Nonlinear Regression on Riemannian Manifolds and Its Applications to Neuro-Image Analysis

  • Monami BanerjeeEmail author
  • Rudrasis Chakraborty
  • Edward Ofori
  • David Vaillancourt
  • Baba C. Vemuri
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9349)


Regression in its most common form where independent and dependent variables are in ℝ n is a ubiquitous tool in Sciences and Engineering. Recent advances in Medical Imaging has lead to a wide spread availability of manifold-valued data leading to problems where the independent variables are manifold-valued and dependent are real-valued or vice-versa. The most common method of regression on a manifold is the geodesic regression, which is the counterpart of linear regression in Euclidean space. Often, the relation between the variables is highly complex, and existing most commonly used geodesic regression can prove to be inaccurate. Thus, it is necessary to resort to a non-linear model for regression. In this work we present a novel Kernel based non-linear regression method when the mapping to be estimated is either from M → ℝ n or ℝ n  → M, where M is a Riemannian manifold. A key advantage of this approach is that there is no requirement for the manifold-valued data to necessarily inherit an ordering from the data in ℝ n . We present several synthetic and real data experiments along with comparisons to the state-of-the-art geodesic regression method in literature and thus validating the effectiveness of the proposed algorithm.


Riemannian Manifold Support Vector Regression Essential Tremor Canonical Correlation Analysis Nonlinear Regression Technique 
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.
    Adachi, M., Hudson, K.: Embeddings and immersions. American Mathematical Soc. (2012)Google Scholar
  2. 2.
    Davis, B.C., Fletcher, P.T., et al.: Population shape regression from random design data. In: IEEE ICCV, pp. 1–7 (2007)Google Scholar
  3. 3.
    Deng, Y., Rangarajan, A., et al.: A Riemannian framework for matching point clouds represented by the Schrodinger distance transform. In: IEEE CVPR, pp. 3756–3761 (2014)Google Scholar
  4. 4.
    Drucker, H., Burges, C.J., et al.: Support vector regression machines. In: NIPS, pp. 155–161 (1997)Google Scholar
  5. 5.
    Du, J., Goh, A., et al.: Geodesic regression on orientation distribution functions with its application to an aging study. Neuroimage, 416–426 (2014)Google Scholar
  6. 6.
    Fletcher, P., Lu, C., et al.: Principal geodesic analysis for the study of nonlinear statistics of shape. In: IEEE TMI, pp. 995–1005 (2004)Google Scholar
  7. 7.
    Fletcher, P.T.: Geodesic regression and the theory of least squares on Riemannian manifolds. International Journal of Computer Vision, 171–185 (2013)Google Scholar
  8. 8.
    Fréchet, M.: Les éléments aléatoires de nature quelconque dans un espace distancié. Annales de l’institut Henri Poincaré, pp. 215–310 (1948)Google Scholar
  9. 9.
    Hinkle, J., Muralidharan, P., Fletcher, P.T., Joshi, S.: Polynomial regression on Riemannian manifolds. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 1–14. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  10. 10.
    Ho, J., Cheng, G., et al.: Recursive Karcher expectation estimators and geometric law of large numbers. In: AISTATS, pp. 325–332 (2013)Google Scholar
  11. 11.
    Ho, J., Xie, Y., et al.: On a nonlinear generalization of sparse coding and dictionary learning. In: ICML, pp. 1480–1488 (2013)Google Scholar
  12. 12.
    Hong, Y., Kwitt, R., Singh, N., Davis, B., Vasconcelos, N., Niethammer, M.: Geodesic regression on the Grassmannian. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part II. LNCS, vol. 8690, pp. 632–646. Springer, Heidelberg (2014)Google Scholar
  13. 13.
    Hong, Y., Singh, N., Kwitt, R., Niethammer, M.: Time-warped geodesic regression. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part II. LNCS, vol. 8674, pp. 105–112. Springer, Heidelberg (2014)Google Scholar
  14. 14.
    Kendall, D.: A survey of the statistical theory of shape. Stat. Science, 87–99 (1989)Google Scholar
  15. 15.
    Kim, H.J., Adluru, N., Bendlin, B.B., Johnson, S.C., Vemuri, B.C., Singh, V.: Canonical Correlation analysis on Riemannian Manifolds and its Applications. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part II. LNCS, vol. 8690, pp. 251–267. Springer, Heidelberg (2014)Google Scholar
  16. 16.
    Kim, H.J., Bendlin, B.B., et al.: MGLM on Riemannian manifolds with applications to statistical analysis of diffusion weighted images. In: IEEE CVPR, pp. 2705–2712 (2014)Google Scholar
  17. 17.
    Marcus, D.S., Wang, T.H., et al.: OASIS: cross-sectional mri data in young, middle aged, nondemented, and demented older adults. Journal of Cognitive Neuroscience, 1498–1507 (2007)Google Scholar
  18. 18.
    Samir, C., Absil, P.-A., et al.: A gradient-descent method for curve fitting on Riemannian manifolds. Foundations of Comput. Mathematics, 49–73 (2012)Google Scholar
  19. 19.
    Singh, N., Niethammer, M.: Splines for diffeomorphic image regression. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part II. LNCS, vol. 8674, pp. 121–129. Springer, Heidelberg (2014)Google Scholar
  20. 20.
    Vaillancourt, D., Spraker, M., et al.: High-resolution diffusion tensor imaging in the substantia nigra of de novo parkinson disease. Neurology, 1378–1384 (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Monami Banerjee
    • 1
    Email author
  • Rudrasis Chakraborty
    • 1
  • Edward Ofori
    • 2
  • David Vaillancourt
    • 2
  • Baba C. Vemuri
    • 1
  1. 1.Department of CISEUniversity of FloridaGainesvilleUSA
  2. 2.Department of Applied Physiology and KinesiologyUniversity of FloridaGainesvilleUSA

Personalised recommendations