Advertisement

Hierarchical Multimodal Image Registration Based on Adaptive Local Mutual Information

  • Dante De Nigris
  • Laurence Mercier
  • Rolando Del Maestro
  • D. Louis Collins
  • Tal Arbel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6362)

Abstract

We propose a new, adaptive local measure based on gradient orientation similarity for the purposes of multimodal image registration. We embed this metric into a hierarchical registration framework, where we show that registration robustness and accuracy can be improved by adapting both the similarity metric and the pixel selection strategy to the Gaussian blurring scale and to the modalities being registered. A computationally efficient estimation of gradient orientations is proposed based on patch-wise rigidity. We have applied our method to both rigid and non-rigid multimodal registration tasks with different modalities. Our approach outperforms mutual information (MI) and previously proposed local approximations of MI for multimodal (e.g. CT/MRI) brain image registration tasks. Furthermore, it shows significant improvements in terms of mTRE over standard methods in the highly challenging clinical context of registering pre-operative brain MRI to intra-operative US images.

Keywords

multimodal image registration image-guided neurosurgery 

References

  1. 1.
    Maes, F., Collignon, A., Dirk, V., Marchal, G., Suetens, P.: Multimodality image registration by maximization of mutual information. IEEE Trans. Med. Imaging 16, 187–198 (1997)CrossRefGoogle Scholar
  2. 2.
    Viola, P., Wells, W.M.: Alignment by maximization of mutual information. In: IJCV, pp. 16–23 (1995)Google Scholar
  3. 3.
    Pluim, J., Maintz, J., Viergever, M.: Mutual-information-based registration of medical images: a survey. IEEE Trans. Med. Imaging 22(8), 986–1004 (2003)CrossRefGoogle Scholar
  4. 4.
    Arbel, T., Morandi, X., Comeau, R., Collins, D.L.: Automatic non-linear MRI-Ultrasound registration for the correction of intra-operative brain deformations. In: Niessen, W.J., Viergever, M.A. (eds.) MICCAI 2001. LNCS, vol. 2208, pp. 913–922. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  5. 5.
    Roche, A., Pennec, X., Malandain, G., Ayache, N.: Rigid registration of 3D ultrasound with MR images: a new approach combining intensity and gradient information. IEEE Trans. Med. Imaging 20, 1038–1049 (2001)CrossRefGoogle Scholar
  6. 6.
    Ji, S., Wu, Z., Hartov, A., Roberts, D.W., Paulsen, K.D.: Mutual-information-based image to patient re-registration using intraoperative ultrasound in image-guided neurosurgery. Medical Physics 35(10), 4612–4624 (2008)CrossRefGoogle Scholar
  7. 7.
    Karaçali, B.: Information theoretic deformable registration using local image information. IJCV 72, 219–237 (2007)CrossRefGoogle Scholar
  8. 8.
    Biesdorf, A., Wörz, S., Kaiser, H.J., Rohr, K.: Hybrid spline-based multimodal registration using local measures for joint entropy and mutual information. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009. LNCS, vol. 5761, pp. 607–615. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  9. 9.
    Lindeberg, T.: Scale-space theory in computer vision. Springer, Heidelberg (1993)zbMATHGoogle Scholar
  10. 10.
    Klein, S., Staring, M., Murphy, K., Viergever, M., Pluim, J.: elastix: a toolbox for intensity-based medical image registration. IEEE Trans. Med. Imaging 29(1), 196–205 (2010)CrossRefGoogle Scholar
  11. 11.
    Chen, H., Varshney, P.K.: Mutual information-based CT-MR brain image registration using generalized partial volume joint histogram estimation. IEEE Trans. Medical Imaging 22(9), 1111–1119 (2003)CrossRefGoogle Scholar
  12. 12.
    Tsao, J.: Interpolation artifacts in multimodality image registration based on maximization of mutual information. IEEETrans. Med. Imaging 22(7), 854–864 (2003)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Dante De Nigris
    • 1
  • Laurence Mercier
    • 2
  • Rolando Del Maestro
    • 3
  • D. Louis Collins
    • 2
  • Tal Arbel
    • 1
  1. 1.Centre for Intelligent MachinesMcGill University 
  2. 2.Dept. of Biomedical EngineeringMcGill University 
  3. 3.Montreal Neurological Institute and HospitalMcGill University 

Personalised recommendations