Multispectral Image Registration Based on Local Canonical Correlation Analysis

  • Mattias P. Heinrich
  • Bartłomiej W. Papież
  • Julia A. Schnabel
  • Heinz Handels
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8673)


Medical scans are today routinely acquired using multiple sequences or contrast settings, resulting in multispectral data. For the automatic analysis of this data, the evaluation of multispectral similarity is essential. So far, few concepts have been proposed to deal in a principled way with images containing multiple channels. Here, we present a new approach based on a well known statistical technique: canonical correlation analysis (CCA). CCA finds a mapping of two multidimensional variables into two new bases, which best represent the true underlying relations of the signals. In contrast to previously used metrics, it is therefore able to find new correlations based on linear combinations of multiple channels. We extend this concept to efficiently model local canonical correlation (LCCA) between image patches. This novel, more general similarity metric can be applied to images with an arbitrary number of channels. The most important property of LCCA is its invariance to affine transformations of variables. When used on local histograms, LCCA can also deal with multimodal similarity. We demonstrate the performance of our concept on challenging clinical multispectral datasets.


multichannel canonical correlation multimodal MRI 


  1. 1.
    Peyrat, J.M., Delingette, H., Sermesant, M., Xu, C., Ayache, N.: Registration of 4D cardiac CT sequences under trajectory constraints with multichannel diffeomorphic demons. IEEE Transactions on Medical Imaging 29(7), 1351–1368 (2010)CrossRefGoogle Scholar
  2. 2.
    Rohde, G., Pajevic, S., Pierpaoli, C., Basser, P.: A comprehensive approach for multi-channel image registration. In: Gee, J.C., Maintz, J.B.A., Vannier, M.W. (eds.) WBIR 2003. LNCS, vol. 2717, pp. 214–223. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  3. 3.
    Avants, B.B., Epstein, C.L., Grossman, M., Gee, J.C.: Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Med. Imag. Anal. 12(1), 26–41 (2008)CrossRefGoogle Scholar
  4. 4.
    Ruiz-Alzola, J., Westin, C., Warfield, S., Alberola, C., Maier, S., Kikinis, R.: Nonrigid registration of 3D tensor medical data. Med. Imag. Anal. 6(2), 143–161 (2002)CrossRefGoogle Scholar
  5. 5.
    Taquet, M., Macq, B., Warfield, S.K.: A generalized correlation coefficient: Application to DTI and multi-fiber DTI. In: MMBIA 2012, pp. 9–14. IEEE (2012)Google Scholar
  6. 6.
    Wein, W., Brunke, S., Khamene, A., Callstrom, M.R., Navab, N.: Automatic CT-ultrasound registration for diagnostic imaging and image-guided intervention. Med. Imag. Anal. 12(5), 577–585 (2008)CrossRefGoogle Scholar
  7. 7.
    Iglesias, J.E., Konukoglu, E., Zikic, D., Glocker, B., Van Leemput, K., Fischl, B.: Is synthesizing MRI contrast useful for inter-modality analysis? In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part I. LNCS, vol. 8149, pp. 631–638. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  8. 8.
    Guimond, A., Roche, A., Ayache, N., Meunier, J.: Three-dimensional multimodal brain warping using the demons algorithm and adaptive intensity corrections. IEEE Transactions on Medical Imaging 20(1), 58–69 (2001)CrossRefGoogle Scholar
  9. 9.
    Li, Y., Verma, R.: Multichannel image registration by feature-based information fusion. IEEE Transactions on Medical Imaging 30(3), 707–720 (2011)CrossRefGoogle Scholar
  10. 10.
    Hotelling, H.: Relations between two sets of variates. Biometrika 28(3-4), 321–377 (1936)CrossRefzbMATHGoogle Scholar
  11. 11.
    Friman, O., Cedefamn, J., Lundberg, P., Borga, M., Knutsson, H.: Detection of neural activity in functional MRI using canonical correlation analysis. Magnetic Resonance in Medicine 45(2), 323–330 (2001)CrossRefGoogle Scholar
  12. 12.
    Suarez, R.O., Commowick, O., Prabhu, S.P., Warfield, S.K.: Automated delineation of white matter fiber tracts with a multiple region-of-interest approach. NeuroImage 59(4), 3690–3700 (2012)CrossRefGoogle Scholar
  13. 13.
    He, K., Sun, J., Tang, X.: Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(6), 1397–1409 (2013)CrossRefGoogle Scholar
  14. 14.
    Heinrich, M.P., Papież, B.W., Schnabel, J.A., Handels, H.: Non-parametric discrete registration with convex optimisation. In: Ourselin, S., Modat, M. (eds.) WBIR 2014. LNCS, vol. 8545, pp. 51–61. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  15. 15.
    Mendrik, A.: Evaluation framework for MR brain image segmentation. In: MICCAI Grand Challenge (2013),
  16. 16.
    Landman, B., Warfield, S.: Segmentation: Algorithms, theory and applications. In: MICCAI SATA (2013),
  17. 17.
    Ourselin, S., Roche, A., Prima, S., Ayache, N.: Block matching: A general framework to improve robustness of rigid registration of medical images. In: Delp, S.L., DiGoia, A.M., Jaramaz, B. (eds.) MICCAI 2000. LNCS, vol. 1935, pp. 557–566. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  18. 18.
    Heinrich, M.P., Jenkinson, M., Papież, B.W., Brady, S.M., Schnabel, J.A.: Towards realtime multimodal fusion for image-guided interventions using self-similarities. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part I. LNCS, vol. 8149, pp. 187–194. Springer, Heidelberg (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Mattias P. Heinrich
    • 1
  • Bartłomiej W. Papież
    • 2
  • Julia A. Schnabel
    • 2
  • Heinz Handels
    • 1
  1. 1.Institute of Medical InformaticsUniversity of LübeckGermany
  2. 2.Institute of Biomedical Engineering, Department of EngineeringUniversity of OxfordUK

Personalised recommendations