Multi-modal Image Registration Using Polynomial Expansion and Mutual Information

  • Daniel Forsberg
  • Gunnar Farnebäck
  • Hans Knutsson
  • Carl-Fredrik Westin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7359)

Abstract

The use of polynomial expansion in image registration has previously been shown to be beneficial due to fast convergence and high accuracy. However, earlier work has only been for mono-modal image registration. In this work, it is shown how polynomial expansion and mutual information can be linked to achieve multi-modal image registration. The proposed method is evaluated using MRI data and shown to have a satisfactory accuracy while not increasing the computation time significantly.

Keywords

Mutual Information Image Registration Shannon Entropy Conditional Entropy Polynomial Expansion 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Collignon, A., Maes, F., Delaere, D., Vandermeulen, D., Suetens, P., Marchal, G.: Automated multimodality image registration based on information theory. In: XIVth International Conference on Information Processing in Medical Imaging, IPMI 1995, vol. 3, pp. 263–274. Kluwer Academic Publishers (1995)Google Scholar
  2. 2.
    Collins, D., Zijdenbos, A., Kollokian, V., Sled, J., Kabani, N., Holmes, C., Evans, A.: Design and construction of a realistic digital brain phantom. IEEE Transactions on Medical Imaging 17(3), 463–468 (1998)CrossRefGoogle Scholar
  3. 3.
    Farnebäck, G.: Polynomial expansion for orientation and motion estimation. Ph.D. thesis, Linköping University, Sweden (2002)Google Scholar
  4. 4.
    Farnebäck, G., Westin, C.-F.: Affine and Deformable Registration Based on Polynomial Expansion. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006, Part I. LNCS, vol. 4190, pp. 857–864. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Forsberg, D., Andersson, M., Knutsson, H.: Non-rigid diffeomorphic image registration of medical images using polynomial expansion (2012), Accepted at the International Conference on Image Analysis and RecognitionGoogle Scholar
  6. 6.
    Knutsson, H., Westin, C.F.: Normalized and differential convolution: Methods for interpolation and filtering of incomplete and uncertain data. In: Proceedings of Computer Vision and Pattern Recognition 1993, New York City, USA, pp. 515–523 (1993)Google Scholar
  7. 7.
    Parzen, E.: On Estimation of a Probability Density Function and Mode. The Annals of Mathematical Statistics 33(3), 1065–1076 (1962)MathSciNetMATHCrossRefGoogle Scholar
  8. 8.
    Pluim, J., Maintz, J., Viergever, M.: Mutual-information-based registration of medical images: A survey. IEEE Transactions on Medical Imaging 22(8), 986–1004 (2003)CrossRefGoogle Scholar
  9. 9.
    Rosenblatt, M.: Remarks on some nonparametric estimates of a density function. The Annals of Mathematical Statistics 27, 832–837 (1956)MathSciNetMATHCrossRefGoogle Scholar
  10. 10.
    Viola, P., Wells III., W.M.: Alignment by maximization of mutual information. In: Proceedings of Fifth International Conference on Computer Vision, pp. 16–23 (1995)Google Scholar
  11. 11.
    Wang, Y.J., Farnebck, G., Westin, C.F.: Multi-affine registration using local polynomial expansion. Journal of Zhejiang University - Science C 11, 495–503 (2010)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Daniel Forsberg
    • 1
    • 2
    • 3
  • Gunnar Farnebäck
    • 1
  • Hans Knutsson
    • 1
    • 2
  • Carl-Fredrik Westin
    • 4
  1. 1.Department of Biomedical EngineeringLinköping UniversitySweden
  2. 2.Center for Medical Image Science and VisualizationLinköping UniversitySweden
  3. 3.Sectra ImtecLinköpingSweden
  4. 4.Laboratory of Mathematics in ImagingBrigham Women’s Hospital, Harvard Medical SchoolBostonUSA

Personalised recommendations