TY - GEN
T1 - Hybrid GA Variational Bayes inference of finite mixture models for voxel classification in brain images
AU - Sun, Li
AU - Zhang, Yanning
AU - Ma, Miao
AU - Tian, Guangjian
PY - 2011
Y1 - 2011
N2 - This paper proposes a hybrid Genetic Algorithm (GA) and Variational Bayes (VB) inference Gaussian mixture model parameters estimation methodology for unsupervised voxel classification. Unlike Expectation-Maximization algorithm (EM), the mixture model distribution parameters are modeled by a set of hyper-parameters in VB inference framework. These hyper-parameters which characterize the mixture model distributions are estimated by a Variational Expectation-Maximization (VEM) learning algorithm. However, it is difficult to initialize the hyper-parameters for VEM algorithm without prior knowledge. This study introduces a hybrid GA and VEM methodology to estimate the finite mixture models fully automatically without any specific initialization steps for voxel classification in brain images. The proposed VEM, GAVEM algorithms are validated and compared with GA and EM algorithms on real three-dimensional human brain MRI images. The voxel tissue classification results demonstrate that VEM, and GAVEM algorithms achieve competitive segmentation results compared to other parameters estimation algorithms, and fully automatically.
AB - This paper proposes a hybrid Genetic Algorithm (GA) and Variational Bayes (VB) inference Gaussian mixture model parameters estimation methodology for unsupervised voxel classification. Unlike Expectation-Maximization algorithm (EM), the mixture model distribution parameters are modeled by a set of hyper-parameters in VB inference framework. These hyper-parameters which characterize the mixture model distributions are estimated by a Variational Expectation-Maximization (VEM) learning algorithm. However, it is difficult to initialize the hyper-parameters for VEM algorithm without prior knowledge. This study introduces a hybrid GA and VEM methodology to estimate the finite mixture models fully automatically without any specific initialization steps for voxel classification in brain images. The proposed VEM, GAVEM algorithms are validated and compared with GA and EM algorithms on real three-dimensional human brain MRI images. The voxel tissue classification results demonstrate that VEM, and GAVEM algorithms achieve competitive segmentation results compared to other parameters estimation algorithms, and fully automatically.
KW - Bayes inference
KW - Expectation-maximization algorithm (EM)
KW - Finite mixture model (FMM)
KW - Genetic algorithm (GA)
KW - Image segmentation
KW - Magnetic resonance imaging (MRI)
UR - http://www.scopus.com/inward/record.url?scp=78650748341&partnerID=8YFLogxK
U2 - 10.4028/www.scientific.net/AMR.143-144.364
DO - 10.4028/www.scientific.net/AMR.143-144.364
M3 - 会议稿件
AN - SCOPUS:78650748341
SN - 9780878492237
T3 - Advanced Materials Research
SP - 364
EP - 369
BT - Smart Materials and Intelligent Systems
T2 - International Conference on Smart Materials and Intelligent Systems 2010, SMIS 2010
Y2 - 17 December 2010 through 20 December 2010
ER -