基于双注意力机制的医学超声图像降噪模型  

Noise Reduction Model of Medical Ultrasound Images Based on Dual Attention Mechanism

作　　者：熊晨辰 蒋卫丽 贾立中 邵党国[1] 相艳[1] 马磊[1] 杨嘉林[1] Xiong Chenchen;Jiang Weili;Jia Lizhong;Shao Dangguo;Xiang Yan;Ma Lei;Yang Jialin(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming,Yunnan 650504,China;College of Computer Science,Sichuan University,Chengdu,Sichuan 610065,China;Medical Imaging Department,First Affiliated Hospital of Kunming Medical University,Kunming,Yunan 650504,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650504 [2]四川大学计算机学院,四川成都610065 [3]昆明医科大学第一附属医院医学影像科,云南昆明650504

出　　处：《激光与光电子学进展》2022年第2期403-412,共10页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61702069);云南省科技厅面上项目(KKS0201703015)。

摘　　要：医学超声图像中会不可避免地产生斑点噪声。为有效去除医学超声图像中的噪声,本研究团队提出了一种基于双注意力机制的医学超声图像降噪模型。首先,针对医学超声图像数量有限的问题,对伯克利分割数据集中的400张图像进行旋转和缩放,获得23700张自然图像,再通过斑点噪声模型对其添加斑点噪声来模拟超声图像;接着,在构建降噪模型过程中,针对传统卷积神经网络在特征提取时存在的一些不足,分别引入位置注意力机制、通道注意力机制和全卷积网络对现有模型进行改进,构建更优的超声图像降噪模型;最后,在模型训练过程中,为防止梯度消失引入了批量归一化操作。实验结果表明:从视觉观察效果和客观评价指标来看,所提模型对11张模拟超声图像和2张真实超声图像(物理体膜超声图像和肝脏超声图像)的去噪效果均优于对比模型。所提模型是一种有效的医学超声图像降噪模型,不仅有效降低了斑点噪声,还较好地保留了图像的细节信息。Speckle noise will inevitably exist in medical ultrasound images.Therefore,this study proposes a medical ultrasound image noise reduction model based on the dual attention mechanism to effectively remove noise in the medical ultrasound images.First,due to the limited number of medical ultrasound images,we rotated and zoomed 400 images in Berkeley dataset to receive 23700 images.Then,we added speckle noises using the speckle noise model to simulate the ultrasonic images.Second,during the construction process of the noise reduction model,aiming at some disadvantages of traditional convolutional neural networks in the feature extraction,we introduced position attention mechanism,channel attention mechanism,and full convolutional network to improve the existing model and build a better ultrasonic image noise reduction model.Finally,we introduced a batch normalization operation to prevent the gradient from disappearing during the model training process.The experimental results show that the noise suppression effects of 11 simulated ultrasound images and 2 real ultrasound images(the physical body membrane and liver ultrasonic images)are better than other models in terms of visual observation effect and objective evaluation index.Therefore,the proposed model is an effective noise suppression model for medical ultrasound images.It can effectively reduce speckle noise and retain the image details.

关 键 词：图像处理 医学超声图像 斑点噪声模型 位置注意力机制 通道注意力机制 斑点噪声抑制 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]