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.


Segmentation results of real data from IBSR with the name 12_3 (39th image). (a) Initial image, (b) ground truth, and (c–f) the segmentation results of GMM, Wells, MCFC, and MNGMM.
© Copyright Policy
Related In: Results  -  Collection

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

fig6: Segmentation results of real data from IBSR with the name 12_3 (39th image). (a) Initial image, (b) ground truth, and (c–f) the segmentation results of GMM, Wells, MCFC, and MNGMM.

Mentions: Figure 6 shows the segmentation results on a real brain MR data from the Internet brain segmentation repository (IBSR at http://www.cma.mgh.harvard.edu/ibsr/) with the name 12_3 (39th image). The intensity distribution of the basal ganglia is midway between the assumed distributions of GM and WM and the basal ganglia have low contrast. From the results, we can find that our method can obtain accurate result. In order to quantitatively evaluate the benefits, we segmented 20 standard sets of real brain MR data from IBSR by using GMM, Wells method, MCFC, and MNGMM. The average quantitative results of GM, WM, and CSF are listed in Table 2. It can be seen that our method is more accurate than others.


Multigrid Nonlocal Gaussian Mixture Model for Segmentation of Brain Tissues in Magnetic Resonance Images
Segmentation results of real data from IBSR with the name 12_3 (39th image). (a) Initial image, (b) ground truth, and (c–f) the segmentation results of GMM, Wells, MCFC, and MNGMM.
© Copyright Policy
Related In: Results  -  Collection

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

fig6: Segmentation results of real data from IBSR with the name 12_3 (39th image). (a) Initial image, (b) ground truth, and (c–f) the segmentation results of GMM, Wells, MCFC, and MNGMM.
Mentions: Figure 6 shows the segmentation results on a real brain MR data from the Internet brain segmentation repository (IBSR at http://www.cma.mgh.harvard.edu/ibsr/) with the name 12_3 (39th image). The intensity distribution of the basal ganglia is midway between the assumed distributions of GM and WM and the basal ganglia have low contrast. From the results, we can find that our method can obtain accurate result. In order to quantitatively evaluate the benefits, we segmented 20 standard sets of real brain MR data from IBSR by using GMM, Wells method, MCFC, and MNGMM. The average quantitative results of GM, WM, and CSF are listed in Table 2. It can be seen that our method is more accurate than others.

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.