Multi-subject Dictionary Learning to Segment an Atlas of Brain Spontaneous Activity

  • Gael Varoquaux
  • Alexandre Gramfort
  • Fabian Pedregosa
  • Vincent Michel
  • Bertrand Thirion
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6801)


Fluctuations in brain on-going activity can be used to reveal its intrinsic functional organization. To mine this information, we give a new hierarchical probabilistic model for brain activity patterns that does not require an experimental design to be specified. We estimate this model in the dictionary learning framework, learning simultaneously latent spatial maps and the corresponding brain activity time-series. Unlike previous dictionary learning frameworks, we introduce an explicit difference between subject-level spatial maps and their corresponding population-level maps, forming an atlas. We give a novel algorithm using convex optimization techniques to solve efficiently this problem with non-smooth penalties well-suited to image denoising. We show on simulated data that it can recover population-level maps as well as subject specificities. On resting-state fMRI data, we extract the first atlas of spontaneous brain activity and show how it defines a subject-specific functional parcellation of the brain in localized regions.


Independent Component Analysis Observation Noise Proximal Operator Sparse Principal Component Analysis Dictionary Element 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Archambeau, C., Bach, F.: Sparse probabilistic projections. In: Adv. NIPS (2008)Google Scholar
  2. 2.
    Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM Journal on Imaging Sciences 2(1), 183 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Beckmann, C.F., Smith, S.M.: Probabilistic independent component analysis for functional magnetic resonance imaging. Trans. Med. Im. 23, 137 (2004)CrossRefGoogle Scholar
  4. 4.
    Bell, A., Sejnowski, T.: An information-maximization approach to blind separation and blind deconvolution. Neur. Comp. 7, 1129 (1995)CrossRefGoogle Scholar
  5. 5.
    Biswal, B., Mennes, M., Zuo, X., Gohel, S., Kelly, C., Smith, S., Beckmann, C., Adelstein, J., Buckner, R., Colcombe, S., et al.: Toward discovery science of human brain function. Proc. Ntl. Acad. Sci. 107, 4734 (2010)CrossRefGoogle Scholar
  6. 6.
    Calhoun, V.D., Adali, T., Pearlson, G.D., Pekar, J.J.: A method for making group inferences from fMRI data using independent component analysis. Hum. Brain Mapp. 14, 140 (2001)CrossRefGoogle Scholar
  7. 7.
    Chen, S., Donoho, D., Saunders, M.: Atomic decomposition by basis pursuit. SIAM Review 43, 129 (2001)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Combettes, P., Pesquet, J.: A proximal decomposition method for solving convex variational inverse problems. Inverse Problems 24, 065014 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Damoiseaux, J.S., Rombouts, S.A.R.B., Barkhof, F., Scheltens, P., Stam, C.J., Smith, S.M., Beckmann, C.F.: Consistent resting-state networks across healthy subjects. Proc. Natl. Acad. Sci. 103, 13848 (2006)CrossRefGoogle Scholar
  10. 10.
    Daubechies, I., Roussos, E., Takerkart, S., Benharrosh, M., Golden, C., D’Ardenne, K., Richter, W., Cohen, J.D., Haxby, J.: Independent component analysis for brain fMRI does not select for independence. Proc. Natl. Acad. Sci. 106, 10415 (2009)CrossRefGoogle Scholar
  11. 11.
    Donoho, D.: De-noising by soft-thresholding. Trans. Inf. Theory 41, 613 (1995), MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Golland, P., Golland, Y., Malach, R.: Detection of spatial activation patterns as unsupervised segmentation of fMRI data. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part I. LNCS, vol. 4791, pp. 110–118. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  13. 13.
    Hebiri, M., Van De Geer, S.A.: The Smooth-Lasso and other ℓ1 + ℓ2-penalized methods. ArXiv:1003.4885 (2010),
  14. 14.
    Hyvärinen, A., Oja, E.: Independent component analysis: algorithms and applications. Neural Networks 13, 411 (2000)CrossRefGoogle Scholar
  15. 15.
    Kettenring, J.R.: Canonical analysis of several sets of variables. Biometrika 58, 433 (1971)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Kreutz-Delgado, K., Murray, J., Rao, B., Engan, K., Lee, T., Sejnowski, T.: Dictionary learning algorithms for sparse representation. Neur. Comp. 15, 349 (2003)CrossRefzbMATHGoogle Scholar
  17. 17.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online learning for matrix factorization and sparse coding. Journal of Machine Learning Research 11, 19 (2010)MathSciNetzbMATHGoogle Scholar
  18. 18.
    Mairal, J., Jenatton, R., Obozinski, G., Bach, F.: Network flow algorithms for structured sparsity. In: Adv. NIPS (2010)Google Scholar
  19. 19.
    McHugh, J.: Algorithmic Graph Theory. Prentice-Hall, Englewood Cliffs (1990)zbMATHGoogle Scholar
  20. 20.
    Minka, T.: Automatic choice of dimensionality for PCA. In: Adv. NIPS, p. 598 (2001)Google Scholar
  21. 21.
    Sigg, C., Buhmann, J.: Expectation-maximization for sparse and non-negative PCA. In: Proc. ICML (2008)Google Scholar
  22. 22.
    Smith, S., Fox, P., Miller, K., Glahn, D., Fox, P., Mackay, C., Filippini, N., Watkins, K., Toro, R., Laird, A., et al.: Correspondence of the brain’s functional architecture during activation and rest. Proc. Natl. Acad. Sci. 106, 13040 (2009)CrossRefGoogle Scholar
  23. 23.
    Tipping, M., Bishop, C.: Probabilistic principal component analysis. Journal of the Royal Statistical Society. Series B, Statistical Methodology, 611 (1999)Google Scholar
  24. 24.
    Varoquaux, G., Baronnet, F., Kleinschmidt, A., Fillard, P., Thirion, B.: Detection of brain functional-connectivity difference in post-stroke patients using group-level covariance modeling. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6361, pp. 200–208. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  25. 25.
    Varoquaux, G., Keller, M., Poline, J., Ciuciu, P., Thirion, B.: ICA-based sparse features recovery from fMRI datasets. In: ISBI, p. 1177 (2010)Google Scholar
  26. 26.
    Wainwright, M.: Sharp thresholds for high-dimensional and noisy sparsity recovery using ℓ1-constrained quadratic programming. Trans. Inf. Theory 55, 2183 (2009)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Gael Varoquaux
    • 1
    • 2
    • 3
  • Alexandre Gramfort
    • 2
    • 3
  • Fabian Pedregosa
    • 2
    • 3
  • Vincent Michel
    • 2
    • 3
  • Bertrand Thirion
    • 2
    • 3
  1. 1.INSERM U992 Cognitive Neuroimaging unitFrance
  2. 2.Parietal teamINRIASaclayFrance
  3. 3.LNAO/NeuroSpin, CEA SaclayGif-sur-Yvette, cedexFrance

Personalised recommendations