局部熵驱动下的脑MR图像分割与偏移场恢复耦合模型

核磁共振图像受成像机制的影响往往导致图像中含有噪声以及偏移场,使得传统的图像分割方法很难得到较好的分割结果.为此,提出一种基于局部熵的分割与偏移场恢复耦合模型,首先在小邻域内构建基于模糊C均值(FCM)聚类模型的局部统计项并将偏移场信息耦合到模型中,以恢复图像偏移场;其次采用非局部信息来构建邻域正则项,使得模型在降低噪声影响的同时能有效地保留图像结构信息;最后在对局部能量项进行全局积分时引入局部熵信息,使得模型具有各向异性,从而对噪声和偏移场影响更具鲁棒性.实验结果表明,本文方法可以得到较准确的分割和偏移场矫正结果.

Brain MR image segmentation and bias correction model based on local entropy

Due to the intensity inhomogeneous and noise in brain MR image, it is difficult for the traditional models to obtain desirable segmentation results. In this paper, we first propose a local energy function based on FCM model which combines segmentation with bias correction. As a result, the proposed model can handle intensity inhomogeneity. Then, the non-local method is used as a regularization term to reduce the impact of noise and keep the image structure at the same time. Finally, the local entropy information is incorporated into the model which make it more robust to noise and intensity inhomogeneity. Experiments of the brain magnetic resonance images show that the proposed method can obtain better segmentation results and bias corrected results.