Fuzzy modeling of brain tissues in Bayesian segmentation of brain MR images

Segmentation of brain MRI is the core part in plenty of medical image processing methods. Due to some properties of MR images such as intensity inhomogeneity of tissues, partial volume effect, noise and some other imaging artifacts, segmentation of brain MRI based on voxel gray values is prone to er...

Full description

Bibliographic Details
Main Authors: Farzan, Ali, Ramli, Abdul Rahman, Mashohor, Syamsiah, Mahmud, Rozi
Format: Conference or Workshop Item
Language:English
Published: IEEE 2010
Online Access:http://psasir.upm.edu.my/id/eprint/68851/1/Fuzzy%20modeling%20of%20brain%20tissues%20in%20Bayesian%20segmentation%20of%20brain%20MR%20images.pdf
id oai:psasir.upm.edu.my:68851
record_format eprints
spelling oai:psasir.upm.edu.my:68851 http://psasir.upm.edu.my/id/eprint/68851/ Fuzzy modeling of brain tissues in Bayesian segmentation of brain MR images Farzan, Ali Ramli, Abdul Rahman Mashohor, Syamsiah Mahmud, Rozi Segmentation of brain MRI is the core part in plenty of medical image processing methods. Due to some properties of MR images such as intensity inhomogeneity of tissues, partial volume effect, noise and some other imaging artifacts, segmentation of brain MRI based on voxel gray values is prone to error. Hence involving problem specific information and expert knowledge in designing segmentation algorithms seems to be useful. A two-fold fuzzy segmentation algorithm based on Bayesian method is proposed in this paper. The Bayesian part uses the gray value of voxels in segmenting images and the segmented image is used as the input to fuzzy classifier to improve the misclassified voxels especially in borders between tissues. Similarity index is used to compare our algorithm with the well known method of Ashburner which has been implemented by Statistical Parametric Mapping (SPM) software. Two different brain MRI datasets are used to evaluate the algorithm. Brainweb as a simulated brain MRI dataset and ADNI as real brain MRI dataset are practiced images. Results show that our algorithm performs well in comparison with the one implemented in SPM. It can be concluded that incorporating expert knowledge and problem specific information in segmentation process improve segmentation result. The major advantage of proposed method is that one can update the knowledge base and incorporate new information into segmentation process by adding new fuzzy rules. IEEE 2010 Conference or Workshop Item PeerReviewed text en http://psasir.upm.edu.my/id/eprint/68851/1/Fuzzy%20modeling%20of%20brain%20tissues%20in%20Bayesian%20segmentation%20of%20brain%20MR%20images.pdf Farzan, Ali and Ramli, Abdul Rahman and Mashohor, Syamsiah and Mahmud, Rozi (2010) Fuzzy modeling of brain tissues in Bayesian segmentation of brain MR images. In: 2010 IEEE EMBS Conference on Biomedical Engineering & Sciences (IECBES 2010), 30 Nov.-2 Dec. 2010, Kuala Lumpur, Malaysia. (pp. 77-80). 10.1109/IECBES.2010.5742203
institution UPM IR
collection UPM IR
language English
description Segmentation of brain MRI is the core part in plenty of medical image processing methods. Due to some properties of MR images such as intensity inhomogeneity of tissues, partial volume effect, noise and some other imaging artifacts, segmentation of brain MRI based on voxel gray values is prone to error. Hence involving problem specific information and expert knowledge in designing segmentation algorithms seems to be useful. A two-fold fuzzy segmentation algorithm based on Bayesian method is proposed in this paper. The Bayesian part uses the gray value of voxels in segmenting images and the segmented image is used as the input to fuzzy classifier to improve the misclassified voxels especially in borders between tissues. Similarity index is used to compare our algorithm with the well known method of Ashburner which has been implemented by Statistical Parametric Mapping (SPM) software. Two different brain MRI datasets are used to evaluate the algorithm. Brainweb as a simulated brain MRI dataset and ADNI as real brain MRI dataset are practiced images. Results show that our algorithm performs well in comparison with the one implemented in SPM. It can be concluded that incorporating expert knowledge and problem specific information in segmentation process improve segmentation result. The major advantage of proposed method is that one can update the knowledge base and incorporate new information into segmentation process by adding new fuzzy rules.
format Conference or Workshop Item
author Farzan, Ali
Ramli, Abdul Rahman
Mashohor, Syamsiah
Mahmud, Rozi
spellingShingle Farzan, Ali
Ramli, Abdul Rahman
Mashohor, Syamsiah
Mahmud, Rozi
Fuzzy modeling of brain tissues in Bayesian segmentation of brain MR images
author_facet Farzan, Ali
Ramli, Abdul Rahman
Mashohor, Syamsiah
Mahmud, Rozi
author_sort Farzan, Ali
title Fuzzy modeling of brain tissues in Bayesian segmentation of brain MR images
title_short Fuzzy modeling of brain tissues in Bayesian segmentation of brain MR images
title_full Fuzzy modeling of brain tissues in Bayesian segmentation of brain MR images
title_fullStr Fuzzy modeling of brain tissues in Bayesian segmentation of brain MR images
title_full_unstemmed Fuzzy modeling of brain tissues in Bayesian segmentation of brain MR images
title_sort fuzzy modeling of brain tissues in bayesian segmentation of brain mr images
publisher IEEE
publishDate 2010
url http://psasir.upm.edu.my/id/eprint/68851/1/Fuzzy%20modeling%20of%20brain%20tissues%20in%20Bayesian%20segmentation%20of%20brain%20MR%20images.pdf
_version_ 1698904044457689088
score 12.833586