自适应SUSAN扩散的超声图像去噪算法  

Adaptive speckle reduction algorithm for ultrasound image based on SUSAN diffusion

作　　者：徐宇贵 沈民奋[1] 张琼[1] 方若宇[2] 

机构地区：[1]汕头大学电子工程系,汕头515063 [2]汕头大学计算机科学与技术系,汕头515063

出　　处：《电子测量与仪器学报》2012年第4期331-337,共7页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金(编号:61072037)资助项目;广东省自然科学基金(编号:10151503101000011)资助项目

摘　　要：为了降低超声图像斑点噪声的影响,提出一种自适应SUSAN(ASUSAN)扩散的超声图像去噪算法。通过引入SUSAN算法检测出图像的边缘,然后采用K均值法对模板区域特征值进行分类,自适应获得图像的全斑点噪声区域和相关参数,最后将SUSAN算法与非线性扩散方法相结合,提出一种新的扩散方程对图像进行非线性去噪。实验证明,相比于其他的各向异性扩散算法,本算法能得到更高的PSNR值和FOM值以及更小的MSE值,且在细节保留方面也能取得更好的效果。In order to reduce the effect of speckle noise on ultrasound images, a speckle reduction algorithm for medical ultrasound image based on adaptive SUSAN （ASUSAN） diffusion is proposed. First, the image boundary was detected by using SUSAN algorithm. Then, FFS region and relevant parameters were obtained by using K-means algo- rithm to classify the eigenvalue of template area. Finally, combining SUSAN with nonlinear diffusion method, the dif- fusion method was put forward. The experiments demonstrate that the proposed method outperform other anisotropic diffusion methods in PSNR, MSE and FOM. Moreover, the ultrasound image details can be preserved better after image denoising.

关 键 词：自适应SUSAN扩散 超声图像 去噪 

分 类 号：TN911.73[电子电信—通信与信息系统]