• 研究论文 • 上一篇    下一篇



  1. (1. 西安电子科技大学 雷达信号处理重点实验室, 陕西 西安 710071;
    2. 西安电子科技大学 机电工程学院, 陕西 西安 710071

  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2004-02-20 发布日期:2004-02-20

Application of wavelet analysis in medical image fusion

TAO Guan-qun1;LI Da-peng2;LU Guang-hua1


  1. (1. Key Lab. of Radar Signal Processing, Xidian Univ., Xi'an 710071, China;
    2. School of Mechano-electronic Engineering, Xidian Univ., Xi'an 710071, China)
  • Received:1900-01-01 Revised:1900-01-01 Online:2004-02-20 Published:2004-02-20

摘要: 在临床的实际应用中,单模态的医学图像(CT,MRI)的3D重建不能提供医生所需要的足够信息. 由于成像机理不同和人体组织结构的高度复杂性,不同模态的医学图像提供了不互相覆盖的结构互补信息. 为此在医学图像配准的基础上提出基于小波变换的最大值融合规则,局部平均梯度融合规则,区域能量融合规则等算法. 通过对CT图像与MRI图像基于小波变换的不同融合规则及融合算子进行融合的实验结果比较表明,以区域能量融合规则作为准则的融合效果更好. 能够把这两种图像优点结合在一张图像上,这样能为病变提供准确的定位参照,能清晰地显示病变自身,对诊断和治疗更加有利.

关键词: 医学图像, 互补信息, 小波变换, 区域能量融合规则

Abstract: In practical clinic applications, the 3D reconstrution of the single-modality medical image(CT, MRI) can not provide enough information for clinical doctors. Because of a different imaging mechanism and highly complexity of body tissues and structures, different modality medical images provide non-overlay complementary information. Fusion rules of maximum, local gradient and area energy based on wavelet transform are advanced. Compared fusion results of CT and MRI images are gien, which show the proposed method based on the area energy fusion rule can achieve better fusion performance than other usual fusion rules. The fusion image can combine the merits of two original images, providing not only the exact orientation reference of pathological changes but also the clear pathological tissue.

Key words: medical image, complementary information, wavelet transform, area energy fusion rule


  • TP391.41