COVID-19 stay threatening the health infrastructure worldwide. Computed tomography (CT) was demonstrated as an informative tool for the recognition, quantification, and diagnosis of this kind of disease. It is urgent to design efficient deep learning (DL) approach to automatically localize and discriminate COVID-19 from other comparable pneumonia on lung CT scans. Thus, this study introduces a novel two-stage DL framework for discriminating COVID-19 from community-acquired pneumonia (CAP) depending on the detected infection region within CT slices. Firstly, a novel U-shaped network is presented to segment the lung area where the infection appears. Then, the concept of transfer learning is applied to the feature extraction network to empower the network capabilities in learning the disease patterns. After that, multi-scale information is captured and pooled via an attention mechanism for powerful classification performance. Thirdly, we propose an infection prediction module that use the infection location to guide the classification decision and hence provides interpretable classification decision. Finally, the proposed model was evaluated on public datasets and achieved great segmentation and classification performance outperforming the cutting-edge studies.

COVID-19 继续威胁着全球的卫生基础设施。计算机断层扫描 (CT) 被证明是识别、量化和诊断此类疾病的信息工具。迫切需要设计有效的深度学习 (DL) 方法，以在肺部 CT 扫描中自动定位和区分 COVID-19 与其他类似肺炎。因此，本研究引入了一种新的两阶段 DL 框架，用于根据 CT 切片中检测到的感染区域将 COVID-19 与社区获得性肺炎 (CAP) 区分开来。首先，提出了一种新颖的 U 形网络来分割出现感染的肺部区域。然后，将迁移学习的概念应用于特征提取网络，以增强网络学习疾病模式的能力。在那之后，通过注意力机制捕获和汇集多尺度信息，以获得强大的分类性能。第三，我们提出了一个感染预测模块，该模块使用感染位置来指导分类决策，从而提供可解释的分类决策。最后，所提出的模型在公共数据集上进行了评估，取得了优于前沿研究的出色分割和分类性能。