结合非局部信息的脑MR图像分割与偏移场恢复耦合模型

摘要

磁共振图像由于成像机制的影响往往导致图像中含有噪声和偏移场,使得传统方法很难得到较好的分割结果.为此,在模糊C均值模型的基础上提出一种分割与偏移场恢复耦合模型.首先构建基于非局部信息的邻域正则项,使得在降低噪声影响的同时能有效地保留图像结构信息；其次在模型求解时引入人工蜂群算法,使得模型能快速逼近凸优解.实验结果表明,该模型对噪声和偏移场均具有较好的鲁棒性,可得到较准确的分割和偏移场矫正结果.%Due to the intensity inhomogeneous and noise in brain magnetic resonance (MR) image, it is difficult for the traditional models to obtain desirable segmentation results. In this paper, we first propose a novel model based on fuzzy C means (FCM) which combines segmentation with bias correction, while the non-local method is used as a regularization term to reduce the impact of noise as well as keep the image structure. Then, we introduce the artificial bee colony algorithm to gain the convex optimal solution. Experiments of the brain MR images show that the proposed method can obtain better segmentation results as well as the bias estimation in an accurate way.