联合稀疏和低秩表示的医学超声图像去噪  

Medical ultrasound image denoising based on low-rank and sparse model

作　　者：武俊珂 魏国亮 兰兰 蔡贤杰 WU Junke;WEI Guoliang;LAN Lan;CAI Xianjie(College of Science,University of Shanghai for Science and Technology,Shanghai 200093,China;Business School,University of Shanghai for Science and Technology,Shanghai 200093,China;School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学理学院,上海200093 [2]上海理工大学管理学院,上海200093 [3]上海理工大学光电信息与计算机工程学院,上海200093

出　　处：《上海理工大学学报》2023年第4期364-370,共7页Journal of University of Shanghai For Science and Technology

基　　金：国家自然科学基金资助项目(62273239);上海市科委“科技创新行动计划”国内科技合作项目(20015801100)。

摘　　要：为了保持超声图像的边缘和细节特征,同时去除图像中的噪声,提出了一种改进的低秩稀疏矩阵分解模型。首先,通过对数变换将乘性性质的斑点噪声转换为加性噪声;然后引入L1范数和改进的低秩正则项,以最小化保真项、正则项为目标函数,迭代恢复出去噪后的超声图像;最后使用指数变换从对数域中还原。将本模型应用于肿瘤超声图像,与一些经典的去噪算法进行比较,得出该模型对消化道粘膜下肿瘤超声图像去噪估计具有良好的适用性和实时性。An improved low-rank and sparse matrix decomposition model was proposed to preserve edge,detail features and remove noise in ultrasound images.Firstly,logarithmic transformation was carried out to transform the multiplicative speckle noise into additive noise.Then the L1-norm and improved low-rank regularizer term were introduced to iteratively recover the denoised ultrasound image with the minimisation of the fidelity and regularization term as the objective function.Finally,the exponential transformation was used to restore the resulting graph from the logarithmic domain.The model was compared with some classical denoising algorithms using tumour ultrasound images.The results show that the model has good applicability and real time for the estimation of ultrasonic image denoising of gastrointestinal submucosal tumours.

关 键 词：消化道粘膜下肿瘤 超声图像 斑点噪声 去噪估计 低秩稀疏模型 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]