Supervised segmentation of MRI brain images using combination of multiple classifiers

被引:0
作者
Ali Ahmadvand
Mohammad Sharififar
Mohammad Reza Daliri
机构
[1] Iran University of Science and Technology (IUST),School of Computer Engineering
[2] Iran University of Science and Technology (IUST),Biomedical Engineering Department, Faculty of Electrical Engineering
来源
Australasian Physical & Engineering Sciences in Medicine | 2015年 / 38卷
关键词
Brain segmentation; Magnetic resonance imaging (MRI); Combination of multiple classifiers (CMC); K-nearest neighbor (KNN);
D O I
暂无
中图分类号
学科分类号
摘要
Segmentation of different tissues is one of the initial and most critical tasks in different aspects of medical image processing. Manual segmentation of brain images resulted from magnetic resonance imaging is time consuming, so automatic image segmentation is widely used in this area. Ensemble based algorithms are very reliable and generalized methods for classification. In this paper, a supervised method named dynamic classifier selection-dynamic local training local tanimoto index, which is a member of combination of multiple classifiers (CMCs) methods is proposed. The proposed method uses dynamic local training sets instead of a full statics one and also it change the classifier rank criterion properly for brain tissue classification. Selection policy for combining the different decisions is implemented here and the K-nearest neighbor algorithm is used to find the best local classifier. Experimental results show that the proposed method can classify the real datasets of the internet brain segmentation repository better than all single classifiers in ensemble and produces significantly improvement on other CMCs methods.
引用
收藏
页码:241 / 253
页数:12
相关论文
共 112 条
[1]  
Lin G-C(2012)Multispectral MR images segmentation based on fuzzy knowledge and modified seeded region growing Magn Reson Imaging 30 230-246
[2]  
Wang WJ(2014)Brain MR Image Segmentation Methods and Applications OMICS J Radiol 3 e130-355
[3]  
Kang CC(2002)Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain Neuron 33 341-347
[4]  
Wang CM(2012)Fuzzy local Gaussian mixture model for brain MR image segmentation Inf Technol Biomed, IEEE Trans 16 339-711
[5]  
Ahmadvand A(2007)Genetic algorithms for finite mixture model based voxel classification in neuroimaging Med Imaging, IEEE Trans 26 696-186
[6]  
Daliri M(1997)Statistical approach to segmentation of single-channel cerebral MR images Med Imaging, IEEE Trans 16 176-848
[7]  
Fischl B(2014)Multispectral MRI image segmentation using Markov random field model Signal, Image Video Process 16 840-945
[8]  
Salat DH(2012)Brain tissue segmentation in MR images based on a hybrid of MRF and social algorithms Med Image Anal 21 934-24
[9]  
Busa E(2002)An accurate and efficient Bayesian method for automatic segmentation of brain MRI Medical Imaging, IEEE Trans 2 12-818
[10]  
Albert M(2003)MRF-based image segmentation using ant colony system Electron Lett Comp Vis Image Anal 256 808-88