基于比率距离的自适应超声图像去噪方法  

Adaptive ultrasound image denoising method based on ratio distance

作　　者：惠钊 黄慧明[1] HUI Zhao;HUANG Huiming(School of Physics and Technology,Wuhan University,Wuhan 430072,China)

机构地区：[1]武汉大学物理科学与技术学院

出　　处：《中国医学物理学杂志》2020年第2期174-179,共6页Chinese Journal of Medical Physics

基　　金：国家重点研发计划973项目（2011CB707900）

摘　　要：针对超声图像噪声的瑞利分布特性,使用一种新的自适应超声图像去噪方法,改进固定窗口包含边缘时无法做到沿边缘方向滤波的不足。采用可自由伸缩的自适应滤波窗口,首先针对瑞利分布的噪声引入比率距离,得到超声图像像素间的相似度距离,然后考虑像素的邻域图像块均值,解决相似度距离之间比较的问题,最后像素根据新的相似度距离进行八方向伸展,得到不规则形状的滤波窗口进行去噪。用仿真超声图像和临床超声图像进行实验,图像评价指标结果表明该算法优于经典算法,更适用于去除超声图像的斑点噪声,在去除噪声的同时能够较好地保留细节边缘。For the Rayleigh distribution characteristics of ultrasound image noises,a new adaptive ultrasound image denoising method is improved to overcome the shortcoming of insufficient filtering in the edge direction when the fixed window contains edges.Adaptively scalable filter window is adopted in the study.For the ultrasound image noises with Rayleigh distribution characteristics,the ratio distance is firstly introduced to obtain the similarity distance between the pixels of ultrasound images.Then the mean value of the neighborhood image blocks of the pixel is considered to solve the problem of comparison between the similarity distances.Finally,the pixel is stretched in 8 directions according to the new similarity distance,and an irregular shaped filtering window is obtained for denoising.The experiments with simulated ultrasound images and clinical ultrasound images show that the proposed algorithm is superior to the classical algorithms.The proposed algorithm is more suitable for removing the speckle noise of the ultrasound image and preserving the edge of the detail while removing the noises.

关 键 词：图像处理 超声图像 比率距离 去噪算法 瑞利分布 

分 类 号：R318[医药卫生—生物医学工程] TP391[医药卫生—基础医学]