Universiti Teknologi Malaysia Institutional Repository

Cerebrospinal fluid image segmentation using spatial fuzzy clustering method with improved evolutionary expectation maximization

Abdullah, Afnizanfaizal and irayama, Akihiro and Yatsushiro, Satoshi and Matsumae, Mitsunori and Kuroda, Kagayaki (2013) Cerebrospinal fluid image segmentation using spatial fuzzy clustering method with improved evolutionary expectation maximization. In: 35th Annual International Conference of the IEEE EMBS, 3 - 7 July, 2013, Osaka, Japan.

Full text not available from this repository.

Official URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumbe...


Visualization of cerebrospinal fluid (CSF), that flow in the brain and spinal cord, plays an important role to detect neurodegenerative diseases such as Alzheimer's disease. This is performed by measuring the substantial changes in the CSF flow dynamics, volume and/or pressure gradient. Magnetic resonance imaging (MRI) technique has become a prominent tool to quantitatively measure these changes and image segmentation method has been widely used to distinguish the CSF flows from the brain tissues. However, this is often hampered by the presence of partial volume effect in the images. In this paper, a new hybrid evolutionary spatial fuzzy clustering method is introduced to overcome the partial volume effect in the MRI images. The proposed method incorporates Expectation Maximization (EM) method, which is improved by the evolutionary operations of the Genetic Algorithm (GA) to differentiate the CSF from the brain tissues. The proposed improvement is incorporated into a spatial-based fuzzy clustering (SFCM) method to improve segmentation of the boundary curve of the CSF and the brain tissues. The proposed method was validated using MRI images of Alzheimer's disease patient. The results presented that the proposed method is capable to filter the CSF regions from the brain tissues more effectively compared to the standard EM, FCM, and SFCM methods.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:Image segmentation, Magnetic resonance imaging, Diseases, Clustering methods, Biomedical imaging, Genetic algorithms, Fluids
Subjects:Q Science > QH Natural history > QH301 Biology
Q Science > QR Microbiology
ID Code:50933
Deposited By: Haliza Zainal
Deposited On:27 Jan 2016 01:53
Last Modified:22 Jun 2017 01:28

Repository Staff Only: item control page