基于NLM的双水平集医学图像分割算法  

Medical Images Segmentation with Double Level Set Algorithm Based on Non-local Means Method

作　　者：徐丽 朱家明[1] 唐文杰[1] XU Li;ZHU Jiaming;TANG Wenjie(School of Information Engineering,Yangzhou University,Yangzhou 225127,China)

机构地区：[1]扬州大学信息工程学院,江苏扬州225127

出　　处：《无线电通信技术》2018年第4期367-371,共5页Radio Communications Technology

基　　金：国家自然科学基金项目(61273352;61573307;61473249;61473250)

摘　　要：针对医学图像的复杂多样性,易受到各种外在和内在因素的干扰,提出了基于非局部均值算法的双水平集医学图像分割模型。对于图像含有高噪声的问题,引入非局部均值方法对图像进行去噪处理,并在传统DCV中引入偏移场能量项,利用水平集算法对去噪后的图像再进行分割,得出最终的分割效果图。实验结果显示,该模型有较强的抗噪性,可强化图像边缘信息,得到较好的分割效果。In view of the complex diversity of medical images,which are easy to be affected by external and internal factors,this paper proposes a medical images segmentation model based on non-local means method and double level set algorithm.To deal with the problem that the image contains high noise,the non-local means method is introduced to denoise the image,and the energy content of the biased field is introduced into the traditional DCV. The level set algorithm is used to process the image to obtain the final segmentation effect.The experimental results show that the model can reduce the noise of the image,strengthen the weak edges of the original image,and get better image segmentation effect.

关 键 词：非局部均值去噪 偏移场拟合 双水平集 医学图像分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]