Automatic seed initialization for the expectation-maximization algorithm and its application in 3D medical imaging

Statistical partitioning of images into meaningful areas is the goal of all region-based segmentation algorithms. The clustering or creation of these meaningful partitions can be achieved in number of ways but in most cases it is achieved through the minimization or maximization of some function of the image intensity properties. Commonly these optimization schemes are locally convergent, therefore initialization of the parameters of the function plays a very important role in the final solution. In this paper we perform an automatically initialized expectation-maximization algorithm to partition the data in medical MRI images. We present analysis and illustrate results against manual initialization and apply the algorithm to some common medical image processing tasks.

[1]  Alejandro F. Frangi,et al.  Three-dimensional modeling for functional analysis of cardiac images, a review , 2001, IEEE Transactions on Medical Imaging.

[2]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[3]  R P Velthuizen,et al.  MRI segmentation: methods and applications. , 1995, Magnetic resonance imaging.

[4]  A Zavaljevski,et al.  Multi-level adaptive segmentation of multi-parameter MR brain images. , 2000, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[5]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Ovidiu Ghita,et al.  Rapid automated measurement of body fat distribution from whole-body MRI. , 2005, AJR. American journal of roentgenology.

[7]  Stuart A. Roberts,et al.  New methods for the initialisation of clusters , 1996, Pattern Recognit. Lett..

[8]  W. A. Hanson,et al.  Interactive 3D segmentation of MRI and CT volumes using morphological operations. , 1992, Journal of computer assisted tomography.

[9]  Kristel Michielsen,et al.  Morphological image analysis , 2000 .

[10]  Jeff A. Bilmes,et al.  A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[11]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[12]  Jerry L. Prince,et al.  A Survey of Current Methods in Medical Image Segmentation , 1999 .

[13]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[14]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[15]  Ovidiu Ghita,et al.  MRI diffusion-based filtering: a note on performance characterisation. , 2005, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[16]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[17]  Sankar K. Pal,et al.  Non-convex clustering using expectation maximization algorithm with rough set initialization , 2003, Pattern Recognit. Lett..

[18]  Shehroz S. Khan,et al.  Cluster center initialization algorithm for K-means clustering , 2004, Pattern Recognit. Lett..

[19]  Michael I. Jordan,et al.  On Convergence Properties of the EM Algorithm for Gaussian Mixtures , 1996, Neural Computation.

[20]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .