Nonlinear Estimation and Modeling of fMRI Data Using Spatio-temporal Support Vector Regression

  • Yongmei Michelle Wang
  • Robert T. Schultz
  • R. Todd Constable
  • Lawrence H. Staib
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2732)

Abstract

This paper presents a new and general nonlinear framework for fMRI data analysis based on statistical learning methodology: support vector machines. Unlike most current methods which assume a linear model for simplicity, the estimation and analysis of fMRI signal within the proposed framework is nonlinear, which matches recent findings on the dynamics underlying neural activity and hemodynamic physiology. The approach utilizes spatio-temporal support vector regression (SVR), within which the intrinsic spatio-temporal autocorrelations in fMRI data are reflected. The novel formulation of the problem allows merging model-driven with data-driven methods, and therefore unifies these two currently separate modes of fMRI analysis. In addition, multiresolution signal analysis is achieved and developed. Other advantages of the approach are: avoidance of interpolation after motion estimation, embedded removal of low-frequency noise components, and easy incorporation of multi-run, multi-subject, and multi-task studies into the framework.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Backfriender, W., Baumgartner, R., Stamal, M., Moser, E., Bergmann, H.: Quantification of intensity variations in functional MR images using rotated principal components. Physics in Medicine and Biology 41, 1425–1438 (1996)CrossRefGoogle Scholar
  2. 2.
    Birn, R.M., Saad, Z.S., Bandettini, P.A.: Spatial heterogeneity of the nonlinear dynamics in the fMRI BOLD response. Neuroimage 14, 817–826 (2001)CrossRefGoogle Scholar
  3. 3.
    Boulanouar, K., Roux, F., Celsis, P.: Modeling brain hemodynamic response in functional MRI using vector support method. In: Cognitive Neuroscience Society Annual Meeting (2001) (abstract) Google Scholar
  4. 4.
    Boynton, G.M., Engel, S.A., Glover, G.H., Heeger, D.J.: Linear systems analysis of functional magnetic resonance imaging in human V1. J. Neuroscience 16, 4207–4221 (1996)Google Scholar
  5. 5.
    Collobert, R., Bengio, S.: SVMTorch: Support vector machines for large-scale regression problems. Journal of Machine Learning Research 1, 143–160 (2001)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Constable, R.T., Skudlarski, P., Gore, J.C.: An ROC approach for evaluating functional brain MR imaging and postprocessing protocols. Magnetic Resonance in Medicine 34, 57–64 (1995)CrossRefGoogle Scholar
  7. 7.
    Descombes, X., Kruggel, F., von Cramon, D.Y.: fMRI signal restoration using a spatiotemporal Markov random field preserving transitions. Neuroimage 8, 340–349 (1998)CrossRefGoogle Scholar
  8. 8.
    Friston, K.J., et al.: Statistical parametric maps in functional imaging: A general linear approach. Human Brain Mapping 2, 189–210 (1995)CrossRefGoogle Scholar
  9. 9.
    Friston, K.J., Holmes, A.P., Poline, J.-B., Grasby, P.J., Williams, S.C.R., Frackowiak, R.S.J.: Analysis of fMRI time-series revisited. Neuroimage 2, 45–53 (1995)CrossRefGoogle Scholar
  10. 10.
    Golland, P., et al.: Discriminative analysis for image-based studies. In: Intl. Conf. on Medical Image Computing and Computer-Assisted Intervention, pp. 508–515 (2002)Google Scholar
  11. 11.
    Gretton, A., Doucer, A., Herbrich, R., Rayner, P.J.W., Scholkopf, B.: Support vector regression for black-box system identification. In: IEEE Workshop on Statistical Signal Processing, pp. 341–344 (2001)Google Scholar
  12. 12.
    Grootoonk, S., Hutton, C., Ashburner, J., Howseman, A.M., Josephs, O., Rees, G., Friston, K.J., Turner, R.: Characterization and correction of interpolation effects in the realignment of fMRI time series. Neuroimage 11, 49–57 (2000)CrossRefGoogle Scholar
  13. 13.
    Hartvig, N.V., Jensen, J.L.: Spatial mixture modeling of fMRI data. Human Brain Mapping 11, 233–248 (2000)CrossRefGoogle Scholar
  14. 14.
    Johnson, R.A., Bhattacharyya, G.K.: Statistics: Principles and Methods. John Wiley & Sons, Inc., Chichester (2001)Google Scholar
  15. 15.
    Katanoda, K., Matsuda, Y., Sugishita, M.: A spatio-temporal regression model for the analysis of functional MRI data. Neuroimage 17, 1415–1428 (2002)CrossRefGoogle Scholar
  16. 16.
    Laird, A.R., Rogers, B.P., Meyerand, M.E.: Investigating the nonlinearity of fMRI activation data. In: Proc. Second Joint EMBS / BMES Conference, pp. 23–26 (2002)Google Scholar
  17. 17.
    Lang, N.: Statistical procedures for functional MRI. In: Moonen, C., Bandettini, P. (eds.) Functional MRI, pp. 301–355. Springer, Heidelberg (1999)Google Scholar
  18. 18.
    Li, Y., Gong, S., Liddell, H.: Support vector regression and classification based multiview face detection and recognition. In: Proc. Fourth IEEE Intl. Conf. on Automatic Face and Gesture Recognition, pp. 300–305 (2000)Google Scholar
  19. 19.
    Marchini, J.L., Ripley, B.D.: A new statistical approach to detecting significant activation in functional MRI. Neuroimage 12, 366–380 (2000)CrossRefGoogle Scholar
  20. 20.
    McKeown, M., Makeig, S., Brown, G., Jung, T., Kindermann, S., Bell, A., Sejnowski, T.: Analysis of fMRI data by blind separation into independent spatial components. Human Brain Mapping 6, 160–188 (1998)CrossRefGoogle Scholar
  21. 21.
    Miller, K.L., Luh, W.M., Lie, T.L., Martinez, A., Obata, T., Wong, E.C., Frank, L.R., Buxton, R.B.: Nonlinear temporal dynamics of the cerebral blood flow response. Human Brain Mapping 13, 1–12 (2001)CrossRefGoogle Scholar
  22. 22.
    Mukherjee, S., Osuna, E., Girosi, F.: Nonlinear prediction of chaotic time series using support vector machines. In: Proc. IEEE Workshop on Neural Networks and Signal Processing, vol. VII, pp. 511–520 (1997) Google Scholar
  23. 23.
    Ogawa, S., Lee, T.M., Nayak, A.S., Glynn, P.: Oxygenation-sensitive contrast in magnetic resonance image of rodent brain of high magnetic fields. Magnetic Resonance in Medicine 14, 68–78 (1990)CrossRefGoogle Scholar
  24. 24.
    Schultz, R.T., et al.: The role of the fusiform face area in social cognition: Implications for the pathobiology of autism. Phil. Trans. of the Royal Society, Series B 358, 415–427 (2003)CrossRefGoogle Scholar
  25. 25.
    Skudlarski, P., Constable, R.T., Gore, J.C.: ROC analysis of statistical methods used in functional MRI: Individual subjects. Neuroimage 9, 311–329 (1999)CrossRefGoogle Scholar
  26. 26.
    Smola, A.J., Scholkopf, B.: A Tutorial on Support Vector Regression. NeuroCOLT Technical Report NC-TR-98-030, Royal Holloway College, University of London, UK (1998)Google Scholar
  27. 27.
    Vapnik, V.N.: Statistical Leaning Theory. John Wiley & Sons, New York (1998)Google Scholar
  28. 28.
    Zarahn, E., Aguirre, G.K., D’Esposito, M.: Empirical analyses of BOLD fMRI statistics. I. Spatially unsmoohed data collected under null-hypothesis conditions. Neuroimage 5, 179–197 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Yongmei Michelle Wang
    • 1
  • Robert T. Schultz
    • 2
  • R. Todd Constable
    • 1
  • Lawrence H. Staib
    • 1
  1. 1.Department of Diagnostic Radiology 
  2. 2.Child Study CenterYale University School of MedicineNew HavenUSA

Personalised recommendations