Skip to main content
Log in

Multimodality Image Registration Using Spatial Procrustes Analysis and Modified Conditional Entropy

Journal of Signal Processing Systems Aims and scope Submit manuscript

Abstract

In this paper, we propose a new image registration technique using two kinds of information known as object shapes and voxel intensities. The proposed approach consists of two registration steps. First, an initial registration is carried out for two volume images by applying Procrustes analysis theory to the two sets of 3D feature points representing object shapes. During this first stage, a volume image is segmented by using a geometric deformable model. Then, 3D feature points are extracted from the boundary of a segmented object. We conduct an initial registration by applying Procrustes analysis theory with two sets of 3D feature points. Second, a fine registration is followed by using a new measure based on the entropy of conditional probabilities. Here, to achieve the final registration, we define a modified conditional entropy (MCE) computed from the joint histograms for voxel intensities of two given volume images. By using a two step registration method, we can improve the registration precision. To evaluate the performance of the proposed registration method, we conduct various experiments for our method as well as existing methods based on the mutual information (MI) and maximum likelihood (ML) criteria. We evaluate the precision of MI, ML and MCE-based measurements by comparing their registration traces obtained from magnetic resonance (MR) images and transformed computed tomography (CT) images with respect to x-translation and rotation. The experimental results show that our method has great potential for the registration of a variety of medical images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9

Similar content being viewed by others

References

  1. Hajnal, J. V., Hill, D. L. G., & Hawkes, D. J. (2001). Medical image registration. New York: CRC Press.

    Google Scholar 

  2. Maintz, J. B. A., & Viergever, M. A. (1998). A survey of medical image registration. Medical Image Analysis, 2(1), 1–36.

    Article  Google Scholar 

  3. Sonka, M., & Fitzpatrick, J. M. (2000). Handbook of medical imaging, vol. 2. Medical image processing and analysis. Washington: SPIE Press.

    Google Scholar 

  4. Yoo, T. S. (2004). Insight into images: Principles and practice for segmentation, registration, and image analysis. Massachusetts: A K Peters.

    Google Scholar 

  5. Fitzpatrick, J. M., & West, J. B. (2001). The distribution of target registration error in Regid-Body point based registration. IEEE Transactions on Medical Imaging, 20(9), 917–927.

    Article  Google Scholar 

  6. Chan, H. M., & Chung, A. C. S. (2003). Efficient 3D–3D vascular registration based on multiple orthogonal 2D projections. LNCS, 2717, 301–310.

    Google Scholar 

  7. Mases, F., Collignon, A., Vandermeulen, D., Marchal, G., & Suetens, P. (1997). Multimodality image registration by maximization of mutual information. IEEE Transaction on Medical Imaging, 16(2), 187–198.

    Article  Google Scholar 

  8. Mases, F., Vandermeulen, D., & Suetens, P. (2003). Medical image registration using mutual information. Proceedings of The IEEE, 91(10), 1699–1722.

    Article  Google Scholar 

  9. Periaswamy, S., & Farid, H. (2003). Elastic registration in the presence of intensity variations. IEEE Transactions on Medical Imaging, 22(7), 865–874.

    Article  Google Scholar 

  10. Pluim, J. P. W., Maintz, J. B. A., & Viergever, M. A. (2003). Mutual information based registration of medical images: A survey. IEEE Transactions on Medical Imaging, 20, 1–20.

    Google Scholar 

  11. Wirth, M. A., Narhan, J., & Gray, D. (2002). Non-rigid mammogram registration using mutual information. SPIE Medical Imaging: Image Processing, 4684, 562–573.

    Google Scholar 

  12. Lee, H., & Hong, H. (2005). Robust surface registration using a Gaussian weighted distance map in PET-CT brain images. CAIRP 2005, LNCS 3773 (pp. 794–803).

  13. Liu, T., Shen, D., & Davatzikos, C. (2004). Deformable registration of cortical structures via hybrid volumetric and surface warping. NeuroImage, 22, 1790–1801.

    Article  Google Scholar 

  14. Moradi, M., Abolmaesoumi, P., & Mousavi, P. (2006). Deformable registration using scale space keypoints. Proceedings of SPIE, 6144, 791–798.

    Google Scholar 

  15. Pluim, J. P. W., Maintz, J. B. A., & Viergever, M. A. (2000). Image registration by maximization of combined mutual information and gradient information. IEEE Transactions on Medical Imaging, 19(8), 809–814.

    Article  Google Scholar 

  16. Johnson, H. J., & Christensen, G. E. (2002). Consistent landmark and intensity-based image registration. IEEE Transactions on Medical Imaging, 21(5), 450–461.

    Article  Google Scholar 

  17. Gan, R., & Chung, A. C. S. (2005). Distance-intensity for image registration. LNCS, 3765, 281–290.

    Google Scholar 

  18. Dryden, I. L., & Mardia, K. V. (1998). Statistical shape analysis. New York: Wiley.

    MATH  Google Scholar 

  19. Zhuang, H., & Sudhaker, R. (1997). Simultaneous rotation and translation fitting of two 3-D point sets. IEEE Transactions On Systems, Mam, And Cybernetics, 27(1), 127–131.

    Article  Google Scholar 

  20. Wen, G., Wang, Z., Xia, S., & Zhu, D. (2006). Least-squares fitting of multiple M-dimensional points sets. Visual Computation, 22, 387–398.

    Article  Google Scholar 

  21. Caselles, V., Kimmel, R., & Sapiro, G. (1995). Geodesic active contours. In Proceedings of ICCV, 95, 694–699.

    Google Scholar 

  22. Cho, W., Kim, S., Lee, M., & Park, S. (2007). Extraction of anatomic structures from medical volumetric images. MMM 2007, LNCS 4351, Part 1 (pp. 86–95).

  23. Han, X., Xu, C., & Prince, J. L. (2003). A topology preserving level set method for geometric deformable models. IEEE Transanctions on PAMI, 25(6), 755–768.

    Google Scholar 

  24. Osher, S., & Nikos Paragios, (2006). Geometric level set methods in imaging, vision, and graphics. Springer.

  25. Osher, S., & Sethian, J. A. (1988). Fronts propagating with curvature dependent speed: Algorithms based on Hamilton–Jacobi formulations. J. Computational Physics, 79, 12–49.

    Article  MATH  MathSciNet  Google Scholar 

  26. Sethian, J. A. (2005). Level set methods and fast marching methods. Cambridge University Press.

  27. Vese, L. A., & Chan, T. F. (2002). A multiphase level set framework for image segmentation using the Mumford and Shah model. International Journal of Computer Vision, 50, 271–293.

    Article  MATH  Google Scholar 

  28. Kelland, P., & Tait, P. G. (2005). Introduction to quaternions. Adamant Media Corporation.

  29. Zhu, Y. M., & Cochoff, S. M. (2002). Likelihood maximization approach to image registration. IEEE Transactions on Image Processing, 11(12), 1417–1426.

    Article  MathSciNet  Google Scholar 

  30. Ibanez, L., Schroeder, W., Ng, L., & Cates, J. The ITK software Guide. Kitware.

Download references

Acknowledgement

This work was supported by the Korea Research Foundation Grant funded by the Korea government (KRF-2007-311-D00752).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Myung-Eun Lee.

Appendix

Appendix

Result 3.1 The full Procrustes fit gives us the matching parameters which are the translation parameter and the rotation parameter. They are

$$\begin{array}{*{20}c} {{{\left( {u_{0} i + v_{0} j + w_{0} k} \right)} = 0,}} {{\ifmmode\expandafter\hat\else\expandafter\^\fi{\theta } = - \arg {\left( {{\left( {A*} \right)}^{T} B} \right)}.}} \\ \end{array}$$

Proof: We wish to minimize over (u 0, v 0, w 0, θ) the expression

$$\begin{array}{*{20}c} {D^2 = \left( {{\mathbf{\varepsilon }}^* } \right)^T {\mathbf{\varepsilon }} = \left\| {{\mathbf{A}} - {\mathbf{X}}_{\mathbf{D}} {\mathbf{B}}_{\mathbf{0}} } \right\|^2 } \\ { = \left\| {{\mathbf{A}} - e^{i_H \theta } {\mathbf{B}} - \left( {u_0 i + v_0 j + w_0 k} \right){\mathbf{1}}_k } \right\|^2 } \\ { = \left( {{\mathbf{A}} * } \right)^T {\mathbf{A}} + \left( {{\mathbf{B}} * } \right)^T {\mathbf{B}} - e^{i_H \theta } \left( {{\mathbf{A}} * } \right)^T {\mathbf{B}} - e^{ - i_H \theta } {\mathbf{A}}\left( {{\mathbf{B}} * } \right)^T + k\left( {u_0^2 + v_0^2 + w_0^2 } \right)} \\ \end{array} ,$$

where A and B are centered. Clearly, the minimizing the square distance yields that u 0, v 0 and w 0 are zero. Let \(\left( {{\mathbf{A}}^ * } \right)^T {\mathbf{B}} = re^{i_H \omega } \left( {r \geqslant 0} \right)\) and then we have

$$\left( {e^{i_H \theta } \left( {{\mathbf{A}} * } \right)^T {\mathbf{B}} + e^{ - i_H \theta } {\mathbf{A}}\left( {{\mathbf{B}} * } \right)^T } \right) = \left( {re^{i_H \left( {\theta + \omega } \right)} + re^{ - i_H \left( {\theta + \omega } \right)} } \right) = 2r\cos \left( {\theta + \omega } \right).$$

So to minimize the square distance D 2 over θ we need to maximize 2rcos(θ + ω). Clearly, a solution for θ is \(\ifmmode\expandafter\hat\else\expandafter\^\fi{\theta } = - \omega = - \arg {\left( {{\left( {A^{*} } \right)}^{T} B} \right)}\).

Rights and permissions

Reprints and permissions

About this article

Cite this article

Cho, WH., Kim, SW., Lee, ME. et al. Multimodality Image Registration Using Spatial Procrustes Analysis and Modified Conditional Entropy. J Sign Process Syst Sign Image Video Technol 54, 101–114 (2009). https://doi.org/10.1007/s11265-008-0203-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11265-008-0203-9

Keywords

Navigation