基于Hermite微分算子的水平集MR图像分割方法.docVIP

基于Hermite微分算子的水平集MR图像分割方法 作者：杨丰；金大年；陈武凡；罗敏　　(南方医科大学生物医学工程学院，广东??广州??510515) 摘要：本文介绍一种基于Hermite微分算子用于MR图像分割的水平集方法。该方法采用Hermite微分算子来代替传统一阶差分算子，即在水平集曲线演化时函数微分用像素点的二阶邻域差值求得，而不是传统方法由一阶邻域决定。实验结果表明，对于相同的分割过程，运用了Hermite微分算子的水平集方法，其分割结果更加精确。尤其是对于由噪声等因素所引起的退化图像，其分割效果明显优于传统方法，而运算速度与传统方法相差无几。 关键词：MRI；图像分割；水平集；有限差分；Hermite 中图分类号：R318.5??文献标识码：A??文章编号：1673-4254(2006)01-0036-05 A level set method based on Hermite derivative filter for segmentation of magnetic resonance imagesYANG Feng；JIN Da-nian；CHEN Wu-fan；LUO MinCollege of Biomedical Engineering, Southern Medical University, Guangzhou 510515, ChinaAbstract: A level set segmentation algorithm based on Hermite derivative filter is proposed for segmentation of human magnetic resonance images (MRI). Instead of utilizing the traditional first difference, Hermite derivative filter was used to calculate the differential coefficients in the course of level set interface evolution, so that the differential coefficients were no longer decided by the first neighbor, but by the second neighbor of the examined pixel. Results of the segmentation tests proved that to the same segmentation process, the level set method utilizing Hermite derivative filter produced a more accurate result. The proposed method showed especial superiority over the conventional method for images with interferences by noise. At the same time, the new algorithm did not increase the time for the segmentation.Key words: magnetic resonance imaging; image segmentation; level set; finite difference; Hermite收稿日期：2005-06-12基金项目：“973”国家重点基础研究发展规划项目(2003CB716100)；广东省自然科学基金项目(32891)Supported by Natural Science Foundation of Guangdong Province(32891)and National 973 Development Project in High-tech Research(2003CB716100)作者简介：杨丰(1965-)，男，副教授，研究方向：医学图像处理和模式识别，E-mail:yangf@ ????MR图像分割是计算机对人体组织进行定性或定量分析所必不可少关键步骤。基于几何变形模型的水平集图像分割方法 HYPERLINK /cgi-bin/SEARCH.EXE?COMM_RECNO=2540COMM_RLTID=11 \l LAB2006000110001#LAB2006000110001 [1] HYPERLINK /cgi-bin/SEARCH.EXE?COMM_R