一种基于局部信息的多相脑图分割模型

Multiphase Brain Image Segmentation Model Based on Local Information

针对脑核磁共振成像中灰度不均匀的现象,提出一种基于局部信息的多相脑图分割模型。采用阈值法进行轮廓初始化,利用多相水平集拟合图像的局部信息,从而得到脑灰质、脑白质和脑脊液图像。实验结果表明,该模型能有效地对多相脑图进行分割,给出准确光滑的目标边界,并且不需要重新初始化。

To solve the intensity inhomogeneity in the segmentation of Magnetic Resonance Imaging（MRI）,this paper presents a new multiphase level set model for brain image segmentation.The proposed model uses local image intensities and thresholding method for initialization to segment White Matter（WM）,Gray Matter（GM） and Cerebrospinal Fluid（CSF）.Experimental results show that the proposed method can effectively segment multiphase brain image and provide a smooth contou,and it does not need reinitialization.