Canonical Correlation Analysis of Sub-cortical Brain Structures Using Non-rigid Registration

  • Anil Rao
  • Kola Babalola
  • Daniel Rueckert
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4057)


In this paper, we present the application of canonical correlation analysis to investigate how the shapes of different structures within the brain vary statistically relative to each other. Canonical correlation analysis is a multivariate statistical technique which extracts and quantifies correlated behaviour between two sets of vector variables. Firstly, we perform non-rigid image registration of 93 sets of 3D MR images to build sets of surfaces and correspondences for sub-cortical structures in the brain. Canonical correlation analysis is then used to extract and quantify correlated behaviour in the shapes of each pair of surfaces. The results show that correlations are strongest between neighbouring structures and reveal symmetry in the correlation strengths for the left and right sides of the brain.


Lateral Ventricle Canonical Correlation Analysis Surface Point Magnetic Resonance Spectroscopic Image Correlate Behaviour 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ashburner, J., Friston, K.J.: Voxel-based morphometry – the methods. NeuroImage 11(6), 805–821 (2000)CrossRefGoogle Scholar
  2. 2.
    Ashburner, J., Friston, K.J.: Why voxel-based morphometry should be used. NeuroImage 14(6), 1238–1243 (2001)CrossRefGoogle Scholar
  3. 3.
    Ashburner, J., Hutton, C., Frackowiak, R., Johnsrude, I., Price, C., Friston, K.: Identifying global anatomical differences: Deformation-based morphometry. Human Brain Mapping 6, 638–657 (1998)CrossRefGoogle Scholar
  4. 4.
    Bajcsy, R., Kovačič, S.: Multiresolution elastic matching. Computer Vision, Graphics and Image Processing 46, 1–21 (1989)CrossRefGoogle Scholar
  5. 5.
    Bookstein, F.L.: Voxel-based morphometry should not be used with imperfectly registered images. NeuroImage 14(6), 1452–1462 (2001)CrossRefGoogle Scholar
  6. 6.
    Bro-Nielsen, M., Gramkow, C.: Fast fluid registration of medical images. In: Höhne, K.H., Kikinis, R. (eds.) VBC 1996. LNCS, vol. 1131, pp. 267–276. Springer, Heidelberg (1996)Google Scholar
  7. 7.
    Christensen, G.E., Joshi, S.C., Miller, M.I.: Individualizing anatomical atlases of the head. In: Höhne, K.H., Kikinis, R. (eds.) VBC 1996. LNCS, vol. 1131, pp. 434–348. Springer, Heidelberg (1996)Google Scholar
  8. 8.
    Christensen, G.E., Miller, M.I., Mars, J.L., Vannier, M.W.: Automatic analysis of medical images using a deformable textbook. In: Computer Assisted Radiology, Berlin, Germany, pp. 146–151. Springer, Heidelberg (1995)Google Scholar
  9. 9.
    Chung, M.K., Worsley, K.J., Paus, T., Collins, D.L., Cherif, C., Giedd, J.N., Rapoport, J.L., Evans, A.C.: A unified statistical approach to deformation-based morphometry. NeuroImage 14(3), 595–606 (2001)CrossRefGoogle Scholar
  10. 10.
    Collins, D.L., Neelin, P., Peters, T.M., Evans, A.C.: Automatic 3D intersubject registration of MR volumetric data in standardized Talairach space. Journal of Computer Assisted Tomography 18(2), 192–205 (1994)CrossRefGoogle Scholar
  11. 11.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 484–498. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  12. 12.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active Shape Models - their training and application. Computer Vision and Image Understanding 61(1), 38–59 (1995)CrossRefGoogle Scholar
  13. 13.
    Gee, J., Reivich, M., Bajcsy, R.: Elastically deforming 3D atlas to match anatomical brain images. Journal of Computer Assisted Tomography 17(2), 225–236 (1993)CrossRefGoogle Scholar
  14. 14.
    Grenander, U., Miller, M.I.: Computational anatomy: An emerging discipline. Quarterly of Applied Mathematics 56(4), 617–694 (1998)MATHMathSciNetGoogle Scholar
  15. 15.
    Horn, B.: Closed-form solution of absolute orientation using unit quaternions. Journal of the Optical Society of America 4, 629–642 (1987)Google Scholar
  16. 16.
    Laudadio, T., Pels, P., Lathauwer, L., Hecke, P., Huffel, S.: Tissue segmentation and classification of mrsi data using canonical correlation analysis. Magnetic Resonance in Medicine 54, 1519–1529 (2005)CrossRefGoogle Scholar
  17. 17.
    Liu, T., Shen, D., Davatzikos, C.: Predictive modeling of anatomic structures using canonical correlation analysis. In: IEEE International Symposium on Biomedical Imaging (2004)Google Scholar
  18. 18.
    Mardia, K.V., Kent, J.T., Bibby, J.M.: Multivariate analysis. Academic Press, Belfast (1982)Google Scholar
  19. 19.
    Mazziotta, J., Toga, A., Evans, A., Fox, P., Lancaster, J.: A probabilistic atlas of the human brain: Theory and rationale for its developement. The international consortium for brain mapping. NeuroImage 2(2), 89–101 (1995)CrossRefGoogle Scholar
  20. 20.
    Rueckert, D., Sonoda, L.I., Hayes, C., Hill, D.L.G., Leach, M.O., Hawkes, D.J.: Non-rigid registration using free-form deformations: Application to breast MR images. IEEE Transactions on Medical Imaging 18(8), 712–721 (1999)CrossRefGoogle Scholar
  21. 21.
    Zollei, L., Panych, L., Grimson, E., Wells, W.: Exploratory identification of cardiac noise in fmri images. In: Ellis, R.E., Peters, T.M. (eds.) MICCAI 2003. LNCS, vol. 2878, pp. 475–482. Springer, Heidelberg (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Anil Rao
    • 1
  • Kola Babalola
    • 2
  • Daniel Rueckert
    • 1
  1. 1.Visual Information Processing Group, Department of ComputingImperial College LondonLondonU.K
  2. 2.Division of Image Science & Bio-medical EngineeringUniversity of ManchesterManchesterU.K

Personalised recommendations