Edge- and Detail-Preserving Sparse Image Representations for Deformable Registration of Chest MRI and CT Volumes

  • Mattias P. Heinrich
  • Mark Jenkinson
  • Bartlomiej W. Papież
  • Fergus V. Glesson
  • Sir Michael Brady
  • Julia A. Schnabel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7917)


Deformable medical image registration requires the optimisation of a function with a large number of degrees of freedom. Commonly-used approaches to reduce the computational complexity, such as uniform B-splines and Gaussian image pyramids, introduce translation-invariant homogeneous smoothing, and may lead to less accurate registration in particular for motion fields with discontinuities. This paper introduces the concept of sparse image representation based on supervoxels, which are edge-preserving and therefore enable accurate modelling of sliding organ motions frequently seen in respiratory and cardiac scans. Previous shortcomings of using supervoxels in motion estimation, in particular inconsistent clustering in ambiguous regions, are overcome by employing multiple layers of supervoxels. Furthermore, we propose a new similarity criterion based on a binary shape representation of supervoxels, which improves the accuracy of single-modal registration and enables multi-modal registration. We validate our findings based on the registration of two challenging clinical applications of volumetric deformable registration: motion estimation between inhale and exhale phase of CT scans for radiotherapy planning, and deformable multi-modal registration of diagnostic MRI and CT chest scans. The experiments demonstrate state-of-the-art registration accuracy, and require no additional anatomical knowledge with greatly reduced computational complexity.


supervoxels sliding motion multi-modal fusion pulmonary 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)CrossRefGoogle Scholar
  2. 2.
    Castillo, E., Castillo, R., Martinez, J., Shenoy, M., Guerrero, T.: Four-dimensional deformable image registration using trajectory modeling. Phys. Med. Biol. 55(1), 305 (2009)CrossRefGoogle Scholar
  3. 3.
    Felzenszwalb, P., Huttenlocher, D.: Efficient Belief Propagation for Early Vision. Int. J. Comp. Vis. 70(1), 41–54 (2006)CrossRefGoogle Scholar
  4. 4.
    Glocker, B., Komodakis, N., Tziritas, G., Navab, N., Paragios, N.: Dense image registrations through MRFs and efficient linear programming. Med. Imag. Anal. 12(6), 731–741 (2008)CrossRefGoogle Scholar
  5. 5.
    Heinrich, M.P., Jenkinson, M., Bhushan, M., Matin, T., Gleeson, F.V., Brady, M., Schnabel, J.A.: MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration. Med. Imag. Anal. 16(7), 1423–1435 (2012)CrossRefGoogle Scholar
  6. 6.
    Heinrich, M., Jenkinson, M., Brady, M., Schnabel, J.: MRF-based deformable registration and ventilation estimation of lung CT. IEEE Trans. Med. Imag. (2013)Google Scholar
  7. 7.
    Kolmogorov, V., Rother, C.: Minimizing nonsubmodular functions with graph cuts - a review. IEEE Trans. Pattern Anal. Mach. Intell. 29(7), 1274–1279 (2007)CrossRefGoogle Scholar
  8. 8.
    Kopf, J., Cohen, M.F., Lischinski, D., Uyttendaele, M.: Joint bilateral upsampling. ACM Trans. Graph. 26(3), 96 (2007)CrossRefGoogle Scholar
  9. 9.
    Lei, C., Selzer, J., Yang, Y.H.: Region-tree based stereo using dynamic programming optimization. In: CVPR, pp. 2378–2385. IEEE (2006)Google Scholar
  10. 10.
    Lucchi, A., Smith, K., Achanta, R., Knott, G., Fua, P.: Supervoxel-based segmentation of mitochondria in EM image stacks with learned shape features. IEEE Trans. Med. Imag. 31(2), 474–486 (2012)CrossRefGoogle Scholar
  11. 11.
    Schmidt-Richberg, A., Werner, R., Handels, H., Ehrhardt, J.: Estimation of slipping organ motion by registration with direction-dependent regularization. Med. Imag. Anal. 16(1), 150–159 (2012)CrossRefGoogle Scholar
  12. 12.
    Shi, W., Zhuang, X., Pizarro, L., Bai, W., Wang, H., Tung, K.P., Edwards, P., Rueckert, D.: Registration using sparse free-form deformations. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part II. LNCS, vol. 7511, pp. 659–666. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  13. 13.
    Unser, M.A., Aldroubi, A., Gerfen, C.R.: Multiresolution image registration procedure using spline pyramids. In: Int. Symp. on Optics, Imaging, and Instrumentation, SPIE, pp. 160–170 (1993)Google Scholar
  14. 14.
    Vandemeulebroucke, J., Bernard, O., Rit, S., Kybic, J., Clarysse, P., Sarrut, D.: Automated segmentation of a motion mask to preserve sliding motion in deformable registration of thoracic CT. Med. Phys. 39, 1006 (2012)CrossRefGoogle Scholar
  15. 15.
    Yianilos, P.N.: Data structures and algorithms for nearest neighbor search in general metric spaces. In: ACM-SIAM Symp. on Discrete Algorithms, pp. 311–321 (1993)Google Scholar
  16. 16.
    Zabih, R., Woodfill, J.: Non-parametric local transforms for computing visual correspondence. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 801, pp. 151–158. Springer, Heidelberg (1994)CrossRefGoogle Scholar
  17. 17.
    Zitnick, C.W., Jojic, N., Kang, S.B.: Consistent segmentation for optical flow estimation. In: ICCV, pp. 1308–1315. IEEE (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Mattias P. Heinrich
    • 1
    • 2
  • Mark Jenkinson
    • 2
  • Bartlomiej W. Papież
    • 1
  • Fergus V. Glesson
    • 3
  • Sir Michael Brady
    • 4
  • Julia A. Schnabel
    • 1
  1. 1.Institute of Biomedical EngineeringUniversity of OxfordUK
  2. 2.Centre for Functional MRI of the BrainOxford UniversityUK
  3. 3.Department of RadiologyChurchill HospitalOxfordUK
  4. 4.Department of OncologyUniversity of OxfordUK

Personalised recommendations