Cargando…

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

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 de...

Descripción completa

Detalles Bibliográficos
Autores principales: Elazab, Ahmed, Wang, Changmiao, Jia, Fucang, Wu, Jianhuang, Li, Guanglin, Hu, Qingmao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4697674/
https://www.ncbi.nlm.nih.gov/pubmed/26793269
http://dx.doi.org/10.1155/2015/485495
_version_ 1782407975064829952
author Elazab, Ahmed
Wang, Changmiao
Jia, Fucang
Wu, Jianhuang
Li, Guanglin
Hu, Qingmao
author_facet Elazab, Ahmed
Wang, Changmiao
Jia, Fucang
Wu, Jianhuang
Li, Guanglin
Hu, Qingmao
author_sort Elazab, Ahmed
collection PubMed
description 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.
format Online
Article
Text
id pubmed-4697674
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher Hindawi Publishing Corporation
record_format MEDLINE/PubMed
spelling pubmed-46976742016-01-20 Segmentation of Brain Tissues from Magnetic Resonance Images Using Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering Elazab, Ahmed Wang, Changmiao Jia, Fucang Wu, Jianhuang Li, Guanglin Hu, Qingmao Comput Math Methods Med Research Article 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. Hindawi Publishing Corporation 2015 2015-12-17 /pmc/articles/PMC4697674/ /pubmed/26793269 http://dx.doi.org/10.1155/2015/485495 Text en Copyright © 2015 Ahmed Elazab et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Elazab, Ahmed
Wang, Changmiao
Jia, Fucang
Wu, Jianhuang
Li, Guanglin
Hu, Qingmao
Segmentation of Brain Tissues from Magnetic Resonance Images Using Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering
title Segmentation of Brain Tissues from Magnetic Resonance Images Using Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering
title_full Segmentation of Brain Tissues from Magnetic Resonance Images Using Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering
title_fullStr Segmentation of Brain Tissues from Magnetic Resonance Images Using Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering
title_full_unstemmed Segmentation of Brain Tissues from Magnetic Resonance Images Using Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering
title_short Segmentation of Brain Tissues from Magnetic Resonance Images Using Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering
title_sort segmentation of brain tissues from magnetic resonance images using adaptively regularized kernel-based fuzzy c-means clustering
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4697674/
https://www.ncbi.nlm.nih.gov/pubmed/26793269
http://dx.doi.org/10.1155/2015/485495
work_keys_str_mv AT elazabahmed segmentationofbraintissuesfrommagneticresonanceimagesusingadaptivelyregularizedkernelbasedfuzzycmeansclustering
AT wangchangmiao segmentationofbraintissuesfrommagneticresonanceimagesusingadaptivelyregularizedkernelbasedfuzzycmeansclustering
AT jiafucang segmentationofbraintissuesfrommagneticresonanceimagesusingadaptivelyregularizedkernelbasedfuzzycmeansclustering
AT wujianhuang segmentationofbraintissuesfrommagneticresonanceimagesusingadaptivelyregularizedkernelbasedfuzzycmeansclustering
AT liguanglin segmentationofbraintissuesfrommagneticresonanceimagesusingadaptivelyregularizedkernelbasedfuzzycmeansclustering
AT huqingmao segmentationofbraintissuesfrommagneticresonanceimagesusingadaptivelyregularizedkernelbasedfuzzycmeansclustering