融合局部和全局信息的两相脑图分割模型

Brain Image Segmentation Combining Local and Global Information Based on Two-phase Active Contour Model

为了解决脑核磁共振图像中的灰度不均匀现象,提出了一个基于两相的脑图像分割模型.该模型在图像局部熵基础上融合局部高斯信息和全局信息的两相水平集来拟合图像信息,同时采用一种新的简单有效的初始化方法,进行脑灰质、脑白质、脑髓液分割.实验结果表明,该模型能有效地对脑灰质、脑白质、脑髓液进行分割,同时提供准确光滑的目标边界,解决了CV模型等对灰度不均匀图像分割失败的问题.

To solve the intensity inhomogeneity in the segmentation of magnetic resonance （MR） images,this paper presents a new two-phase level set model for segmentation of brain MR images. The proposed model is based on local image entropy and utilizes local gaussian image information and global image information. A kind of simple and useful method is used for initialization to segment white matter （WM） ,gray matter （GM） and cerebrospinal fluid （CSF）. The results show that the proposed method can effectively segment WM,GM,and CSF and simultaneously provide a smooth contour. The intensity inhomogeneity problems can be solved that can not be overcome by the CV model.