Brain MR image segmentation based on local Gaussian mixture model and nonlocal spatial regularization

Abstract Brain Magnetic Resonance (MR) images often suffer from the inhomogeneous intensities caused by the bias field and heavy noise. The most widely used image segmentation algorithms, which typically rely on the homogeneity of image intensities in different regions, often fail to provide accurate segmentation results due to the existence of bias field and heavy noise. This paper proposes a novel variational approach for brain image segmentation with simultaneous bias correction. We define an energy functional with a local data fitting term and a nonlocal spatial regularization term. The local data fitting term is based on the idea of local Gaussian mixture model (LGMM), which locally models the distribution of each tissue by a linear combination of Gaussian function. By the LGMM, the bias field function in an additive form is embedded to the energy functional, which is helpful for eliminating the influence of the intensity inhomogeneity. For reducing the influence of noise and getting a smooth segmentation, the nonlocal spatial regularization is drawn upon, which is good at preserving fine structures in brain images. Experiments performed on simulated as well as real MR brain data and comparisons with other related methods are given to demonstrate the effectiveness of the proposed method.

[1]  Jun Liu,et al.  Image Segmentation Using a Local GMM in a Variational Framework , 2012, Journal of Mathematical Imaging and Vision.

[2]  G. Barker,et al.  Correction of intensity nonuniformity in MR images of any orientation. , 1993, Magnetic resonance imaging.

[3]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[4]  Colin Studholme,et al.  A non-local fuzzy segmentation method: Application to brain MRI , 2009, Pattern Recognit..

[5]  Lalit Gupta,et al.  A gaussian-mixture-based image segmentation algorithm , 1998, Pattern Recognit..

[6]  Chunming Li,et al.  Image segmentation with simultaneous illumination and reflectance estimation: An energy minimization approach , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[7]  Yunjie Chen,et al.  An improved level set method for brain MR images segmentation and bias correction , 2009, Comput. Medical Imaging Graph..

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

[9]  D. Kennedy,et al.  Anatomic segmentation and volumetric calculations in nuclear magnetic resonance imaging. , 1989, IEEE transactions on medical imaging.

[10]  Jerry L. Prince,et al.  Adaptive fuzzy segmentation of magnetic resonance images , 1999, IEEE Transactions on Medical Imaging.

[11]  P. Narayana,et al.  Correction for intensity falloff in surface coil magnetic resonance imaging. , 1988, Medical physics.

[12]  Hong Yan,et al.  An adaptive spatial fuzzy clustering algorithm for 3-D MR image segmentation , 2003, IEEE Transactions on Medical Imaging.

[13]  John C. Gore,et al.  A robust parametric method for bias field estimation and segmentation of MR images , 2009, CVPR.

[14]  Guy Gilboa,et al.  Nonlocal Operators with Applications to Image Processing , 2008, Multiscale Model. Simul..

[15]  Chunming Li,et al.  A Variational Level Set Approach to Segmentation and Bias Correction of Images with Intensity Inhomogeneity , 2008, MICCAI.

[16]  Nikolas P. Galatsanos,et al.  A spatially constrained mixture model for image segmentation , 2005, IEEE Transactions on Neural Networks.

[17]  S. Arridge,et al.  Sources of intensity nonuniformity in spin echo images at 1.5 T , 1994, Magnetic resonance in medicine.

[18]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[19]  Yunjie Chen,et al.  Image segmentation and bias correction via an improved level set method , 2011, Neurocomputing.

[20]  Nicholas Ayache,et al.  Maximum Likelihood Estimation of the Bias Field in MR Brain Images: Investigating Different Modelings of the Imaging Process , 2001, MICCAI.

[21]  John W. Fisher,et al.  A Unified Variational Approach to Denoising and Bias Correction in MR , 2003, IPMI.

[22]  Colin Studholme,et al.  A non-local fuzzy segmentation method: Application to brain MRI , 2011, Pattern Recognit..

[23]  Martin Styner,et al.  Parametric estimate of intensity inhomogeneities applied to MRI , 2000, IEEE Transactions on Medical Imaging.

[24]  Aly A. Farag,et al.  A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data , 2002, IEEE Transactions on Medical Imaging.

[25]  Alan L. Yuille,et al.  Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Daoqiang Zhang,et al.  Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation , 2007, Pattern Recognit..

[27]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[28]  Hayit Greenspan,et al.  Constrained Gaussian mixture model framework for automatic segmentation of MR brain images , 2006, IEEE Transactions on Medical Imaging.

[29]  Chunming Li,et al.  MRI Tissue Classification and Bias Field Estimation Based on Coherent Local Intensity Clustering: A Unified Energy Minimization Framework , 2009, IPMI.

[30]  Dzung L. Pham,et al.  Spatial Models for Fuzzy Clustering , 2001, Comput. Vis. Image Underst..

[31]  R. Gupta,et al.  Polynomial modeling and reduction of RF body coil spatial inhomogeneity in MRI , 1993, IEEE Trans. Medical Imaging.

[32]  Luminita A. Vese,et al.  Nonlocal Variational Image Deblurring Models in the Presence of Gaussian or Impulse Noise , 2009, SSVM.

[33]  Bostjan Likar,et al.  A Review of Methods for Correction of Intensity Inhomogeneity in MRI , 2007, IEEE Transactions on Medical Imaging.

[34]  Qiang Chen,et al.  Fuzzy Local Gaussian Mixture Model for Brain MR Image Segmentation , 2012, IEEE Transactions on Information Technology in Biomedicine.

[35]  Paul D Acton,et al.  Artificial neural network classifier for the diagnosis of Parkinson's disease using [99mTc]TRODAT-1 and SPECT , 2006, Physics in medicine and biology.

[36]  M. A. Balafar,et al.  Gaussian mixture model based segmentation methods for brain MRI images , 2012, Artificial Intelligence Review.

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

[38]  R. Redner,et al.  Mixture densities, maximum likelihood, and the EM algorithm , 1984 .

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

[40]  Lei Zhang,et al.  A variational multiphase level set approach to simultaneous segmentation and bias correction , 2010, 2010 IEEE International Conference on Image Processing.

[41]  R. Woods,et al.  Cortical change in Alzheimer's disease detected with a disease-specific population-based brain atlas. , 2001, Cerebral cortex.

[42]  L. Axel,et al.  Intensity correction in surface-coil MR imaging. , 1987, AJR. American journal of roentgenology.

[43]  Manuel Graña,et al.  A parametric gradient descent MRI intensity inhomogeneity correction algorithm , 2007, Pattern Recognit. Lett..