Limits...
Multigrid Nonlocal Gaussian Mixture Model for Segmentation of Brain Tissues in Magnetic Resonance Images

View Article: PubMed Central - PubMed

ABSTRACT

We propose a novel segmentation method based on regional and nonlocal information to overcome the impact of image intensity inhomogeneities and noise in human brain magnetic resonance images. With the consideration of the spatial distribution of different tissues in brain images, our method does not need preestimation or precorrection procedures for intensity inhomogeneities and noise. A nonlocal information based Gaussian mixture model (NGMM) is proposed to reduce the effect of noise. To reduce the effect of intensity inhomogeneity, the multigrid nonlocal Gaussian mixture model (MNGMM) is proposed to segment brain MR images in each nonoverlapping multigrid generated by using a new multigrid generation method. Therefore the proposed model can simultaneously overcome the impact of noise and intensity inhomogeneity and automatically classify 2D and 3D MR data into tissues of white matter, gray matter, and cerebral spinal fluid. To maintain the statistical reliability and spatial continuity of the segmentation, a fusion strategy is adopted to integrate the clustering results from different grid. The experiments on synthetic and clinical brain MR images demonstrate the superior performance of the proposed model comparing with several state-of-the-art algorithms.

No MeSH data available.


Generation of the grid: (a) initial results; (b) histogram of patch (6,2); (c) histogram of patch (3, 3); (d)–(f) results of multigrid.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5015012&req=5

fig2: Generation of the grid: (a) initial results; (b) histogram of patch (6,2); (c) histogram of patch (3, 3); (d)–(f) results of multigrid.

Mentions: In this paper we present a new method to generate the multigrid. Firstly, the boundary of the brain needs to be found, because there are a large number of pixels belonging to the background in brain MR images, which usually affect the accuracy of segmentation methods. Secondly, the brain region is divided into N × N small nonoverlapping grids. The generated nonoverlapping grids may not satisfy assumption (3). Figure 2 shows the generated multigrid on brain MR images. In this paper, we set N = 6. It can be seen from Figure 2(a) that the grids (1, 1) and (6, 3) only contain some CSF pixels and the grids (1, 6) and (6, 6) have no brain tissues. Furthermore, the grid (6, 1) has no pixels of the WM. The NGMM cannot obtain accurate results based on these grids. In order to deal with this problem, the small grids need to be combined. The combine process includes 6 steps as follows.


Multigrid Nonlocal Gaussian Mixture Model for Segmentation of Brain Tissues in Magnetic Resonance Images
Generation of the grid: (a) initial results; (b) histogram of patch (6,2); (c) histogram of patch (3, 3); (d)–(f) results of multigrid.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5015012&req=5

fig2: Generation of the grid: (a) initial results; (b) histogram of patch (6,2); (c) histogram of patch (3, 3); (d)–(f) results of multigrid.
Mentions: In this paper we present a new method to generate the multigrid. Firstly, the boundary of the brain needs to be found, because there are a large number of pixels belonging to the background in brain MR images, which usually affect the accuracy of segmentation methods. Secondly, the brain region is divided into N × N small nonoverlapping grids. The generated nonoverlapping grids may not satisfy assumption (3). Figure 2 shows the generated multigrid on brain MR images. In this paper, we set N = 6. It can be seen from Figure 2(a) that the grids (1, 1) and (6, 3) only contain some CSF pixels and the grids (1, 6) and (6, 6) have no brain tissues. Furthermore, the grid (6, 1) has no pixels of the WM. The NGMM cannot obtain accurate results based on these grids. In order to deal with this problem, the small grids need to be combined. The combine process includes 6 steps as follows.

View Article: PubMed Central - PubMed

ABSTRACT

We propose a novel segmentation method based on regional and nonlocal information to overcome the impact of image intensity inhomogeneities and noise in human brain magnetic resonance images. With the consideration of the spatial distribution of different tissues in brain images, our method does not need preestimation or precorrection procedures for intensity inhomogeneities and noise. A nonlocal information based Gaussian mixture model (NGMM) is proposed to reduce the effect of noise. To reduce the effect of intensity inhomogeneity, the multigrid nonlocal Gaussian mixture model (MNGMM) is proposed to segment brain MR images in each nonoverlapping multigrid generated by using a new multigrid generation method. Therefore the proposed model can simultaneously overcome the impact of noise and intensity inhomogeneity and automatically classify 2D and 3D MR data into tissues of white matter, gray matter, and cerebral spinal fluid. To maintain the statistical reliability and spatial continuity of the segmentation, a fusion strategy is adopted to integrate the clustering results from different grid. The experiments on synthetic and clinical brain MR images demonstrate the superior performance of the proposed model comparing with several state-of-the-art algorithms.

No MeSH data available.