基于小波变换和纹理测度的多模医学图像融合研究.pdfVIP

th Proceedings of the 26 Chinese Control Conference July 26-31, 2007, Zhangjiajie, Hunan, China 基于小波变换和纹理测度的多模医学图像融合* 康原原，李 彬，田联房，毛宗源 华南理工大学自动化科学与工程学院, 广州 510640 E-mail: kangbian110@ 摘 要：多模医学图像融合在医疗诊断上具有重要的应用价值。本文采用双正交小波变换的多分辨率分析方法，对 CT 和 PET 图像进行融合，提出了将局部标准差和能量相结合作为纹理测度的融合算法。实验表明，该算法能较多 地获得多源图像的解剖结构和功能代谢信息，很好地保留了源图像的边缘和纹理特征，是医学图像融合中比较可取 的方法。 关键词：双正交小波, 线性相位, 纹理特征, 局部标准差, 局部能量 Multi-modal Medical Image Fusion Based On Wavelet Transform And Texture Measure Kang Yuanyuan, Li Bin, Tian Lianfang ,Mao Zongyuan College of Automation Science and Engineering, South China University of Technology , Guangzhou 510640, P.R.China E-mail: kangbian110@ Abstract: Multi-modal medical image fusion has important value in medical diagnosis. In this paper, the multi-resolution analysis of Biorthogonal Wavelet Transform is introduced for CT and PET image fusion, then a new fusion algorithm with the combination of local standard deviation and energy as texture measurement is presented. Experiments show that both anatomical and metabolism information can be obtained effectively, and both the edge and texture features can be reserved successfully. Key Words: Biorthogonal Wavelet, Linear Phase, Texture Feature, Local Standard Deviation, Local Energy 文首先采用双正交小波基分别对解剖和功能图像进 1 引言(Introduction) 行三层小波分解，然后构造一种新的融合规则得到 医学图像融合是当前国内外研究的热点，在临 融合图像的小波系数，并通过小波逆变换完全重构 床诊断和治疗、计算机辅助诊断、远程医疗、放射 融合图像。 治疗及制定手术计划等方面有着广泛的应用前景。 2 双正交小波变换理论(Biorthogonal Wavelet