A Comparison of Acceleration Techniques for Nonrigid Medical Image Registration

  • Stefan Klein
  • Marius Staring
  • Josien P. W. Pluim
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4057)


Mutual information based nonrigid registration of medical images is a popular approach. The coordinate mapping that relates the two images is found in an iterative optimisation procedure. In every iteration a computationally expensive evaluation of the mutual information’s derivative is required. In this work two acceleration strategies are compared. The first technique aims at reducing the number of iterations, and, consequently, the number of derivative evaluations. The second technique reduces the computational costs per iteration by employing stochastic approximations of the derivatives. The performance of both methods is tested on an artificial registration problem, where the ground truth is known, and on a clinical problem involving low-dose CT scans and large deformations. The experiments show that the stochastic approximation approach is superior in terms of speed and robustness. However, more accurate solutions are obtained with the first technique.


Mutual Information Gradient Descent Stochastic Approximation Nonrigid Registration Stochastic Gradient Descent 
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.
    Mattes, D., Haynor, D.R., Vesselle, H., Lewellen, T.K., Eubank, W.: PET-CT image registration in the chest using free-form deformations. IEEE Transactions on Medical Imaging 22, 120–128 (2003)CrossRefGoogle Scholar
  2. 2.
    Rueckert, D., Sonoda, L.I., Hayes, C., Hill, D.L.G., Leach, M.O., Hawkes, D.J.: Nonrigid registration using free-form deformations: Application to breast MR images. IEEE Transactions on Medical Imaging 18, 712–721 (1999)CrossRefGoogle Scholar
  3. 3.
    Nocedal, J., Wright, S.J.: Numerical optimization. Springer, New York (1999)MATHCrossRefGoogle Scholar
  4. 4.
    Thévenaz, P., Unser, M.: Optimization of mutual information for multiresolution image registration. IEEE Transactions on Image Processing 9, 2083–2099 (2000)MATHCrossRefGoogle Scholar
  5. 5.
    Nocedal, J.: Updating quasi-Newton matrices with limited storage. Mathematics of Computation 35, 773–782 (1980)MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Moré, J.J., Thuente, D.J.: Line search algorithms with guaranteed sufficient decrease. ACM Transactions on Mathematical Software 20, 286–307 (1994)MATHCrossRefGoogle Scholar
  7. 7.
    Dai, Y.H.: A family of hybrid conjugate gradient methods for unconstrained optimization. Mathematics of Computation 72, 1317–1328 (2003)MATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Dai, Y.H.: An efficient hybrid conjugate gradient method for unconstrained optimization. Annals of Operations Research 103, 33–47 (2001)MATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Klein, S., Staring, M., Pluim, J.P.W.: Comparison of gradient approximation techniques for optimisation of mutual information in nonrigid registration. In: Fitzpatrick, J., Reinhardt, J. (eds.) Proceedings of SPIE Medical Imaging: Image Processing, vol. 5747, pp. 192–203. SPIE press, Bellingham (2005)Google Scholar
  10. 10.
    Robbins, H., Monro, S.: A stochastic approximation method. The Annals of Mathematical Statistics 22, 400–407 (1951)MATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Kushner, H.J., Clark, D.S.: Stochastic approximation methods for constrained and unconstrained systems. Springer, New York (1978)Google Scholar
  12. 12.
    Kybic, J., Unser, M.: Fast parametric elastic image registration. IEEE Transactions on Image Processing 12, 1427–1442 (2003)CrossRefGoogle Scholar
  13. 13.
    Hu, S., Hoffman, E.A., Reinhardt, J.M.: Automatic lung segmentation for accurate quantitation of volumetric X-Ray CT images. IEEE Transactions on Medical Imaging 20, 490–498 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Stefan Klein
    • 1
  • Marius Staring
    • 1
  • Josien P. W. Pluim
    • 1
  1. 1.Image Sciences InstituteUniversity Medical Center UtrechtUtrechtThe Netherlands

Personalised recommendations