独立分量分析在PET图像去噪处理中的应用  

Application of Independent Component Analysis on PET Image De-noising

作　　者：徐秋平[1] 韦琦[1] 

机构地区：[1]哈尔滨理工大学电气与电子工程学院,黑龙江哈尔滨150040

出　　处：《哈尔滨理工大学学报》2009年第6期61-65,共5页Journal of Harbin University of Science and Technology

基　　金：黑龙江省自然科学基金(E200932);黑龙江省教育厅科学技术研究项目(11511075);中国博士后基金(2005037656);哈尔滨理工大学青年拔尖创新人才计划

摘　　要：独立分量分析(independent component analysis,ICA)是基于信号高阶统计量的盲源分离方法.提出将这种算法与中值滤波和小波滤波相结合应用于正电子发射计算机断层扫描(Positron Emission Tomography,PET)图像的去噪处理中,并与中值滤波和小波滤波进行对比分析.仿真实验证明了本文算法相较于中值滤波和小波滤波在PET图像处理中取得了更好的效果.Independent Component Analysis （ICA） is a blind source separation algorithm based on high statistics of singnal. Combined with median filter and wavelet filter, the algorithm was applied to PET image de-noising and compared with median filter and wavelet filter in this paper. Simulation experiments proved that the algorithm in the paper is better than median filter and wavelet filter in the process of PET image de-noising.

关 键 词：独立分量分析 盲源分离 正电子发射计算机断层扫描 

分 类 号：R331.37[医药卫生—人体生理学]