WBIR 2012: Biomedical Image Registration pp 256-265 | Cite as

On Combining Algorithms for Deformable Image Registration

  • Sascha E. A. Muenzing
  • Bram van Ginneken
  • Josien P. W. Pluim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7359)

Abstract

We propose a meta-algorithm for registration improvement by combining deformable image registrations (MetaReg). It is inspired by a well-established method from machine learning, the combination of classifiers. MetaReg consists of two main components: (1) A strategy for composing an improved registration by combining deformation fields from different registration algorithms. (2) A method for regularization of deformation fields post registration (UnfoldReg). In order to compare and combine different registrations, MetaReg utilizes a landmark-based classifier for assessment of local registration quality. We present preliminary results of MetaReg, evaluated on five CT pulmonary breathhold inspiration and expiration scan pairs, employing a set of three registration algorithms (NiftyReg, Demons, Elastix). MetaReg generated for each scan pair a registration that is better than any registration obtained by each registration algorithm separately. On average, 10% improvement is achieved, with a reduction of 30% of regions with misalignments larger than 5mm, compared to the best single registration algorithm.

Keywords

Deformable image registration meta-algorithm combination pattern recognition 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Danielsson, P.E.: Euclidean Distance Mapping. Computer Graphics and Image Processing 14, 227–248 (1980)CrossRefGoogle Scholar
  2. 2.
    Ibáñez, L., Schroeder, W., Ng, L., Cates, J.: The ITK Software Guide. Kitware, Inc. (2005)Google Scholar
  3. 3.
    Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On combining classifiers. IEEE Trans. on Pattern Analysis and Machine Intelligence 20(3), 226–239 (1998)CrossRefGoogle Scholar
  4. 4.
    Klein, S., Staring, M., Murphy, K., Viergever, M., Pluim, J.: elastix: a toolbox for intensity-based medical image registration. IEEE Transactions on Medical Imaging 29(1), 196–205 (2010)CrossRefGoogle Scholar
  5. 5.
    Lee, S., Wolberg, G., Shin, S.: Scattered data interpolation with multilevel b-splines. Trans. on Visualization and Computer Graphics 3(3), 228–244 (1997)CrossRefGoogle Scholar
  6. 6.
    Modat, M., McClelland, J., Ourselin, S.: Lung registration using the NiftyReg package. Medical Image Analysis for the Clinic - A Grand Challenge 2010, 33–42 (2010)Google Scholar
  7. 7.
    Modat, M., Ridgway, G.R., Taylor, Z.A., Lehmann, M., Barnes, J., Hawkes, D.J., Fox, N.C., Ourselin, S.: Fast free-form deformation using graphics processing units. Computer Methods and Programs in Biomedicine 98(3), 278–284 (2010)CrossRefGoogle Scholar
  8. 8.
    Muenzing, S.E.A., Murphy, K., van Ginneken, B., Pluim, J.P.W.: Automatic detection of registration errors for quality assessment in medical image registration. In: Proceedings of the SPIE, vol. 7259, pp. 72590K–72590K–9 (2009)Google Scholar
  9. 9.
    Muenzing, S.E.A., van Ginneken, B., Pluim, J.P.W.: Knowledge-driven regularization of the deformation field for PDE based nonrigid registration algorithms. Medical Image Analysis for the Clinic - A Grand Challenge 2010, 127–136 (2010)Google Scholar
  10. 10.
    Murphy, K., van Ginneken, B., Klein, S., Staring, M., de Hoop, B., Viergever, M., Pluim, J.P.W.: Semi-automatic construction of reference standards for evaluation of image registration. Medical Image Analysis 15, 71–84 (2011)CrossRefGoogle Scholar
  11. 11.
    Murphy, K., et al.: Evaluation of registration methods on thoracic CT: The EMPIRE10 challenge. IEEE Trans. on Medical Imaging 30, 1901–1920 (2011)CrossRefGoogle Scholar
  12. 12.
    van Rikxoort, E., de Hoop, B., Viergever, M., Prokop, M., van Ginneken, B.: Automatic lung segmentation from thoracic computed tomography scans using a hybrid approach with error detection. Medical Physics 36(7), 2934–2947 (2009)CrossRefGoogle Scholar
  13. 13.
    Staring, M., Klein, S., Reiber, J., Niessen, W., Stoel, B.: Pulmonary Image Registration With elastix Using a Standard Intensity-Based Algorithm. Medical Image Analysis for the Clinic - A Grand Challenge 2010 (2010)Google Scholar
  14. 14.
    Tustison, N., Gee, J.: N-d c k b-spline scattered data approximation. The Insight Journal. (2005)Google Scholar
  15. 15.
    Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Non-parametric Diffeomorphic Image Registration with the Demons Algorithm. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part II. LNCS, vol. 4792, pp. 319–326. Springer, Heidelberg (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Sascha E. A. Muenzing
    • 1
  • Bram van Ginneken
    • 2
  • Josien P. W. Pluim
    • 1
  1. 1.Image Sciences InstituteUniversity Medical Center UtrechtThe Netherlands
  2. 2.Diagnostic Image Analysis GroupRadboud University Nijmegen Medical CenterThe Netherlands

Personalised recommendations