COVID-19 has become a global epidemic that seriously endangers human health. One of the key steps to combat the pandemic is to diagnose the infected patients timely. Although RT-PCR is regarded as the gold standard for COVID-19 diagnosis, it suffers from a high false-negative rate, especially for early-stage patients, and thus chest CT has been applied as an effective diagnostic tool in confirming COVID-19. To this end, we propose a Deep Dual Attention Network for accurate diagnosis of COVID-19 from CT images, which can effectively extract imaging features from complex COVID-19 lesions, showing excellent performance. This will help in the early implementation of public health surveillance, containment, and response to the epidemic.

Automatic diagnosis of Coronavirus disease 2019 (COVID-19) using chest computed tomography (CT) images is of great significance for preventing its spread. However, it is difficult to precisely identify COVID-19 due to the following problems: 1) the location and size of lesions can vary greatly in CT images; 2) its unique characteristics are often imperceptible in imaging findings. To solve these problems, a Deep Dual Attention Network ($\text {D}^{\text {2}}\text {ANet}$) is proposed for accurate diagnosis of COVID-19 by integrating dual attention modules (DAMs) with different scales of the feature extractor, where DAM can adaptively detect relevant lesion regions to extract discriminative imaging features of COVID-19. Specifically, DAM is implemented by two parallel blocks: 1) global attention block (GAB) and 2) local attention block (LAB), in which GAB is designed to roughly locate the infected regions from the entire image by modeling global contexts while LAB is developed to explic...