English

应用科学学报 ›› 2026, Vol. 44 ›› Issue (3): 437-451.doi: 10.3969/j.issn.0255-8297.2026.03.007

• 智能信息处理 • 上一篇    

融合双重注意力机制的轻量级U型肺部病灶图像分割网络

何晓晨1, 丁德锐1, 李明2, 王飞1, 王博3   

  1. 1. 上海理工大学光电信息与计算机工程学院, 上海 200093;
    2. 江苏海洋大学计算机工程学院, 江苏 连云港 222005;
    3. 磅客策(上海) 智能医疗科技有限公司, 上海 201619
  • 收稿日期:2023-09-15 发布日期:2026-06-23
  • 通信作者: 丁德锐，教授，博士生导师，研究方向为深度学习图像处理、智能算法。E-mail:deruiding2010@usst.edu.cn E-mail:deruiding2010@usst.edu.cn
  • 基金资助:
    国家自然科学基金(No.61973219);江苏省高等学校基础科学(自然科学)研究面上项目(No.23KJB520006)

Dual Attention-Incorporated Lightweight U-shaped Network for Lung Lesion Image Segmentation

HE Xiaochen1, DING Derui1, LI Ming2, WANG Fei1, WANG Bo3   

  1. 1. School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China;
    2. School of Computer Engineering, Jiangsu Ocean University, Lianyungang 222005, Jiangsu, China;
    3. Puncture (Shanghai) Intelligent Medical Technology Co., Ltd., Shanghai 201619, China
  • Received:2023-09-15 Published:2026-06-23

PDF

6

摘要： 为了解决肺部病灶图像对比度低、纹理细节模糊以及边缘特征提取不充分等难题，本文提出一种融合双重注意力机制的轻量级U型网络。首先，设计一种注意双分支组合模块。在编码阶段，两分支分别关注全局与局部信息，获取病灶全局定位信息与边缘特征；其次，同时引入并行的纹理增强模块，使用量化计数算子得到统计特征直方图，增强浅层网络提取的纹理特征，解决了对比度低的挑战；最后，构建反注意双干扰细分模块，在解码阶段使网络关注并处理误分割信息，实现重构图像内假阳性与假阴性特征的同时消除。在肺部病灶数据集COVID-19 CT scan和MS COVID-19上验证了网络的有效性。与现有网络相比，本文所提网络在5个评价指标上均取得了最优结果，Dice指标相比次优的UNeXt模型提高了1.42%，且同时实现了参数轻量化的效果。

关键词: 肺部病灶图像, 轻量级U型网络, 双重注意力机制, 纹理增强

Abstract: To address the problems of low contrast, fuzzy texture details, and inadequate edge feature extraction in lung lesion images, this paper proposed a novel lightweight U-shaped network incorporating dual attention, termed DALU-Net. First, an attentionbased two-branch fusion module was designed. During encoding, the two branches focused on global and local information, respectively, to capture global localization information and lesion edge features. Then, a parallel texture enhancement module was introduced,and a statistical feature histogram was obtained using a quantization counting operator to enhance the texture features extracted by the shallow network and address the challenge of low contrast. Finally, a reverse-attention dual-interference refinement module was developed to enable the network to focus on and process mis-segmentation information during the decoding stage, thus simultaneously eliminating false-positive and false-negative features in the reconstructed image. The effectiveness of the network was verified on two lung lesion datasets: COVID-19 CT scan and MS COVID-19. Compared with existing networks,the proposed network achieves the best results on all five evaluation metrics, with a Dice score that is 1.42% higher than that of the second-best model, UNeXt, while also using fewer parameters.

Key words: lung lesion image, lightweight U-shaped network, dual attention mechanism, texture enhancement

中图分类号: