Accurate and rapid diagnosis of COVID-19 using chest X-ray (CXR) plays an important role in large-scale screening and epidemic prevention. Unfortunately, identifying COVID-19 from the CXR images is challenging as its radiographic features have a variety of complex appearances, such as widespread ground-glass opacities and diffuse reticular-nodular opacities. To solve this problem, we propose an adaptive attention network (AANet), which can adaptively extract the characteristic radiographic findings of COVID-19 from the infected regions with various scales and appearances. It contains two main components: an adaptive deformable ResNet and an attention-based encoder. First, the adaptive deformable ResNet, which adaptively adjusts the receptive fields to learn feature representations according to the shape and scale of infected regions, is designed to handle the diversity of COVID-19 radiographic features. Then, the attention-based encoder is developed to model nonlocal interactions by self-attention mechanism, which learns rich context information to detect the lesion regions with complex shapes. Extensive experiments on several public datasets show that the proposed AANet outperforms state-of-the-art methods.

中文翻译：

---

AANet：用于从胸部 X 射线图像检测 COVID-19 的自适应注意网络

使用胸部 X 光 (CXR) 准确快速地诊断 COVID-19 在大规模筛查和防疫中发挥着重要作用。不幸的是，从 CXR 图像中识别 COVID-19 具有挑战性，因为其放射学特征具有多种复杂的外观，例如广泛的磨玻璃影和弥漫性网状结节影。为了解决这个问题，我们提出了一种自适应注意力网络（AANet），它可以从各种规模和外观的感染区域自适应地提取 COVID-19 的特征影像学发现。它包含两个主要组件：自适应可变形 ResNet 和基于注意力的编码器。首先是自适应变形 R​​esNet，它根据感染区域的形状和规模自适应地调整感受野以学习特征表示，旨在处理 COVID-19 放射学特征的多样性。然后，基于注意力的编码器被开发为通过自注意力机制对非局部交互进行建模，该机制学习丰富的上下文信息以检测具有复杂形状的病变区域。对几个公共数据集的大量实验表明，所提出的 AANet 优于最先进的方法。