WestminsterResearch

A hybrid approach to MR imaging segmentation using unsupervised clustering and approximate reducts

Widz, Sebastian and Revett, Kenneth and Slezak, Dominik (2005) A hybrid approach to MR imaging segmentation using unsupervised clustering and approximate reducts. In: Slezak, Dominik and Yao, Jingtao and Peters, James F. and Ziarko, Wojciech and Hu, Xiaohua, (eds.) Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing: 10th International Conference, RSFDGrC 2005, Regina, Canada, August 31 - September 3, 2005: Proceedings. Lecture Notes in Computer Science, 2 (3642). Berlin, Germany, Springer, pp. 372-382. ISBN 3540286608

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1007/11548706_39

Abstract

We introduce a hybrid approach to magnetic resonance image segmentation using unsupervised clustering and the rules derived from approximate decision reducts. We utilize the MRI phantoms from the Simulated Brain Database. We run experiments on randomly selected slices from a volumetric set of multi-modal MR images (T1, T2, PD). Segmentation accuracy reaches 96% for the highest resolution images and 89% for the noisiest image volume. We also tested the resultant classifier on real clinical data, which yielded an accuracy of approximately 84%.

Item Type:Book Section
Research Community:University of Westminster > Electronics and Computer Science, School of
ID Code:2226
Deposited On:28 Jun 2006
Last Modified:16 Oct 2009 10:56

Repository Staff Only: item control page