心脏超声波图像斑点噪声去除方法仿真分析

Simulation and Analysis for Speckle Noise Removal Method of Cardiac Ultrasound Image

研究心脏超声波图像质量优化问题,由于心脏的组成十分复杂,心血管各部分大小、厚度及其的不均匀,心脏瓣膜运动状况受到疾病影响也不规律,使得心脏在进行超声波图像采集过程中,往往存在大量的斑点噪声。传统的去噪算法都是将噪声转换成加信噪声,加以去除,但是转换过程会造成图像的大量有用信息损失,去噪结果缺陷明显。提出利用总体最小二乘模型的心脏超声波图像斑点噪声去除方法。根据最小二乘法相关原理,将最小二乘法相关原理应用到心脏超声波图像斑点噪声去除过程中,建立总体最小二乘模型,针对该模型的输出结果进行直交投影变换处理,实现心脏超声波图像斑点噪声的去噪处理。实验结果表明,利用改进算法进行心脏超声波斑点噪声去除处理,能够极大的提高图像的分辨率,满足心脏临床医学诊断和治疗的实际需求。

A heart ultrasonic image speckle noise removal method by using total least squares model is proposed. On the basis of the least squares principle, the related principle of minimum square method is applied to cardiac ultrasound image speckle noise removal process to establish the model of total least squares, orthogonal projection transformation processing is utilized for the output of the model, and the denoising processing for the heart ultrasound image speckle noise is realized. Experimental results show that the improved algorithm can greatly improve the resolution of the image, and meet the needs of heart clinical medical diagnosis and treatment.