DMCA
T.: Anatomy dependent multi-context fuzzy clustering for separation of brain tissues in mr images (2004)
| Venue: | In: 2nd International Workshop on Medial Imaging and Augmented Reality |
| Citations: | 1 - 0 self |
BibTeX
@INPROCEEDINGS{Zhu04t.:anatomy,
author = {Cz Zhu and Fc Lin and Tz Jiang},
title = {T.: Anatomy dependent multi-context fuzzy clustering for separation of brain tissues in mr images},
booktitle = {In: 2nd International Workshop on Medial Imaging and Augmented Reality},
year = {2004}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. In a previous work, a local tissue distribution model and multi-context fuzzy clustering (MCFC) method had been proposed to successfully classify 3D T1-weighted MR images into tissues of white matter, gray matter, and cerebral spinal fluid in the condition of intensity inhomogeneities. This pa-per presents a complementary and improved version of MCFC. Firstly, quanti-tative analyses are added to validate the soundness of basic assumptions for MCFC. Carefully studies on the experiment results of MCFC on a set of simu-lated MR data disclose a fact that misclassification rate in a context of MCFC is spatially dependent on the anatomical position of the context; moreover, most of the misclassifications concentrate in regions of brain stem and cerebellum. Such unique distribution pattern of misclassification inspires us to choose dif-ferent context size at such special anatomical regions. This anatomy-dependent MCFC (adMCFC) has been tested on both simulated and 10 clinical T1-weighted images and the experiments results show that adMCFC outperforms MCFC and other related methods. 1
Keyphrases
anatomy dependent multi-context fuzzy mr image brain tissue experiment result improved version special anatomical region related method simu-lated mr data unique distribution pattern misclassification rate quanti-tative analysis local tissue distribution model t1-weighted mr image previous work anatomical position white matter multi-context fuzzy clustering carefully study cerebral spinal fluid anatomy-dependent mcfc clinical t1-weighted image intensity inhomogeneity dif-ferent context size gray matter admcfc outperforms mcfc basic assumption misclassification inspires brain stem
