Limits...
Segmentation of Brain Tissues from Magnetic Resonance Images Using Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering.

Elazab A, Wang C, Jia F, Wu J, Li G, Hu Q - Comput Math Methods Med (2015)

Bottom Line: The algorithms employ the heterogeneity of grayscales in the neighborhood and exploit this measure for local contextual information and replace the standard Euclidean distance with Gaussian radial basis kernel functions.The main advantages are adaptiveness to local context, enhanced robustness to preserve image details, independence of clustering parameters, and decreased computational costs.Experimental results show that the proposed algorithms are superior in preserving image details and segmentation accuracy while maintaining a low computational complexity.

View Article: PubMed Central - PubMed

Affiliation: Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 1068 Xueyuan Boulevard, Shenzhen 518055, China; University of Chinese Academy of Sciences, 52 Sanlihe Road, Beijing 100864, China; Faculty of Computers and Information, Mansoura University, Elgomhouria Street, Mansoura 35516, Egypt.

ABSTRACT
An adaptively regularized kernel-based fuzzy C-means clustering framework is proposed for segmentation of brain magnetic resonance images. The framework can be in the form of three algorithms for the local average grayscale being replaced by the grayscale of the average filter, median filter, and devised weighted images, respectively. The algorithms employ the heterogeneity of grayscales in the neighborhood and exploit this measure for local contextual information and replace the standard Euclidean distance with Gaussian radial basis kernel functions. The main advantages are adaptiveness to local context, enhanced robustness to preserve image details, independence of clustering parameters, and decreased computational costs. The algorithms have been validated against both synthetic and clinical magnetic resonance images with different types and levels of noises and compared with 6 recent soft clustering algorithms. Experimental results show that the proposed algorithms are superior in preserving image details and segmentation accuracy while maintaining a low computational complexity.

No MeSH data available.


Related in: MedlinePlus

Calculation and effect of the regularization parameter in different cases. (a) Noisy image. (b) 6 × 6 subimage, red rectangle from (a), with 3 different windows A, B, and C. (c) Weights associated with each pixel using the proposed method. (d) Membership values after three iterations.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4697674&req=5

fig1: Calculation and effect of the regularization parameter in different cases. (a) Noisy image. (b) 6 × 6 subimage, red rectangle from (a), with 3 different windows A, B, and C. (c) Weights associated with each pixel using the proposed method. (d) Membership values after three iterations.

Mentions: The parameter φi assigns higher values for those pixels with high LVC (for pixel i being brighter than the average grayscale of its neighbors, φi will be 2 + ωi, and ωi will be large when the sum of LVC within its neighborhood is large) and lower values otherwise. When the local average grayscale is equal to the grayscale of the central pixel, φi will be zero and the algorithm will behave as the standard FCM algorithm. The value 2 in (11) is set through experiments to balance between the convergence rate and the capability to preserve details. The proposed parameter φi is embedded into (5) to replace α. Figure 1 shows the calculation of φi with different cases of noise.


Segmentation of Brain Tissues from Magnetic Resonance Images Using Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering.

Elazab A, Wang C, Jia F, Wu J, Li G, Hu Q - Comput Math Methods Med (2015)

Calculation and effect of the regularization parameter in different cases. (a) Noisy image. (b) 6 × 6 subimage, red rectangle from (a), with 3 different windows A, B, and C. (c) Weights associated with each pixel using the proposed method. (d) Membership values after three iterations.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4697674&req=5

fig1: Calculation and effect of the regularization parameter in different cases. (a) Noisy image. (b) 6 × 6 subimage, red rectangle from (a), with 3 different windows A, B, and C. (c) Weights associated with each pixel using the proposed method. (d) Membership values after three iterations.
Mentions: The parameter φi assigns higher values for those pixels with high LVC (for pixel i being brighter than the average grayscale of its neighbors, φi will be 2 + ωi, and ωi will be large when the sum of LVC within its neighborhood is large) and lower values otherwise. When the local average grayscale is equal to the grayscale of the central pixel, φi will be zero and the algorithm will behave as the standard FCM algorithm. The value 2 in (11) is set through experiments to balance between the convergence rate and the capability to preserve details. The proposed parameter φi is embedded into (5) to replace α. Figure 1 shows the calculation of φi with different cases of noise.

Bottom Line: The algorithms employ the heterogeneity of grayscales in the neighborhood and exploit this measure for local contextual information and replace the standard Euclidean distance with Gaussian radial basis kernel functions.The main advantages are adaptiveness to local context, enhanced robustness to preserve image details, independence of clustering parameters, and decreased computational costs.Experimental results show that the proposed algorithms are superior in preserving image details and segmentation accuracy while maintaining a low computational complexity.

View Article: PubMed Central - PubMed

Affiliation: Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 1068 Xueyuan Boulevard, Shenzhen 518055, China; University of Chinese Academy of Sciences, 52 Sanlihe Road, Beijing 100864, China; Faculty of Computers and Information, Mansoura University, Elgomhouria Street, Mansoura 35516, Egypt.

ABSTRACT
An adaptively regularized kernel-based fuzzy C-means clustering framework is proposed for segmentation of brain magnetic resonance images. The framework can be in the form of three algorithms for the local average grayscale being replaced by the grayscale of the average filter, median filter, and devised weighted images, respectively. The algorithms employ the heterogeneity of grayscales in the neighborhood and exploit this measure for local contextual information and replace the standard Euclidean distance with Gaussian radial basis kernel functions. The main advantages are adaptiveness to local context, enhanced robustness to preserve image details, independence of clustering parameters, and decreased computational costs. The algorithms have been validated against both synthetic and clinical magnetic resonance images with different types and levels of noises and compared with 6 recent soft clustering algorithms. Experimental results show that the proposed algorithms are superior in preserving image details and segmentation accuracy while maintaining a low computational complexity.

No MeSH data available.


Related in: MedlinePlus