Tian GuangJian, Xia Yong, Zhang Yanning, Feng Dagan
China Realtime Database Co. Ltd, State Grid Electric Power Research Institute, Nanjing, China.
IEEE Trans Inf Technol Biomed. 2011 May;15(3):373-80. doi: 10.1109/TITB.2011.2106135. Epub 2011 Jan 13.
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.
期望最大化（EM）算法已被广泛应用于脑磁共振图像分割中的高斯混合模型（GMM）估计。然而，EM算法是确定性的，本质上容易过度拟合训练数据并陷入局部最优。在本文中，我们提出了一种用于脑磁共振图像分割的混合遗传与变分EM（GA-VEM）算法。在这种方法中，执行VEM算法来估计GMM，并使用遗传算法来初始化VEM算法中涉及的GMM参数共轭先验分布的超参数。由于遗传算法有实现全局优化的潜力，而VEM可以稳定地避免过拟合，因此混合GA-VEM算法能够克服传统基于EM方法的缺点。我们将我们的方法与基于EM、基于VEM和基于GA-EM的分割算法，以及统计参数映射包和FMRIB软件库中用于20个低分辨率和17个高分辨率脑磁共振研究的分割程序进行了比较。我们的结果表明，所提出的方法可以显著提高脑磁共振图像分割的性能。
