Unsupervised Segmentation Method for Brain MRI Based on Fuzzy Techniques

In the present research a novel spatially weighted Fuzzy C-Means (FCM) clustering algorithm for image thresholding is presented. The segmentation technique is for magnetic resonance (MR) images of the brain based on fuzzy algorithms for learning vector quantization (FALVQ) by creating of a combined...

Full description

Saved in:
Bibliographic Details
Published inAl-Nahrain journal for engineering sciences Vol. 13; no. 1
Main Author Nasser N. Khamiss
Format Journal Article
LanguageEnglish
Published Al-Nahrain Journal for Engineering Sciences 01.03.2010
Subjects
Brain MRI
Unsupervised Segmentation
Online AccessGet full text

Cover

More Information
Summary:In the present research a novel spatially weighted Fuzzy C-Means (FCM) clustering algorithm for image thresholding is presented. The segmentation technique is for magnetic resonance (MR) images of the brain based on fuzzy algorithms for learning vector quantization (FALVQ) by creating of a combined method in utilizing both LVQ (learning vector quantization) and the fuzzy technique. Such a technique is obtaining more efficient method for the process of diagnosis of the human brain tumor without the need for sophisticated steps or human manner. To speed up the FCM algorithm, the iteration is carried out with the statistical gray level histogram of image instead of the conventional whole data of image. Some comparisons with classical thresholding algorithm and fuzzy thresholding algorithm are also considered in this research. Experimental results on real images are given to demonstrate the effectiveness of the proposed algorithm. In addition, due to the neighborhood model, the proposed method is more tolerant to noise.
ISSN:2521-9154
2521-9162