Abstract
Non-rigid image registration is a prerequisite for many medical image analysis applications such as image fusion of multimodality images and quantitative change analysis of a temporal sequence in computer-aided diagnosis. By establishing the point correspondence of the extracted feature points, it is possible to recover the deformation using nonlinear interpolation methods. However, it may be very difficult to establish such correspondence at an initial stage when confronted with large and complex deformation. In this paper, a mixture of principal axes registration (mPAR) method is proposed to resolve the correspondence problem through a neural computational approach. The novel feature of mPAR is the alignment of two point sets without the need of establishing explicit point correspondence. Instead, it aligns the two point sets by minimizing the relative entropy between their probability distributions resulting in a maximum likelihood estimate of the transformation matrix. The registration process consists of two steps: (1) a finite mixture scheme to establish an improved point correspondence and (2) a multilayer perceptron neural network (MLP) to recover the nonlinear deformation. The neural computation for registration uses a committee machine to obtain a mixture of piece-wise rigid registrations, which gives a reliable point correspondence using multiple extracted objects in a finite mixture scheme. Then the MLP is used to determine the coefficients of a polynomial transform using extracted control points. We have applied our mPAR method to register synthetic data sets, surgical prostate models, and a temporal sequence of mammograms of a single patient. The experimental results show that mPAR not only improves the accuracy of the point correspondence but also results in a desirable error-resilience property for control point selection errors.
References
M. Moshfeghi and H. Rusinek, “Three-Dimensional Registration of Multimodality Medical Images Using the Principal Axes Techniques,” Philips J. Res., vol. 47, no. 2, 1992, pp. 81-97.
V. Govindu and C. Shekhar, “Alignment Using Distributions of Local Geometric Properties,” IEEE Trans. Pattern Anal. Machine Intell., vol. 21, no. 10, 1999, pp. 1031-1043.
K.S. Arun, T.S. Huang, and S.D. Blostein, “Least-Squares Fitting of Two 3-D Point Sets,” IEEE Trans. Pattern Anal. Machine Intell., vol. 9, no. 5, 1987, pp. 698-700.
A.D.J. Cross and E.R. Hancock, “Graph Matching with a Dual-Step EM Algorithm,” IEEE Trans. Pattern Anal. Machine Intell., vol. 20, no. 11, 1998, pp. 1236-1253.
T.M. Cover and J.A. Thomas, Elements of Information Theory, New York: Wiley, 1991.
G.E. Hinton, P. Dayan, and M. Revow, “Modeling the Manifolds of Images of Handwritten Digits,” IEEE Trans. Neural Nets, vol. 8, no. 1, 1997, pp. 65-74.
Y. Wang, L. Luo, M.T. Freedman, and S.Y. Kung, “Probabilistic Principal Component Subspaces: A Hierarchical Finite Mixture Model for Data Visualization,” IEEE Trans. Neural Nets, vol. 11, no. 3, 2000, pp. 625-636.
Y. Wang, K. Woods, and M. McClain, “Information-Theoretic Matching of Two Point Sets,” IEEE Transactions on Image Processing, 2002 (in press).
L. Perlovsky and M. McManus, “Maximum Likelihood Neural Networks for Sensor Fusion and Adaptive Classification,” Neural Networks, vol. 4, 1991, pp. 89-102.
S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed., Upper Saddle River, Ney Jersey: Prentice-Hall, Inc., 1999.
S.Y. Kung, Principal Component Neural Networks, New York: Wiley, 1996.
M.I. Jordan and R.A. Jacobs, “Hierarchical Mixture of Experts and the EM Algorithm,” Neural Computation, vol. 6, 1994, pp. 181-214.
D.M. Titterington, A.F.M. Smith, and U.E. Markov, Statistical Analysis of Finite Mixture Distributions, New York: John Wiley, 1985.
K. Woods, “Patient Site Model Supported Change Detection,” Proceedings of SPIE Medical Imaging, vol. 1, no. 24, 2000, pp. 1095-1106.
J. Lu, R. Srikanchana, M. McClain, Y. Wang, J. Xuan, I.A. Sesterhenn, M.T. Freedman, and S.K. Mun, “A Statistical Volumetric Model for Characterization and Visualization of Prostate Cancer,” Proc. SPIE Medical Imaging, vol. 3976, 2000, pp. 142-153.
K. Woods, “Image Guided Diagnosis through Change Detection in Image Sequences,” Doctoral Dissertation, The Catholic University of America, 2000.
M.A. Wirth et al., “Point to Point Registration of Non-Rigid Medical Images Using Local Elastic Transformation Methods,” IEEE Image Proc. App., July 14–17 1997.
N.S. Vujovic, “Registration of Time-Sequences of Random Textures with Application to Mammogram Follow-Up,” Ph.D. Dissertation, Lehigh University, May 1997.
P. Santago and H.D. Gage, “Quantification of MR Brain images by Mixture Density and Partial Volume Modeling,” IEEE Trans. Med. Imag., vol. 12, no. 3, 1993, pp. 566-574.
Y. Wang and T. Adali, “Efficient Learning of Finite Normal Mixtures for Image Quantification,” in Proc. IEEE Int. Conf. Acoustic, Speech, and Signal Processing, Atlanta, GA, 1996, pp. 3422-3425.
R.A. Hummel and S.W. Zucker, “On the Foundations of Relaxation Labeling Processes,” IEEE Trans. Pattern Anal. Machine Intell., vol. 5, May 1983.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Srikanchana, R., Xuan, J., Freedman, M.T. et al. Non-Rigid Image Registration by Neural Computation. The Journal of VLSI Signal Processing-Systems for Signal, Image, and Video Technology 37, 237–246 (2004). https://doi.org/10.1023/B:VLSI.0000027488.23703.ba
Published:
Issue Date:
DOI: https://doi.org/10.1023/B:VLSI.0000027488.23703.ba