南方医科大学学报

南方医科大学学报 ›› 2006, Vol. 26 ›› Issue (01): 36-40.

• • 上一篇    下一篇

基于Hermite微分算子的水平集MR图像分割方法

杨丰;金大年;陈武凡;罗敏;   

  1. 南方医科大学生物医学工程学院； 南方医科大学生物医学工程学院 广东 广州 510515； 广东 广州 510515；
  • 出版日期:2006-01-20 发布日期:2006-01-20
  • 基金资助:
    “93”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)

A level set method based on Hermite derivative filter for segmentation of magnetic resonance images

YANG Feng, JIN Da-nian, CHEN Wu-fan, LUO Min College of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China   

  1. 南方医科大学生物医学工程学院； 南方医科大学生物医学工程学院 广东 广州 510515； 广东 广州 510515；
  • Online:2006-01-20 Published:2006-01-20

PDF

986

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。尤其是对于南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。 更多还原

Abstract: 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.

中图分类号: