A unifying framework for partial volume segmentation of brain MR images

Accurate brain tissue segmentation by intensity-based voxel classification of magnetic resonance (MR) images is complicated by partial volume (PV) voxels that contain a mixture of two or more tissue types. In this paper, we present a statistical framework for PV segmentation that encompasses and extends existing techniques. We start from a commonly used parametric statistical image model in which each voxel belongs to one single tissue type, and introduce an additional downsampling step that causes partial voluming along the borders between tissues. An expectation-maximization approach is used to simultaneously estimate the parameters of the resulting model and perform a PV classification. We present results on well-chosen simulated images and on real MR images of the brain, and demonstrate that the use of appropriate spatial prior knowledge not only improves the classifications, but is often indispensable for robust parameter estimation as well. We conclude that general robust PV segmentation of MR brain images requires statistical models that describe the spatial distribution of brain tissues more accurately than currently available models.

[1]  H. Donald Gage,et al.  Statistical models of partial volume effect , 1995, IEEE Trans. Image Process..

[2]  D R Haynor,et al.  Partial volume tissue classification of multichannel magnetic resonance images-a mixel model. , 1991, IEEE transactions on medical imaging.

[3]  Jerry L. Prince,et al.  Unsupervised partial volume estimation in single-channel image data , 2000, Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis. MMBIA-2000 (Cat. No.PR00737).

[4]  Max A. Viergever,et al.  Multiscale Segmentation of Three-Dimensional MR Brain Images , 1999, International Journal of Computer Vision.

[5]  Stanley L. Sclove,et al.  Application of the Conditional Population-Mixture Model to Image Segmentation , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  G. C. Wei,et al.  A Monte Carlo Implementation of the EM Algorithm and the Poor Man's Data Augmentation Algorithms , 1990 .

[7]  Koenraad Van Leemput,et al.  A Statistical Framework for Partial Volume Segmentation , 2001, MICCAI.

[8]  W. Eric L. Grimson,et al.  Enhanced Spatial Priors for Segmentation of Magnetic Resonance Imagery , 1998, MICCAI.

[9]  David H. Laidlaw,et al.  Partial-volume Bayesian classification of material mixtures in MR volume data using voxel histograms , 1997, IEEE Transactions on Medical Imaging.

[10]  W. Eric L. Grimson,et al.  Adaptive Segmentation of MRI Data , 1995, CVRMed.

[11]  Alan C. F. Colchester,et al.  Intensity-Based Object Extraction from 3D Medical Images Including a Correction of Partial Volume Errors , 1994, BMVC.

[12]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[13]  J. Besag.  Efficiency of pseudolikelihood estimation for simple Gaussian fields , 1977 .

[14]  P. Santago,et al.  Quantification of MR brain images by mixture density and partial volume modeling , 1993, IEEE Trans. Medical Imaging.

[15]  E. Ising.  Beitrag zur Theorie des Ferromagnetismus , 1925 .

[16]  Koenraad Van Leemput,et al.  Automated model-based tissue classification of MR images of the brain , 1999, IEEE Transactions on Medical Imaging.

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

[18]  James C. Gee,et al.  Robust partial-volume tissue classification of cerebral MRI scans , 1997, Medical Imaging.

[19]  Miguel Ángel,et al.  Morphometric analysis of brain structures in MRI , 1999 .

[20]  Michael Brady,et al.  Estimating the bias field of MR images , 1997, IEEE Transactions on Medical Imaging.

[21]  J. Alison Noble,et al.  An adaptive segmentation algorithm for time-of-flight MRA data , 1999, IEEE Transactions on Medical Imaging.

[22]  Ron Kikinis,et al.  Markov random field segmentation of brain MR images , 1997, IEEE Transactions on Medical Imaging.

[23]  Zhengrong Liang,et al.  Parameter estimation and tissue segmentation from multispectral MR images , 1994, IEEE Trans. Medical Imaging.

[24]  Koenraad Van Leemput,et al.  Automated segmentation of multiple sclerosis lesions by model outlier detection , 2001, IEEE Transactions on Medical Imaging.

[25]  New York Dover,et al.  ON THE CONVERGENCE PROPERTIES OF THE EM ALGORITHM , 1983 .

[26]  Koenraad Van Leemput,et al.  Automated model-based bias field correction of MR images of the brain , 1999, IEEE Transactions on Medical Imaging.

[27]  É. Moulines,et al.  Convergence of a stochastic approximation version of the EM algorithm , 1999 .

[28]  X. Descombes,et al.  The Ising/Potts model is not well suited to segmentation tasks , 1996, 1996 IEEE Digital Signal Processing Workshop Proceedings.

[29]  R. Leahy,et al.  Magnetic Resonance Image Tissue Classification Using a Partial Volume Model , 2001, NeuroImage.

[30]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[31]  Z Wu,et al.  A Bayesian approach to subvoxel tissue classification in NMR microscopic images of trabecular bone , 1994, Magnetic resonance in medicine.

[32]  D. M. Titterington,et al.  Comments on "Application of the Conditional Population-Mixture Model to Image Segmentation" , 1984, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Mohamed-Jalal Fadili,et al.  Brain tissue classification of magnetic resonance images using partial volume modeling , 2000, IEEE Transactions on Medical Imaging.

[34]  Reto Meuli,et al.  Robust parameter estimation of intensity distributions for brain magnetic resonance images , 1998, IEEE Transactions on Medical Imaging.

[35]  Stan Z. Li,et al.  Markov Random Field Modeling in Computer Vision , 1995, Computer Science Workbench.