基于自适应高斯滤波的超声斑点降噪  

Speckle Reduction Based on Adaptive Gauss Filtering

作　　者：邵党国[1] 邓阳阳[1] 相艳[1] 易三莉[1] 余正涛[1] 贺建峰[1] 刘翠寅 宗绍云[3] 

机构地区：[1]昆明理工大学信息工程与自动化学院和云南省计算机技术应用重点实验室,昆明650500 [2]昆明理工大学计算中心,昆明650500 [3]云南省第一人民医院,昆明650032

出　　处：《数据采集与处理》2017年第4期746-753,共8页Journal of Data Acquisition and Processing

基　　金：国家博士后基金(2016M592894XB)资助项目

摘　　要：医学超声图像存在的斑点噪声降低了图像的质量,给临床诊断和图像的后续处理带来了困难。为了有效地去除噪声,本文提出了一种自适应高斯滤波的超声斑点降噪算法。该算法利用局部特征匹配计算出图像的处理窗口区域与参考区域的相似度,再根据相似度将整幅图像区分为斑点噪声区域和组织区域。同时利用相似度调整高斯滤波器的宽度值,使高斯滤波器对图像的不同区域进行不同程度的过滤。物理体模实验和人体超声肝脏实验结果表明,该算法可以有效地去除超声图像中的斑点噪声并保留组织结构,并且可使迭代次数大大减少,是一种有效的医学超声图像降噪方法。Speckle noises in medical ultrasound image would decrease the quality of image and bring diffi- culties to the analysis and diagnosis of the subsequent image. To reduce speckle, here we propose a speckle reduction algorithm based on the adaptive Gauss filter. The algorithm distinguishes the image with speckle regions and characteristic regions by a similarity deprived from local characteristic matching between the processing window and a reference speckle area. According to the similarity, this algorithm adjustes adaptively the width of the Gauss filter. Ultrasound phantom testing and vivo imaging show that the proposed method is effective. It can reduce the numbers of iteration significantly, as well as the speckle and preserve edge.

关 键 词：超声图像 局部特征匹配 自适应滤波 相似度 斑点噪声抑制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]