医学超声图像SRAD模型优化研究

Optimization of SRAD Model for Medical Ultrasound Images

研究医学超声图像提取优化问题,超声图像斑点噪声较大,影响图像精度。为抗噪声,提出一种各向异性斑点减少模型(SRAD)的优化方法,用于减少超声图像中的斑点噪声。采用扩散方向由四个扩展为八个,再根据八个方向到中心点的距离不同赋予相应的权值,进行仿真,使图像信息得到加强的同时减少所需的迭代次数。仿真结果表明,在处理速度加快,并能够较好地保证处理后得到的图像在抑制噪声和保护图像的精度质量。

This paper proposes an optimization approach of speckle reduce anisotropic diffusion（SRAD） for the problem of larger calculating amount for the normal SRAD model in the ultrasound image speckle processing.The proposed approach modifies the diffusion directions from four to eight and assigns different weightings to each according to the distance between them and the centre point.This process enhances the texture information and,at the same time,reduces the number of iteration.The simulation experimental results show that the proposed approach is faster in speed and can ensure the processed image better in the quality of suppressing speckle and preserving image details.