作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2006, Vol. 32 ›› Issue (15): 194-196. doi: 10.3969/j.issn.1000-3428.2006.15.069

• 人工智能及识别技术 • 上一篇    下一篇

基于多分辨率分析和混合优化的医学图像配准

张见威1;韩国强1;张见东2   

  1. 1. 华南理工大学计算机科学与工程学院,广州510641;2. 黑龙江省大庆市第四医院神经内科,大庆163712
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2006-08-05 发布日期:2006-08-05

Medical Image Registration Based on Multi-resolution Analysis
and Hybrid Optimization

ZHANG Jianwei1; HAN Guoqiang1;ZHANG Jiandong2   

  1. 1. School of Computer Science and Engineering, South China University of Technology, Guangzhou 510641;
    2. Department of Neurology, Fourth Hospital of Daqing, Heilongjiang Province, Daqing 163712
  • Received:1900-01-01 Revised:1900-01-01 Online:2006-08-05 Published:2006-08-05

摘要: 基于图像几何特征的配准方法速度快,应用价值高,但由于几何特征提取的不准确问题使配准易陷入局部极小,而目前常用的全局优化算法又存在收敛速度慢的问题。该文提出了一种以图像边界的平均Haudorff距离作为代价函数,基于多分辨率分析和混合优化策略的图像配准方法,将其用于医学图像配准,并与基于Hausdorff距离的几种传统方法进行分析比较,实验结果显示,在模拟退火算法和Powell算法的混合优化策略下,新方法具有良好的全局优化性能和时间性能。

关键词: 平均Hausdorff距离, 多分辨率分析, 混合优化, 医学图像配准

Abstract: Image registration method based on geometric features is fast and available in application to medical image registration. At the same time, due to inaccuracy of geometric features extracted from images, local optimum is often obtained. Moreover, global optimization algorithms are slower. This paper presents a new image registration method based on mean Hausdorff distance, multi-resolution, and hybrid optimization to be applied to medical image registration, and it is compared with other methods. Results of experiments show that the new method is excellent both in global optimization and runtime.

Key words: Mean Hausdorff distance, Multi-resolution analysis, Hybrid optimization, Medical image registration

中图分类号: