Lesion Preserving Image Registration with Applications to Human Brains

  • Stefan Henn
  • Lars Hömke
  • Kristian Witsch
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3175)


The goal of image registration is to find a transformation that aligns one image to another. In this paper we present a novel automatically image registration approach for images with structural distortions (e.g. a lesion within a human brain). The main idea is to define a suitable matching energy, which effectively measures the similarity between the images. The minimization of the matching energy is an ill-posed problem. Hence, we add a regularity energy borrowed from linear elasticity theory, which incorporates smoothness constraints into the displacement. The resulting energy functional is minimized by a Levenberg-Marquardt iteration-scheme. Finally, we give a two-dimensional example of these applications.


Image Registration Trust Region Linear Elasticity Theory Lesion Mapping Parameter Choice Rule 
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.
    Amit, Y.: A nonlinear variational problem for image matching. SIAM J. Sci. Comput. 15, 207–224 (1994)zbMATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Bajcsy, R., Kovacic, S.: Multiresolution elastic matching. Computer Vision 46, 1–21 (1989)Google Scholar
  3. 3.
    Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Akeley, K. (ed.) Siggraph 2000, Computer Graphics Proceedings, pp. 417–424. ACM Press / ACM SIGGRAPH / Addison Wesley Longman (2000)Google Scholar
  4. 4.
    Chan, T., Kang, S., Shen, J.: Euler’s elastica and curvature based inpaintings. J. Appl. Math. 63(2), 564–592 (2002)zbMATHMathSciNetGoogle Scholar
  5. 5.
    Chan, T., Shen, J.: Mathematical models for local nontexture inpaintings. SIAM Journal on Applied Mathematics 62(3), 1019–1043 (2002)zbMATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Christensen, G., Miller, M., Vannier, M., Grenander, U.: Individualizing neuroanatomical atlases using a massively parallel computer. IEEE Computer 29(1), 32–38 (1996)Google Scholar
  7. 7.
    Clarenz, U., Henn, S., Rumpf, M., Witsch, K.: Relations between optimization and gradient flow methods with application to image registration. In: Proceedings of the 18th GAMM-Seminar Leipzig (2002)Google Scholar
  8. 8.
    Davis, M., Khotanzad, A., Flaming, D., Harms, S.: A physics based coordinate transformation for 3d medical images. IEEE Trans. on medical imaging 16(3), 317–328 (1997)CrossRefGoogle Scholar
  9. 9.
    Droske, M., Rumpf, M.: A variational approach to non-rigid morphological registration. SIAM Appl. Math. 64(2), 668–687 (2004)zbMATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Fischer, B., Modersitzki, J.: Curvature based image registration. JMIV 18, 81–85 (2003)zbMATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Henn, S.: Numerische Lösung und Modellierung eines inversen Problems zur Assimilation digitaler Bilddaten, Phd thesis Heinrich-Heine-Universität Düsseldorf. Logos-Verlag Berlin, Berlin (2001)Google Scholar
  12. 12.
    Henn, S.: A levenberg-marquardt scheme for nonlinear image registration. BIT Numerical Mathematics 43(4), 743–759 (2003)zbMATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Henn, S., Hömke, L., Witsch, K.: A generalized image registration framework using incomplete image information – with applications to lesion mapping. Springer Series in Mathematics in Industry. Springer, Heidelberg (2004)Google Scholar
  14. 14.
    Henn, S., Schormann, T., Engler, K., Zilles, K., Witsch, K.: Elastische Anpassung in der digitalen Bildverarbeitung auf mehreren Auflösungsstufen mit Hilfe von Mehrgitterverfahren. In: Informatik aktuell Mustererkennung, pp. 392–399. Springer, Heidelberg (1997)Google Scholar
  15. 15.
    Henn, S., Witsch, K.: A multigrid-approach for minimizing a nonlinear functional for digital image matching. Computing 64(4), 339–348 (1999)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Henn, S., Witsch, K.: Iterative multigrid regularization techniques for image matching. SIAM J. Sci. Comput (SISC) 23(4), 1077–1093 (2001)zbMATHCrossRefMathSciNetGoogle Scholar
  17. 17.
    Henn, S., Witsch, K.: Multi-modal image registration using a variational approach. SIAM J. Sci. Comput (SISC) 25(4), 1429–1447 (2004)CrossRefMathSciNetGoogle Scholar
  18. 18.
    Hömke, L., Weder, B., Binkofski, F., Amunts, K.: Lesion mapping in MRI data - an application of cytoarchitectonic probabilistic maps. In: WWW, Jülich. Second Vogt-Brodmann Symposium (2004),
  19. 19.
    Weder, B., Amunts, K., Hömke, L., Mohlberg, H., Bönig, L., Fretz, C., Binkofski, F.: Lesion analysis in high-resolution MR-images of patients with unilateral tactile agnosia using cytoarchitectonic mapping. In: Presented at the 10th Annual metting of the Organization for Human Brain Mapping, Budapest, June 13-17 (2004)Google Scholar
  20. 20.
    Keeling, S., Ring, W.: Medical image registration and interpolation by optical flow with maximal rigidity. Journal of Mathematical Imaging and Vision JMIV (to appear)Google Scholar
  21. 21.
    Saad, Y.: Iterative methods for sparse linear systems (2000)Google Scholar
  22. 22.
    Van Loan, C.F.: Computational Frameworks for the Fourier Transform. Frontiers in Applied Mathematics, vol. 10. SIAM, Philadelphia (1992)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Stefan Henn
    • 1
  • Lars Hömke
    • 2
  • Kristian Witsch
    • 1
  1. 1.Mathematisches InstitutHeinrich-Heine Universität DüsseldorfDüsseldorfGermany
  2. 2.Institut für Medizin, Forschungszentrum Jülich GmbHJülichGermany

Personalised recommendations