Jun Liu

TL;DR: Wang et al. as mentioned in this paper developed a dual-sampling attention network to automatically diagnose COVID-19 from the community acquired pneumonia (CAP) in chest computed tomography (CT), and proposed a novel online attention module with a 3D convolutional network (CNN) to focus on the infection regions in lungs when making decisions of diagnoses.

TL;DR: A dual-sampling attention network to automatically diagnose COVID-19 from the community acquired pneumonia (CAP) in chest computed tomography (CT) with a novel online attention module with a 3D convolutional network (CNN) to focus on the infection regions in lungs when making decisions of diagnoses.

TL;DR: Several chest CT image features and laboratory indices are found to be highly related to COVID-19 severity, which could be valuable for the clinical diagnosis of CO VID-19.

TL;DR: Wang et al. as discussed by the authors proposed a novel three-component method, namely, a deep multiple instance learning component with instance-level attention to jointly classify the bag and also weigh the instances, a bag-level data augmentation component to generate virtual bags by reorganizing high confidential instances, and a self-supervised pretext component to aid the learning process.

TL;DR: A novel spatial and channel-wise coarse-to-fine attention network inspired by the biological vision mechanism is proposed for the segmentation of COVID-19 lung opacification from CT Images, which achieves better results compared to state-of-the-art image segmentation networks.