基于核模糊聚类的变分水平集医学图像分割方法

针对现有无须重新初始化的变分水平集分割模型, 存在对边缘模糊、对比度差等图像不是很敏感、分割效果不理想的问题, 提出了一种基于核模糊聚类的变分水平集医学图像分割方法。将原始图像进行核模糊C-均值聚类, 把得到的聚类结果带入初始化水平集函数得到初始轮廓, 最后利用李模型的分割方法实现最终的图像分割。实验结果表明, 该方法具有良好的分割质量, 适应性强, 同时可减少迭代次数。

Variational level set method of medical image segmentation based on kernel fuzzy clustering

The existing variational level set without re-initialization model is less sensitive to the margin-blurred and low-contrast image, and its segmentation results are not satisfying. To solve this proplem, this paper proposed a variational level set method of medical image segmentation based on kernel fuzzy clustering, First of all, it transformed the original image by kernel fuzzy C-means clustering, and then introduced the clustering results into the initial level set function to achieve the initial contour. Finally it used the Li model segmentation method to achieve the ultimate image segmentation. The experimental results show that the proposed method has good segmentation quality, strong adaptability, and less iteration times at the same time.