Fuzzy c-means clustering with adjustable feature weighting distribution for brain MRI ventricles segmentation

Authors:
Kai Xiao;Sooi Hock Ho;Aboul ella Hassanien;Nguyen Van Du;Qussay Salih
Affiliations:
University of Nottingham, Jalan Broga, Semenyih, Selangor Darul Ehsan, Malaysia;University of Nottingham, Jalan Broga, Semenyih, Selangor Darul Ehsan, Malaysia;Cairo University, Egypt;Thainguyen University of Technology, Vietnam;University of Nottingham, Jalan Broga, Semenyih, Selangor Darul Ehsan, Malaysia
Venue:
SIP '07 Proceedings of the Ninth IASTED International Conference on Signal and Image Processing
Year:
2007

Citing 1
Cited 1

A Validity Measure for Fuzzy Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence

Automatic brain MRI segmentation scheme based on feature weighting factors selection on fuzzy c-means clustering algorithms with Gaussian smoothing

International Journal of Computational Intelligence in Bioinformatics and Systems Biology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Fuzzy c-means (FCM) is a method of clustering which allows one piece of data to belong to two or more clusters and is widely applied in modern applications of image segmentation. The FCM algorithm supports multiple feature inputs. However in standard FCM algorithm, the weighting of each input feature is equal which makes the result of clustering inflexible for a specific application. In this paper, a modified FCM algorithm which allows the input features weighting distribution to be adjusted for specific application is presented. Experimental results have shown that there are significant improvements when the capability for fine tuning input feature weighting distribution is incorporated in Magnetic Resonance Imaging (MRI) lateral ventricles segmentation. An automatic FCM clustering optimization method by applying validity functions as measurements of clustering results is also suggested.