The Annals of Mathematical Statistics, 164–171 (1970)Google Scholar
  10. 10.
    Batmanghelich, N.K., Taskar, B., Davatzikos, C.: Generative-discriminative basis learning for medical imaging. IEEE Transactions on Medical Imaging 31(1), 51–69 (2012)CrossRefGoogle Scholar
  11. 11.
    Bishop, C.M., et al.: Pattern recognition and machine learning, vol. 4. Springer, New York (2006)zbMATHGoogle Scholar
  12. 12.
    Viterbi, A.: Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Transactions on Information Theory 13(2), 260–269 (1967)zbMATHCrossRefGoogle Scholar
  13. 13.
    Smith, S.M., Miller, K.L., Salimi-Khorshidi, G., Webster, M., Beckmann, C.F., Nichols, T.E., Ramsey, J.D., Woolrich, M.W.: Network modelling methods for fmri. Neuroimage 54(2), 875–891 (2011)CrossRefGoogle Scholar
  14. 14.
    Dosenbach, N.U.F., Fair, D.A., Miezin, F.M., Cohen, A.L., et al.: Distinct brain networks for adaptive and stable task control in humans. Proceedings of the National Academy of Sciences 104(26), 11073 (2007)CrossRefGoogle Scholar
  15. 15.
    Smith, S.M., Miller, K.L., Moeller, S., Xu, J., Auerbach, E.J., Woolrich, M.W., Beckmann, C.F., Jenkinson, M., Andersson, J., Glasser, M.F., et al.: Temporally-independent functional modes of spontaneous brain activity. Proceedings of the National Academy of Sciences 109(8), 3131–3136 (2012)CrossRefGoogle Scholar
  16. 16.
    Faisan, S., Thoraval, L., Armspach, J.P., Heitz, F.: Hidden markov multiple event sequence models: A paradigm for the spatio-temporal analysis of fmri data. Medical Image Analysis 11(1), 1 (2007)CrossRefGoogle Scholar
  17. 17.
    Janoos, F., Machiraju, R., Singh, S., Morocz, I.Á.: Spatio-temporal models of mental processes from fmri. Neuroimage 57(2), 362–377 (2011)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Harini Eavani
    • 1
  • Theodore D. Satterthwaite
    • 2
  • Raquel E. Gur
    • 2
  • Ruben C. Gur
    • 2
  • Christos Davatzikos
    • 1
  1. 1.Section of Biomedical Image Analysis, Department of RadiologyUniversity of PennsylvaniaUSA
  2. 2.Brain Behavior Laboratory, Department of PsychiatryUniversity of PennsylvaniaUSA

Personalised recommendations