基于多尺度注意力小波网络的可适应病变规模超声乳腺图像分割  

Adaptive lesion scale ultrasound breast image segmentation based on multi-scale attention wavelet network

作　　者：孙卓群 赵加祥[1] SUN Zhuoqun;ZHAO Jiaxiang(School of Electronic Information and Optical Engineering,Nankai University,Tianjin 300350,China)

机构地区：[1]南开大学电子信息与光学工程学院,天津300350

出　　处：《微电子学与计算机》2023年第12期45-52,共8页Microelectronics & Computer

摘　　要：针对超声乳腺图像中对不同规模病变的分割鲁棒性不足的问题,提出了一种多尺度注意力小波网络(MAW-Net).通过设计两个轻量的网络模块,多尺度拼接模块和跳过连接升维模块,达到在不同尺度上集成丰富的特征和全局上下文信息,减少编码器和解码器之间的语义差距以适应不同规模病变分割的目的.并引入双树复小波变换,很好地削弱了噪声影响.在两个公共的乳腺超声数据集UDIAT和BUSI数据集上进行测试,其Dice系数分别达到91.32%和84.23%.并与其他6种先进的图像分割方法进行比较,具备强分割鲁棒性、噪声影响小等优势.A Multi-scale Attention Wavelet Network(MAW-Net)is proposed to solve the problem of insufficient robustness for segmentation of lesions of different scales in ultrasound breast images.Through the design of two lightweight network modules,multi-scale splicing module and skip connection up-dimension module,the goal is to integrate rich features and global context information on different scales,reduce the semantic gap between the encoder and decoder,and adapt to the purpose of disease segmentation on different scales.The dual-tree complex wavelet transform is introduced to weaken the influence of noise.The Dice coefficients are 91.32%and 84.23%respectively when tested on two common breast ultrasound data sets UDIAT and BUSI.Compared with other six advanced image segmentation methods,it has the advantages of strong segmentation robustness and small noise impact.

关 键 词：超声乳腺图像 图像分割 多尺度注意力小波网络 双树复小波变换 U-Net 注意力机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]