磁共振颅脑图像快速模糊聚类分割算法的研究

尽管模糊C-均值（简称FCM）聚类算法已广泛应用于图像分割研究，但是，由于模糊C-均值聚类算法所固有的一些缺点，特别是运算开销太大造成了该算法在实际应用中难以推广使用。根据模糊C-均值聚类算法和磁共振颅脑图象的特点，我们提出了一种分割磁共振颅脑图象的快速模糊C-均值（简称FFCM）聚类算法，该算法利用K-均值聚类结果指导模糊聚类的初始化，使模糊聚类的迭代次数明显减少。从而极大地提高模糊聚类的速度，实际应用表明，FFCM的分割速度比FCM快6.5倍以上，而分割精度与FCM相比无显著性差异。

THE STUDY OF FAST FUZZY CLUSTERING SEGMENTATION ALGORITHM OF HEAD MRI

Although fuzzy c means (FCM) clustering algorithm has been widely used in the field of image segmentation study, some inherent deficiencies of this algorithm especially the high cost of computation made the algorithm to be difficult widely used in practice. So we put forth a fast fuzzy c means (FFCM) clustering algorithm used for segmenting MR brain images according to the characteristics of the algorithm and MR brain images. The algorithm uses the result of K means clustering to guide the initiation of fuzzy clustering so that the iteration number of fuzzy clustering can be reduced obviously, thus the speed of fuzzy clustering can be accelerated greatly. The practical application showed that the segmentations produced by FFCM were approximately 6.5 times faster than those produced by FCM and there was no significant difference in the accuracy of the segmentation compared with FCM.