Universiti Teknologi Malaysia Institutional Repository

Brain tissue classification in magnetic resonance images

Yazdani, Sapideh and Yusof, Rubiyah and Karimian, Alireza and Riazi, Amir Hossein (2015) Brain tissue classification in magnetic resonance images. Jurnal Teknologi, 72 (2). pp. 29-32. ISSN 0127-9696


Official URL: http://dx.doi.org/10.11113/jt.v72.3879


Automatic segmentation of brain images is a challenging problem due to the complex structure of brain images, as well as to the absence of anatomy models. Brain segmentation into white matter, gray matter, and cerebral spinal fluid, is an important stage for many problems, including the studies in 3-D visualizations for disease detection and surgical planning. In this paper we present a novel fully automated framework for tissue classification of brain in MR Images that is a combination of two techniques: GLCM and SVM, each of which has been customized for the problem of brain tissue segmentation such that the results are more robust than its individual components that is demonstrated through experiments. The proposed framework has been validated on brainweb dataset of different modalities, with desirable performance in the presence of noise and bias field. To evaluate the performance of the proposed method the Kappa similarity index is computed. Our method achieves higher kappa index (91.5) compared with other methods currently in use. As an application, our method has been used for segmentation of MR images with promising results.

Item Type:Article
Uncontrolled Keywords:gray level cooccurrence matrices, magnetic resonance images, tissue classification
Subjects:R Medicine > RC Internal medicine
Divisions:Malaysia-Japan International Institute of Technology
ID Code:57978
Deposited By: Haliza Zainal
Deposited On:04 Dec 2016 04:08
Last Modified:15 Dec 2021 00:54

Repository Staff Only: item control page