基于双树复小波变换的PET/CT自适应融合算法  

Self-Adaption Fusion Algorithm of PET/CT Based on Dual-Tree Complex Wavelet Transform

作　　者：魏兴瑜 周涛[1,2] 陆惠玲[2] 王文文[1] 

机构地区：[1]宁夏医科大学管理学院,银川750004 [2]宁夏医科大学理学院,银川750004

出　　处：《计算机科学与探索》2015年第3期360-367,共8页Journal of Frontiers of Computer Science and Technology

基　　金：国家自然科学基金;教育部"春晖计划"项目;宁夏自然科学基金;宁夏高等学校科研项目~~

摘　　要：PET/CT医学图像融合对于图像分析及临床诊断具有重要的应用价值,通过融合PET/CT图像,可以丰富图像的信息量,提高信息准确度。针对PET/CT融合问题,提出了一个基于双树复小波的PET/CT自适应融合算法。对已配准的PET和CT图像进行双树复小波变换(dual-tree complex wavelet transform,DTCWT),得到低频分量和高频分量;根据低频图像集中了大部分源图像能量及决定了图像轮廓的特点,采用了自适应高斯隶属度函数的融合规则;在高频图像部分,考虑了图像相邻像素之间的相关性和模糊性问题,在第一层的高频分量上采用了高斯隶属度函数和3×3领域窗口相结合的融合规则,在第二层高频分量上采用了区域方差的融合规则。最后,为了验证算法的有效性和可行性,做了3个方面的实验,分别是该算法和其他像素级融合算法的比较实验,利用信息熵、均值、标准方差和互信息的融合效果评价实验,双树复小波变换中不同融合规则的比较实验。实验结果表明,该算法信息熵提高了7.23%,互信息提高了17.98%,说明该算法是一种有效的多模态医学影像融合方法。PET/CT medical image fusion has very important application value for medical image analysis and diseases diagnosis. It is useful to improve the image content and accuracy by fusing PET/CT images. Aiming at PET/CT fusion problem, this paper proposes a self-adaption fusion algorithm of PET/CT based on dual-tree complex wavelet trans-form. Firstly, source PET and CT images after registration are decomposed low and high frequency sub-images using dual-tree complex wavelet transform （DTCWT）. Secondly, according to the characteristics of low frequency sub-images concentrating the majority energy of the source image and determining the image contour, a fusion rule based on self-adaption Gaussian membership function is adopted in low frequency sub-band coefficients. Thirdly, in high frequency sub-images, according to the relation among region pixels and fuzziness, in the first layer of high-frequency compo-nent, Gaussian membership function and 3 ＆#215; 3 field windows are used to fuse the high-frequency dual-tree complex＆amp;nbsp;wavelet coefficients. In the second layer of high-frequency component, regional variance fusion rule is used. Finally, in order to verify the validity and feasibility of the proposed algorithm, three experiments are done, comparison experi-ment of the proposed algorithm and other pixel-level fusion algorithms, the fusion effect evaluation experiment with information entropy, mean, standard deviation and mutual information, and comparison experiment with different fusion rules of dual-tree complex wavelet transform. The experimental results show that the proposed algorithm can improve the information entropy by 7.23%, and mutual information by 17.98%. That is to say the algorithm is an effi-cient fusion method of multimode medical image.

关 键 词：PET/CT 图像融合 双树复小波 高斯隶属度函数 自适应 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]