Hybrid Genetic and Variational Expectation-Maximization Algorithm for Gaussian-Mixture-Model-Based Brain MR Image Segmentation

The expectation-maximization (EM) algorithm has been widely applied to the estimation of Gaussian mixture model (GMM) in brain MR image segmentation. However, the EM algorithm is deterministic and intrinsically prone to overfitting the training data and being trapped in local optima. In this paper,...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on information technology in biomedicine Ročník 15; číslo 3; s. 373 - 380
Hlavní autoři: Tian, GuangJian, Xia, Yong, Zhang, Yanning, Feng, Dagan
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.05.2011
Témata:
Algorithms
Bayes Theorem
Brain - anatomy & histology
Brain modeling
Estimation
Female
Gallium
Gaussian mixture model (GMM)
genetic algorithm (GA)
Genetic algorithms
Humans
Image Processing, Computer-Assisted - methods
Image resolution
Image segmentation
Information technology
Magnetic Resonance Imaging - methods
Male
MRI
Normal Distribution
variational Bayes inference
ISSN:1089-7771, 1558-0032, 1558-0032
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The expectation-maximization (EM) algorithm has been widely applied to the estimation of Gaussian mixture model (GMM) in brain MR image segmentation. However, the EM algorithm is deterministic and intrinsically prone to overfitting the training data and being trapped in local optima. In this paper, we propose a hybrid genetic and variational EM (GA-VEM) algorithm for brain MR image segmentation. In this approach, the VEM algorithm is performed to estimate the GMM, and the GA is employed to initialize the hyperparameters of the conjugate prior distributions of GMM parameters involved in the VEM algorithm. Since GA has the potential to achieve global optimization and VEM can steadily avoid overfitting, the hybrid GA-VEM algorithm is capable of overcoming the drawbacks of traditional EM-based methods. We compared our approach to the EM-based, VEM-based, and GA-EM based segmentation algorithms, and the segmentation routines used in the statistical parametric mapping package and FMRIB Software Library in 20 low-resolution and 17 high-resolution brain MR studies. Our results show that the proposed approach can improve substantially the performance of brain MR image segmentation.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1089-7771
1558-0032
1558-0032
DOI:10.1109/TITB.2011.2106135