基于模糊聚类空间模型的非均匀MR图像分割

模糊C-均值聚类算法（FCM）已广泛地运用到MR图像的分割中。但传统的算法中未利用图像的空间信息，在分割叠加了噪声和附加了偏移场的非均匀MR图像时分割效果不理想。本文改进了传统FCM的目标函数，引入控制邻域作用紧密程度的参数，提出了一种能够更加合理地运用图像的空间信息，改进的模糊C-均值聚类算法。通过对脑部MR图像的分割实验表明，该算法能够比传统的FCM和其它改进算法对非均匀图像进行更精确的分割。

Inhomogeneous magnetic resonance image segmentation by spatial model to fuzzy clustering

Fuzzy c-means (FCM) clustering algorithm is a popular model widely used in the segmentation of magnetic resonance image (MRI). The conventional FCM doesn't involve the spatial information of MRI and then unexpected segmentation results appear when it is applied to inhomogeneous MRI with noise and bias field. Modifying the objective function of FCM and introducing a variable as the parameter to control the tight degree of neighborhood effect present a spatial model to FCM clustering algorithm. The variable can reasonably use the spatial information of MRI. The experiment results show that the proposed algorithm can provide a powerful segmentation than the conventional FCM and others.