多重注意力引导的超声乳腺癌肿瘤图像分割  

Multiple Attention-guided Mechanisms for Ultrasound Breast Cancer Tumor Image Segmentation

作　　者：郭洪洋 程前 康晓东[1] 杨靖怡 杨舒琪 李芳 张蕊 GUO Hongyang;CHENG Qian;KANG Xiaodong;YANG Jingyi;YANG Shuqi;LI Fang;ZHANG Rui(School of Medical Image,Tianjin Medical University,Tianjin 300202,China;Chongqing University Qianjiang Hospital,Chongqing 409000,China;Beijing Chemical Occupational Disease Control Hospital,Beijing 100093,China)

机构地区：[1]天津医科大学医学影像学院,天津300202 [2]重庆大学附属黔江医院,重庆409000 [3]北京市化工职业病防治院,北京100093

出　　处：《计算机科学》2024年第S01期409-414,共6页Computer Science

基　　金：京津冀协同创新项目(17YEXTZC00020)。

摘　　要：传统基于U-Net超声乳腺图像分割任务中存在预测尺度单一和信息丢失等问题。针对存在的问题,提出一种由多重注意力引导机制的U-Net超声乳腺肿瘤图像分割。首先,在U-Net的编码结构中,引入多个SE通道注意力,对输入的乳腺肿瘤图像进行多层级的语义信息提取,引导编码器聚焦乳腺肿瘤特征,减少冗余背景信息带来的干扰;其次,通过设计特征融合处理模块,对编码器传来的特征图进行复杂语义特征的融合处理;最后,在解码器部分,加入金字塔结构捕获全局空间信息,提高模型对肿瘤图像的多尺度特征提取能力,以提高整体网络的表达能力和分割性能。在乳腺肿瘤图像数据集上对该方法进行了仿真实验,结果表明,与其他U-Net改进策略相比,该方法具有更强的准确率和鲁棒性。There are some problems such as single prediction scale and information loss in traditional U-Net ultrasound breast image segmentation tasks.To solve these problems,a multi-attention-guided U-Net ultrasound image segmentation method for breast tumors is proposed.Firstly,multiple SE attention module are introduced into the encoding structure of U-Net to extract multi-level semantic information from the input breast tumor images,which guides the encoder to focus on the features of breast tumor and reduces the interference caused by redundant background information.Secondly,by designing a feature fusion processing module,the complex semantic feature fusion processing is carried out on the feature graph from the encoder.Finally,in the decoder part,the pyramid structure is added to capture global spatial information to improve the multi-scale feature extraction ability of the model for tumor images,so as to improve the expression ability and segmentation performance of the whole network.The proposed method is simulated on breast tumor image data set,and the results show that compared with other U-Net improved strategies,the proposed method has better accuracy and robustness.

关 键 词：多重注意力引导 乳腺 U-Net 超声 图像分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]