使用梯度卷积外力场的Snake算法及其医学应用  

Gradient convolution field for Snake algorithm and its application in medical

作　　者：周頔[1] 盛歆漪[1] 孙俊[2] 

机构地区：[1]江南大学数字媒体学院数字媒体技术系,江苏无锡214122 [2]江南大学物联网工程学院,江苏无锡214122

出　　处：《计算机工程与应用》2013年第6期29-33,共5页Computer Engineering and Applications

基　　金：国家自然科学基金(No.60703106;No.60474030);国家高技术研究发展计划(863)(No.2008AA02Z21)

摘　　要：针对经典Snake算法以及GVF Snake算法容易受到图像噪声点的干扰而无法正确逼近目标物体边界的问题,提出了一种新的Snake外力场——通过边缘映射图的卷积方式扩展形成的梯度卷积外力场GCF。实验证明,基于这种GCF外力场的Snake算法在图像包含大量噪声的情况下,既能保留边缘信息又排除掉噪声带来的不良影响,正确收敛到目标物体的真实边界上,而且在深凹部位的收敛速度远远快于GVF Snake。将该算法应用于CT肺实质分割中,符合临床精确度要求。This paper proposes a new external force for Snake algorithm, called Gradient Convolution Field（GCF）. GCF is calculated by convolving the edge map generated from the image with the user-defined convolution kernel, with the aim to over- come the noise sensitivity of the traditional Snake algorithm. Experiments and comparisons with GCF are presented to show the advantages of this innovation, including superior noise robustness, reduced computational cost, and the flexibility of tailoring the force field. When this GCF Snake is applied to CT lung segmentation, the results meet the clinical precision acquirement.

关 键 词：SNAKE算法 噪声 外力场 梯度卷积 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]