Abstract: 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 overcome 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.

Key words: Snake algorithm, noise, external force field, gradient convolution

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。

关键词: Snake算法, 噪声, 外力场, 梯度卷积