COVID-19 is a respiratory disease caused by severe acute respiratory syndrome coronavirus (SARS-CoV-2). Due to the rapid spread of COVID-19 around the world, the number of COVID-19 cases continues to increase, and lots of countries are facing tremendous pressure on both public and medical resources. Although RT-PCR is the most widely used detection technology with COVID-19 detection, it still has some limitations, such as high cost, being time-consuming, and having low sensitivity. According to the characteristics of chest X-ray (CXR) images, we design the Parallel Channel Attention Feature Fusion Module (PCAF), as well as a new structure of convolutional neural network MCFF-Net proposed based on PCAF. In order to improve the recognition efficiency, the network adopts 3 classifiers: 1-FC, GAP-FC, and Conv1-GAP. The experimental results show that the overall accuracy of MCFF-Net66-Conv1-GAP model is 94.66% for 4-class classification. Simultaneously, the classification accuracy, precision, sensitivity, specificity, and F1-score of COVID-19 are 100%. MCFF-Net may not only assist clinicians in making appropriate decisions for COVID-19 diagnosis but also mitigate the lack of testing kits.

中文翻译：

---

通过 MCFF-Net 在胸部 X 射线图像中检测 COVID-19

COVID-19 是一种由严重急性呼吸系统综合症冠状病毒 (SARS-CoV-2) 引起的呼吸道疾病。由于 COVID-19 在世界范围内的迅速传播，COVID-19 病例数不断增加，许多国家都面临着公共和医疗资源的巨大压力。尽管 RT-PCR 是 COVID-19 检测中应用最广泛的检测技术，但它仍然存在一些局限性，例如成本高、耗时、灵敏度低等。根据胸部X光（CXR）图像的特点，我们设计了并行通道注意力特征融合模块（PCAF），以及基于PCAF提出的卷积神经网络MCFF-Net的新结构。为了提高识别效率，网络采用了3个分类器：1-FC、GAP-FC和Conv1-GAP。实验结果表明，MCFF-Net66-Conv1-GAP模型对于4类分类的整体准确率为94.66%。同时，COVID-19 的分类准确率、精确度、敏感性、特异性和 F1-score 均为 100%。MCFF-Net 不仅可以帮助临床医生为 COVID-19 诊断做出适当的决定，还可以减少检测试剂盒的缺乏。