Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (14): 224-231.DOI: 10.3778/j.issn.1002-8331.2205-0558

• Graphics and Image Processing • Previous Articles     Next Articles

WCF-MobileNetV3:Lightweight COVID-19 CXR Image Recognition Network

PENG Xinrui, PAN Qing, TIAN Nili   

  1. College of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China
  • Online:2023-07-15 Published:2023-07-15

WCF-MobileNetV3:轻量型新冠肺炎CXR图像识别网络

彭心睿,潘晴,田妮莉   

  1. 广东工业大学 信息工程学院,广州 510006

Abstract: To identify COVID-19 chest X-Ray(CXR) images accurately and quickly, a lightweight model WCF-MobileNetV3 based on weighted channel filter(WCF) is proposed. The model uses MobileNetV3-small as the backbone network. Aiming at the problem that the difference between CXR image samples is small and it is difficult to extract distinguishing features, the WCF module is proposed. First, it extracts the weights of the high-dimensional and low-dimensional channel features from the input feature map. And then, it generates the high-dimensional and low-dimensional feature channel masks by weighted random sampling and fuses the weights. Next, it uses the masks to filter the fused weights. Finally, it assigns the weights to the input feature map to achieve channel-wise feature enhancement. The experimental results on the Chest-X-Ray Image dataset and the COVID-19 Chest X-Ray Image Repository dataset show that the accuracy, precision, and sensitivity of WCF-MobileNeteV3 for COVID-19 recognition are 97.93%, 98.64%, and 97.19%, respectively. Compared with other COVID-19 identification algorithms, WCF-MobileNetV3 can identify COVID-19 CXR images accurately and efficiently with better recognition performance.

Key words: COVID-19, chest X-ray image, convolutional neural network, channel filter

摘要: 为了对新型冠状病毒引发的肺炎胸部X光(chest X-Ray,CXR)图像进行准确且快速的识别,提出了一种基于加权通道筛选(weighted channel filter,WCF)的轻量级模型WCF-MobileNetV3。将轻量级的MobileNetV3-small作为主干网络,并针对CXR图像样本类间差异小、难以提取区分性特征的问题,提出了WCF模块。提取输入特征图的高维与低维通道特征权重;采取加权随机抽样的方式生成高维与低维特征通道掩膜,将高维、低维的权重融合,并利用掩膜对融合后的权重进行通道筛选;将权重赋给输入特征图,实现通道特征增强。在Chest-X-Ray Image与COVID-19 Chest X-Ray Image Repository数据集上进行了实验,结果表明:WCF-MobileNetV3对新冠肺炎CXR图像识别的准确率、精确率、灵敏度分别为97.93%、98.64%、97.19%。与其他新冠肺炎识别算法相比,WCF-MobileNetV3能够准确且高效地识别新冠肺炎CXR图像,具有更好的识别性能。

关键词: 新冠肺炎, CXR图像, 卷积神经网络, 通道筛选