TV-L1-Based 3D Medical Image Registration with the Census Cost Function

  • Simon Hermann
  • René Werner
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8333)


A recent trend in computer vision is to combine the census cost function with a TV-L1 energy minimization scheme. Although this combination is known for its robust performance in computer vision applications, it has not been introduced to 3D medical image registration yet. Addressing pulmonary motion estimation in 4D (3D+t) CT images, we propose incorporating the census cost function into a 3D implementation of the ‘duality-based approach for realtime TV-L1 optical flow’ for the task of lung CT registration. The performance of the proposed algorithm is evaluated on the DIR-lab benchmark and compared to state-of-the-art approaches in this field. Results highlight the potential of the census cost function for accurate pulmonary motion estimation in particular, and 3D medical image registration in general.


Medical image registration census transform pulmonary motion estimation 4D CT 


  1. 1.
    Brock, K.K.: On behalf of the Deformable Registration Accuracy Consortium: Results of a multi-institution deformable registration accuracy study (MIDRAS). Int. J. Radiat. Oncol. Biol. Phys. 76, 583–596 (2010)CrossRefGoogle Scholar
  2. 2.
    Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High Accuracy Optical Flow Estimation Based on a Theory for Warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  3. 3.
    Castillo, R., Castillo, E., Guerra, R., Johnson, V.E., McPhail, T., et al.: A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets. Phys. Med. Biol. 54, 1849–1870 (2009)CrossRefGoogle Scholar
  4. 4.
    Castillo, R., Castillo, E., Martinez, J., Guerrero, T.: Ventilation from four-dimensional computed tomography: density versus Jacobian methods. Phys. Med. Biol. 55, 4661–4685 (2010)CrossRefGoogle Scholar
  5. 5.
    Castillo, E., Castillo, R., White, B., Rojo, J., Guerrero, T.: Least median of squares filtering of locally optimal point matches for compressible flow image registration. Phys. Med. Biol. 57, 4827–4833 (2012)CrossRefGoogle Scholar
  6. 6.
    Chambolle, A.: An Algorithm for Total Variation Minimization and Applications. J. Mathematical Imaging Vision 20, 89–97 (2004)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Ehrhardt, J., Lorenz, C.: 4D Modeling and Estimation of Respiratory Motion for Radiation Therapy. Springer, Berlin (2013)CrossRefGoogle Scholar
  8. 8.
    Heinrich, M.P., Jenkinson, M., Brady, M., Schnabel, J.A.: MRF-based deformable registration and ventilation estimation of lung CT. IEEE Trans. Medical Imaging 32, 1239–1248 (2013)CrossRefGoogle Scholar
  9. 9.
    Hermann, S., Werner, R.: High Accuracy Optical Flow for 3D Medical Image Registration using the Census Cost Function. In: Klette, R., Rivera, M., Satoh, S. (eds.) PSIVT 2013. LNCS, vol. 8333, pp. 23–35. Springer, Heidelberg (2013)Google Scholar
  10. 10.
    Hoog, A.C.B., Singh, T., Singla, P., Podgorsak, M.: Evaluation of advanced Lukas-Kanade optical flow on thoracic 4D-CT. J. Clin. Monit. Comput. 27, 433–441 (2013)CrossRefGoogle Scholar
  11. 11.
    Hirschmüller, H.: Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information. In: IEEE Conf. Computer Vision Pattern Recognition, pp. 807–814 (2005)Google Scholar
  12. 12.
    Kabus, S., Lorenz, C.: Fast Elastic Image Registration. Medical Image Analysis for the Clinic: A Grand Challenge, 81–89 (2010)Google Scholar
  13. 13.
    Li, H., Li, Y., Zhang, X., Li, X., Liu, W., et al.: Dynamically accumulated dose and 4D accumulated dose for moving tumors. Med. Phys. 39, 7359–7367 (2012)CrossRefGoogle Scholar
  14. 14.
    Müller, T., Rabe, C., Rannacher, J., Franke, U., Mester, R.: Illumination-Robust Dense Optical Flow Using Census Signatures. In: Mester, R., Felsberg, M. (eds.) DAGM 2011. LNCS, vol. 6835, pp. 236–245. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  15. 15.
    Murphy, K., van Ginneken, B., Reinhardt, J., Kabus, S., Ding, K., et al.: Evaluation of registration methods on thoracic CT: The EMPIRE10 Challenge. IEEE Trans. Medical Imaging 30, 1901–1920 (2011)CrossRefGoogle Scholar
  16. 16.
    Pock, T., Urschler, M., Zach, C., Beichel, R.R., Bischof, H.: A Duality Based Algorithm for TV-L1-Optical-Flow Image Registration. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part II. LNCS, vol. 4792, pp. 511–518. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  17. 17.
    Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D 60, 259–268 (1992)CrossRefzbMATHGoogle Scholar
  18. 18.
    Rühaak, J., Heldmann, S., Kipshagen, T., Fischer, B.: Highly Accurate Fast lung CT Registration. In: SPIE Medical Imaging: Image Processing. SPIE, vol. 8669, p. 86690Y (2013)Google Scholar
  19. 19.
    Schmidt-Richberg, A., Ehrhardt, J., Werner, R., Handels, H.: Diffeomorphic Diffusion Registration of Lung CT Images Medical Image Analysis for the Clinic: A Grand Challenge, pp. 55–62 (2010)Google Scholar
  20. 20.
    Schmidt-Richberg, A., Werner, R., Handels, H., Ehrhardt, J.: Estimation of slipping organ motion by registration with direction-dependent regularization. Med. Image Anal. 16, 150–159 (2012)CrossRefGoogle Scholar
  21. 21.
    Simpson, D.R., Lawson, J.D., Nath, S.K., Rose, B.S., Mundt, A.J., Mell, L.K.: Utilization of advanced imaging technologies for target delineation in radiation oncology. J. Am. Coll. Radiol. 6, 876–883 (2009)CrossRefGoogle Scholar
  22. 22.
    Urschler, M., Werlberger, M., Scheurer, E., Bischof, H.: Robust Optical Flow Based Deformable Registration of Thoracic CT Images. In: Medical Image Analysis for the Clinic: A Grand Challenge, pp. 195–204 (2010)Google Scholar
  23. 23.
    Warren, H.S.: Hacker’s Delight, pp. 65–72. Addison-Wesley Longman, New York (2002)Google Scholar
  24. 24.
    Werner, R., Ehrhardt, J., Schmidt-Richberg, A., Albers, D., Frenzel, T., et al.: Towards accurate dose accumulation for Step-&-Shoot IMRT: Impact of weighting schemes and temporal image resolution on the estimation of dosimetric motion Eeffects. Z. Med. Phys. 22, 109–122 (2012)CrossRefGoogle Scholar
  25. 25.
    Wedel, A., Pock, T., Zach, C., Bischof, H., Cremers, D.: An Improved Algorithm for TV-L1 Optical Flow. In: Cremers, D., Rosenhahn, B., Yuille, A.L., Schmidt, F.R. (eds.) Statistical and Geometrical Approaches to Visual Motion Analysis. LNCS, vol. 5604, pp. 23–45. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  26. 26.
    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
  27. 27.
    Zach, C., Pock, T., Bischof, H.: A Duality Based Approach for Realtime TV-L1 Optical Flow. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Simon Hermann
    • 1
    • 2
  • René Werner
    • 3
  1. 1.Department of Computer ScienceThe University of AucklandNew Zealand
  2. 2.Department of Computer ScienceHumboldt University of BerlinGermany
  3. 3.Department of Computational NeuroscienceUniversity Medical CenterHamburg-EppendorfGermany

Personalised recommendations