基于空间信息的FCM医学图像高效分割

FCM Algorithm with Spatial Information for Effective Medical Image Segmentation

标准FCM算法仅考虑图像的灰度信息,没有考虑图像的空间信息,所以对噪声比较敏感。考虑到医学图像数据提取中必定包含噪声,因此设计的算法必须对噪声具有鲁棒性。文中算法在KFCM_S2的基础上加入模糊空间信息,利用邻域像素对当前像素作用的先验概率,重新确定当前像素的模糊隶属度,同时进一步地调整距离矩阵。为实现快速聚类,算法的开始进行直方图初始化。实验结果表明,相对于标准的FCM和KFCM_S2算法,文中算法既能快速有效地分割图像,又能提高对噪声的鲁棒性。

Standard FCM algorithm takes into account the gray information,not the spatial information of the image,so the algorithm is sensitive to noise.In view of the fact that medical image data must contain much noise in the process of acquisition,the designed algorithm must be robust to noise.The improved algorithm is formulated by incorporating fuzzy spatial information into KFCM_S2,a prior probability is given to indicate the spatial influence of the neighboring pixels on the centre pixel,the new fuzzy membership of the current pixel is then recounted with the obtained probability,and then adjust the distance matrix.To realize fast clustering,the histogram initialization is used at the beginning of the algorithm.Experiment results show that the improved algorithm is more efficient and more robust to noise than the standard FCM and KFCM_S2.