Advertisement

Registration Fusion Using Markov Random Fields

  • Tobias Gass
  • Gabor Szekely
  • Orcun Goksel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8545)

Abstract

Image registration is a ubiquitous technique in medical imaging. However, finding correspondences reliably between images is a difficult task since the registration problem is ill-posed and registration algorithms are only capable of finding local optima. This makes it challenging to find a suitable registration method and parametrization for a specific application. To alleviate such problems, multiple registrations can be fused which is typically done by weighted averaging, which is sensitive to outliers and can not guarantee that registrations improve. In contrast, in this work we present a Markov random field based technique which fuses registrations by explicitly minimizing local dissimilarities of deformed source and target image, while penalizing non-smooth deformations. We additionally propose a registration propagation technique which combines multiple registration hypotheses which are obtained from different indirect paths in a set of mutually registered images. Our fused registrations are experimentally shown to improve pair-wise correspondences in terms of average deformation error (ADE) and target registration error (TRE) as well as improving post-registration segmentation overlap.

Keywords

Image Registration Markov Random Field Registration Method Registration Algorithm Indirect Path 
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.
    Fischer, B., Modersitzki, J.: Ill-posed medicine - an introduction to image registration. Inverse Probl. 24(3), 1–19 (2008)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Glocker, B., Komodakis, N., Tziritas, G., Navab, N., Paragios, N.: Dense image registration through MRFs and efficient linear programming. Med. Image Anal. 12(6), 731–741 (2008)CrossRefGoogle Scholar
  3. 3.
    Thirion, J.P.: Image matching as a diffusion process: an analogy with Maxwell’s demons. Med. Image Anal. 2(3), 243–260 (1998)CrossRefGoogle Scholar
  4. 4.
    Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Diffeomorphic demons: efficient non-parametric image registration. Neuroimage 45(1 suppl.), 61–72 (2009)CrossRefGoogle Scholar
  5. 5.
    Cachier, P., Ayache, N.: Regularization in Image Non-Rigid Registration: I. Trade-off between Smoothness and Intensity Similarity. Technical report, INRIA (2001)Google Scholar
  6. 6.
    Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Symmetric log-domain diffeomorphic Registration: A demons-based approach. In: Metaxas, D., Axel, L., Fichtinger, G., Székely, G. (eds.) MICCAI 2008, Part I. LNCS, vol. 5241, pp. 754–761. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  7. 7.
    Avants, B., Epstein, C., Grossman, M., Gee, J.: Symmetric Diffeomorphic Image Registration with Cross-Correlation: Evaluating Automated Labeling of Elderly and Neurodegenerative Brain. Med. Image Anal. 12(1), 26–41 (2008)CrossRefGoogle Scholar
  8. 8.
    Keysers, D., Unger, W.: Elastic Image Matching is NP-complete. Pattern Recognition Letters 24, 445–453 (2003)CrossRefzbMATHGoogle Scholar
  9. 9.
    Rueckert, D., Sonoda, L.I., Hayes, C., Hill, D.L., Leach, M.O., Hawkes, D.J.: Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans. Med. Imaging 18(8), 712–721 (1999)CrossRefGoogle Scholar
  10. 10.
    Schapire, R.E.: The strength of weak learnability. Machine Learning 5(2), 197–227 (1990)Google Scholar
  11. 11.
    Heckemann, R.A., Hajnal, J.V., Aljabar, P., Rueckert, D., Hammers, A.: Automatic anatomical brain MRI segmentation combining label propagation and decision fusion. Neuroimage 33(1), 115–126 (2006)CrossRefGoogle Scholar
  12. 12.
    Lempitsky, V., Roth, S., Rother, C.: FusionFlow: Discrete-continuous optimization for optical flow estimation. IEEE Comput. Vis. Pattern Recognit., 1–8 (2008)Google Scholar
  13. 13.
    Iglesias, J.E., Karssemeijer, N.: Robust initial detection of landmarks in film-screen mammograms using multiple FFDM atlases. IEEE Trans. Med. Imaging 28(11), 1815–1824 (2009)CrossRefGoogle Scholar
  14. 14.
    Santemiz, P., Spreeuwers, L.J., Veldhuis, R.N.J.: Automatic landmark detection and face recognition for side-view face images. In: Int. Conf. Biometrics Spec. Interes. Gr. Lecture Notes in Informatics (LNI) - Proceedings, pp. 337–344 (2013)Google Scholar
  15. 15.
    Gass, T., Székely, G., Goksel, O.: Semi-supervised Segmentation Using Multiple Segmentation Hypotheses from a Single Atlas. In: Menze, B.H., Langs, G., Lu, L., Montillo, A., Tu, Z., Criminisi, A. (eds.) MCV 2012. LNCS, vol. 7766, pp. 29–37. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  16. 16.
    Cachier, P., Bardinet, E., Dormont, D., Pennec, X., Ayache, N.: Iconic feature based nonrigid registration: the PASHA algorithm. Comput. Vis. Image Underst. 89(2-3), 272–298 (2003)CrossRefzbMATHGoogle Scholar
  17. 17.
    Cardoso, M.J., Modat, M., Ourselin, S., Keihaninejad, S., Cash, D.: Multi-STEPS: Multi-label similarity and truth estimation for propagated segmentations. In: Math. Methods Biomed. Image Anal., pp. 153–158 (2012)Google Scholar
  18. 18.
    Kolmogorov, V., Zabih, R.: What Energy Functions Can Be Minimized via Graph Cuts. IEEE Trans. Pattern Anal. Mach. Intell. 26(4), 147–159 (2004)CrossRefGoogle Scholar
  19. 19.
    Kolmogorov, V.: Convergent Tree-Reweighted Message Passing for Energy Minimization. IEEE Trans. Pattern Anal. Mach. Intell. 28, 1568–1583 (2006)CrossRefGoogle Scholar
  20. 20.
    Christensen, G.E., Rabbitt, R.D., Miller, M.I., Joshi, S.C., Grenander, U., Coogan, T.A.: Topological Properties of Smooth Anatomic Maps. In: Inf. Process. Med. Imaging, pp. 101–112. Springer (1995)Google Scholar
  21. 21.
    Myronenko, A., Song, X.: Intensity-based image registration by minimizing residual complexity. IEEE Trans. Med. Imaging 29(11), 1882–1891 (2010)CrossRefGoogle Scholar
  22. 22.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Tobias Gass
    • 1
  • Gabor Szekely
    • 1
  • Orcun Goksel
    • 1
  1. 1.Computer Vision LabSwiss Federal Institute of Technology (ETH) ZurichSwitzerland

Personalised recommendations