Abstract
This paper presents an adaptive structure self-organizing finite mixture network for quantification of magnetic resonance (MR) brain image sequences. We present justification for the use of standard finite normal mixture model for MR images and formulate image quantification as a distribution learning problem. The finite mixture network parameters are updated such that the relative entropy between the true and estimated distributions is minimized. The new learning scheme achieves flexible classifier boundaries by forming winner-takes-in probability splits of the data allowing the data to contribute simultaneously to multiple regions. Hence, the result is unbiased and satisfies the asymptotic optimality properties of maximum likelihood. To achieve a fully automatic quantification procedure that can adapt to different slices in the MR image sequence, we utilize an information theoretic criterion that we have introduced recently, the minimum conditional bias/variance (MCBV) criterion. MCBV allows us to determine the suitable number of mixture components to represent the characteristics of each image in the sequence. We present examples to show that the new method yields very efficient and accurate performance compared to expectation-maximization, K-means, and competitive learning procedures.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
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, pp. 566–574, Sept. 1993.
Y. Wang and T. Adali, “Efficient learning of finite normal mixtures for image quantification”, Proc. IEEE Intl. Conf. Acoust., Speech, and Signal Processing, Atlanta, pp. 3422–3425, May 1996.
A.J. Worth and D.N. Kennedy, “Segmentation of magnetic resonance brain images using analog constraint satisfaction neural networks”, Information Processing in Medical Imaging, pp. 225–243, 1993.
T. Lei and W. Sewchand, “A new stochastic model-based image segmentation technique for X-ray CT image”, IEEE Trans. Med. Imaging, Vol. 11, No.1, pp. 53–61, March 1992.
Z. Liang, J.R. MacFall, and D.P. Harrington, “Parameter estimation and tissue segmentation from multispectral MR images”, IEEE Trans. Med. Imag., Vol. 13, No.3, pp. 441–449, Sept. 1994.
Y. Wang, T. Lei, W. Sewchand, and S.K. Mun, “MR imaging statistics and its application in image modeling”, Proc. SPIE Med. Imaging, Newport Beach, 1996 (in press).
D.M. Titterington, A.F.M. Smith, and U.E. Markov, Statistical Analysis of Finite Mixture Distributions, JohnWiley, New York, 1985.
Y. Wang, “Image quantification and the minimum conditional bias/variance criterion”, Proc. 30th Conf. Info. Sci. Sys., Princeton, pp. 1061–1064, March 1996.
A.L. Yuille, P. Stolorz, and J. Utans, “Statistical physics, mixtures of distributions, and the EM algorithm”, Neural Computation, No. 6, pp. 334–340, 1994.
J. Zhang and J.M. Modestino, “Amodel-fitting approach to cluster validation with application to stochastic model-based image segmentation”, IEEE Trans. Pattern Analy. Machine Intell., Vol. 12, No.10, pp. 1009–1017, Oct. 1990.
T.M. Cover and J.A. Thomas, Elements of Information Theory, John Wiley & Sons, Inc., 1991.
R. Gray and L. Davisson, Random Processes—A Mathematical Approach for Engineers, Prentice-Hall, Englewood Cliffs, NJ, Inc., 1986.
T. Kohonen, “The self-organizing map”, Proc. IEEE, Vol. 78, No.9, pp. 1464–1480, 1990.
J.L. Marroquin and F. Girosi, “Some extensions of the k-means algorithm for image segmentation and pattern recognition”, MIT AI Lab., AI Memo 1390, 1993.
L. Perlovsky and M. McManus, “Maximum likelihood neural networks for sensor fusion and adaptive classification”, Neural Networks, Vol. 4, pp. 89–102, 1991.
C. Bouman and B. Liu, “Multiple resolution segmentation of texture images”, IEEE Trans. Pattern Anal. Machine Intel., Vol. 13, No.2, Feb. 1991.
C. Lau, “Magnetic resonance image analysis and MR-PET image co-registration by multi-feature matching”, M.S. Thesis, University of Maryland, Baltimore, MD, Aug. 1995.
J. Xuan, T. Adali, and Y. Wang, “Segmentation of magnetic resonance brain image: Integrating region growing and edge detection”, Proc. IEEE Intl. Conf. Image Processing, Washington, DC, Vol. III, pp. 544–547, Oct. 1995.
T. Adali, M.K. Sönmez, and K. Patel, “On the dynamics of the LRE Algorithm: A distribution learning approach to adaptive equalization”, Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, Detroit, Michigan, pp. 929–932, May 1995.
T. Adali, X. Liu, and M.K. Sönmez, “Conditional distribution learning with neural networks and its application to channel equalization”, IEEE Trans. Signal Processing, Vol. 45, No.4, pp. 1051–1064, April 1997.
G.J. McLachlan and T. Krishnan, The EM Algorithm and Extensions, John Wiley, New York, 1997.
R.M. Neal and G.E. Hinton, “A new view of the EM algorithm that justifies incremental and other variants”, submitted to Biometrica, 1993.
R.A. Jacobs, “Increased rates of convergence through learning rate adaptation”, Neural Networks, Vol. 1, pp. 295–307, 1988.
Y. Wang, T. Adali, and S.C.B. Lo, “Automatic threshold selection for quantification”, SPIE Journal of Biomedical Optics, Vol. 2, No.2, pp. 211–217, April 1997.
S. Chen, C.F.N. Cowan, and P.M. Grant, “Orthogonal least squares learning algorithm for radial basis function networks”, IEEE Trans. Neu. Net., Vol. 2, No.2, pp. 302–309, March 1991.
H. Akaike, “A new look at the statistical model identification”, IEEE Trans. Automatic Cont., Vol. 19, No.6, Dec. 1974.
J. Rissanen, “Minimax entropy estimation of models for vector processes”, in System Identification: Advances and Case Studies, pp. 97–119, 1987.
E.T. Jaynes, “Information theory and statistical mechanics”, Physical Review, Vol. 108, No.2, pp. 620–630/171-190, May 1957.
H.V. Poor, An Introduction to Signal Detection and Estimation, Springer-Verlag, 1988.
L.I. Perlovsky, “Cramer-Rao Bounds for the estimation of normal mixtures”, Pattern Recognition Letters, Vol. 10, pp. 141–148, 1989.
R.A. Redner and N.M. Walker, “Mixture densities, maximum likelihood and the EM algorithm”, SIAM Rev., Vol. 26, pp. 195–239, 1984.
S. Haykin, Neural Networks: A Comprehensive Foundation, Macmillan College Publishing Company, New York, 1994.
J. Rissanen, “Modeling by shortest data description”, Automatica, Vol. 14, 1978.
J.L. Marroquin, “Measure fields for function approximation”, IEEE Trans. Neu. Net., Vol. 6, No.5, pp. 1081–1090, Sept. 1995.
S. Geman, E. Bienenstock, and R. Doursat, “Neural networks and the bias/variance dilemma”, Neural Computation, Vol. 4, pp. 1–58, 1992.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wang, Y., Adali, T., Lau, CM. et al. Quantitative Analysis of MR Brain Image Sequences by Adaptive Self-Organizing Finite Mixtures. The Journal of VLSI Signal Processing-Systems for Signal, Image, and Video Technology 18, 219–239 (1998). https://doi.org/10.1023/A:1007985130296
Published:
Issue Date:
DOI: https://doi.org/10.1023/A:1007985130296