Sfikas G, Nikou C, Galatsanos N, Heinrich C
University of Ioannina, Department of Computer Science, 45110 Ioannina, Greece.
Med Image Comput Comput Assist Interv. 2008;11(Pt 1):43-50. doi: 10.1007/978-3-540-85988-8_6.
In this paper, a spatially constrained mixture model for the segmentation of MR brain images is presented. The novelty of this work is an edge-preserving smoothness prior which is imposed on the probabilities of the voxel labels. This prior incorporates a line process, which is modeled as a Bernoulli random variable, in order to preserve edges between tissues. The main difference with other, state of the art methods imposing priors, is that the constraint is imposed on the probabilities of the voxel labels and not onto the labels themselves. Inference of the proposed Bayesian model is obtained using variational methodology and the model parameters are computed in closed form. Numerical experiments are presented where the proposed model is favorably compared to state of the art brain segmentation methods as well as to a spatially varying Gaussian mixture model.
本文提出了一种用于磁共振脑图像分割的空间约束混合模型。这项工作的新颖之处在于对体素标签概率施加了保边缘平滑先验。该先验纳入了一个线过程，将其建模为伯努利随机变量，以保留组织之间的边缘。与其他施加先验的现有技术方法的主要区别在于，约束是施加在体素标签的概率上，而不是标签本身。使用变分方法对所提出的贝叶斯模型进行推理，并以封闭形式计算模型参数。给出了数值实验，将所提出的模型与现有技术的脑分割方法以及空间变化的高斯混合模型进行了有利的比较。
