基于形态学多尺度修正的模糊C均值脑肿瘤分割方法

针对脑部核磁共振成像(MRI)图像因噪声、灰度不均匀、组织结构复杂及边界模糊不连续等造成肿瘤难以准确分割的问题，提出一种基于形态学多尺度修正的模糊C均值(FCM)聚类分割方法。首先根据邻域统计信息引入控制参数用于区分邻域中的噪声点、边缘点和区域内部点,结合空间位置信息建立像素与结构元素大小之间的函数关系；然后利用不同大小的结构元素对图像中不同类型像素进行形态学闭运算，消除对应于局部极小值的噪声干扰和非规则细节，而目标部分的区域轮廓位置基本保持不变；最后在修正基础上进行FCM聚类分割，避免FCM陷入局部极优和误分类，同时保持区域轮廓准确定位。与标准FCM、核FCM(KFCM)、遗传FCM(GFCM)、模糊局部信息C均值(FLICM)等改进方法以及专家手工勾画结果进行了对比，实验结果表明，该方法的过分割率和欠分割率较低，且与标准分割的相似度指数和JS值均较高，具有较好的分割效果。

Brain tumor segmentation based on morphological multi-scale modification and fuzzy C-means clustering

Tumor in brain Magnetic Resonance Imaging (MRI) images is often difficult to be segmented accurately due to noise, gray inhomogeneity, complex structrue, fuzzy and discontinuous boundaries. For the purpose of getting precise segmentation with less position bias, a new method based on Fuzzy C-Means (FCM) clustering and morphological multi-scale modification was proposed. Firstly, a control parameter was introduced to distinguish noise points, edge points and regional interior points in neighborhood, and the function relationship between pixels and the sizes of structure elements was established by combining with spatial information. Then, different pixels were modified with different-sized structure elements using morphological closing operation. Thus most local minimums caused by irregular details and noises were removed, while region contours positions corresponding to the target area were largely unchanged. Finally, FCM clustering algorithm was employed to implement segmentation on the basis of multi-scale modified image, which avoids the local optimization, misclassification and region contours position bias, while remaining accurate positioning of contour area. Compared with the standard FCM, Kernel FCM (KFCM), Genetic FCM (GFCM), Fuzzy Local Information C-Means (FLICM) and expert hand sketch, the experimental results show that the suggested method can achieve more accurate segmentation result, owing to its lower over-segmentation and under-segmentation, as well as higher similarity index compared with the standard segmentation.