基于小波变换医学图像融合算法的对比分析  

Comparison and Analysis of Medical Image Fusion Algorithms Based on Wavelet Transform

作　　者：胡俊峰[1,2] 唐鹤云[1] 钱建生[2] 

机构地区：[1]徐州医学院医学影像学院,徐州221006 [2]中国矿业大学信息与电气工程学院,徐州221008

出　　处：《中国生物医学工程学报》2011年第2期196-205,共10页Chinese Journal of Biomedical Engineering

基　　金：江苏省高校科技成果转化项目(JHZD09-22);徐州市科技计划项目(XM09B070)

摘　　要：小波变换融合方法具有重要的应用价值,而融合规则的选取直接影响着融合效果。为了获得医学临床上实用的小波融合算法,选择标准CT/MRI图像,通过调整和组合各种小波变换低频及高频融合规则进行仿真实验,深入对比分析各种融合规则对医学图像融合性能的影响。在此基础上,提出低频能量取大与高频系数绝对值取大相结合的融合改进算法,比目前基于传统小波融合规则的融合质量及各项客观评价指标都有明显提高,在各种算法比较中最优。采用多聚焦图像和临床实际的CT/MRI图像进行对比验证,表明了方法的有效性。理论分析和实验结果证明:选取合适的融合规则对融合结果影响很大,本研究提出的算法简单有效。The image fusion method of wavelet transform has important application value.Different choices of fusion rules directly affect the fusion results.In order to obtain practical wavelet transform fusion algorithm in clinic,simulation study were conducted by choosing standard CT and MRI images,adjusting and combining various fusion rules of the wavelet transform low frequency and high frequency.Comparing the traditional wavelet transform algorithm adopting the＂average＂rule to low-frequency and the＂coefficient absolute value＂to high-frequency,an efficient fusion method was proposed which the＂region energy＂fusion rule was adapted to the low-frequency coefficients and the＂region variance＂fusion rule to the high-frequency coefficients.Then the further research has been made and the better algorithm which the＂region energy＂and the＂coefficient absolute value＂ fusion rules were used as the low-frequency and the high-frequency coefficients individually has been introduced.And then the compared experiments were done to test and verify the results using multi-focus images and clinical CT /MRI images.Theoretical analysis and experimental results demonstrated that appropriate fusion rules influence on the image fusion results and the proposed algorithm of image fusion is effective.

关 键 词：图像融合 小波变换 融合规则 效果评价 

分 类 号：R318.04[医药卫生—生物医学工程]