基于先验信息水平集方法的肝脏CT序列图像自动分割

来源期刊:中南大学学报(自然科学版)2015年第4期

论文作者:徐效文 赵于前 闫桂霞 邹润民

文章页码:1310 - 1318

关键词:水平集;肝脏分割;先验信息;CT序列

Key words:level set; liver segmentation; prior knowledge; CT series

摘    要:应用二次区域生长法获取肝脏的初步分割结果,将其作为先验知识,构造新的边缘指示函数和水平集能量函数,有效地解决了因肝脏形状多变以及弱边界问题带来的分割难题。在序列的分割过程中,将上一层分割结果进行距离变换,并提取大于既定阈值的部分生成下一层区域生长的种子点,避免了分割过程中的误差积累,并使序列的分割具有延续性和自动性。算法最后应用自适应边缘行进算法修补边缘,使得分割结果更加完整。实验结果证明了该方法的有效性和可行性。

Abstract: The livers were preliminarily segmented by two-step region growth, and then the segmented results were taken as prior knowledge to construct a new edge indicator and level set energy function. The segment effectively solves the problems of variable liver shapes and weak boundaries. During the liver CT series segmentation, the distance transform that its value is greater than a fixed threshold is extracted from the current slice segmentation to generate the region growth seed points for the next slice segmentation, which avoids the error accumulation and ensures the continuity and automation of liver CT series segmenting process. Finally, the adaptive border marching method was used to correct the segmentation defects. The experimental results demonstrate the effectiveness and feasibility of the proposed method.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号