Computed tomography–based COVID–19 triage through a deep neural network using mask–weighted global average pooling

Background There is an urgent need to find an effective and accurate method for triaging coronavirus disease 2019 (COVID-19) patients from millions or billions of people. Therefore, this study aimed to develop a novel deep-learning approach for COVID-19 triage based on chest computed tomography (CT) images, including normal, pneumonia, and COVID-19 cases. Methods A total of 2,809 chest CT scans (1,105 COVID-19, 854 normal, and 850 non-3COVID-19 pneumonia cases) were acquired for this study and classified into the training set (n = 2,329) and test set (n = 480). A U-net-based convolutional neural network was used for lung segmentation, and a mask-weighted global average pooling (GAP) method was proposed for the deep neural network to improve the performance of COVID-19 classification between COVID-19 and normal or common pneumonia cases. Results The results for lung segmentation reached a dice value of 96.5% on 30 independent CT scans. The performance of the mask-weighted GAP method achieved the COVID-19 triage with a sensitivity of 96.5% and specificity of 87.8% using the testing dataset. The mask-weighted GAP method demonstrated 0.9% and 2% improvements in sensitivity and specificity, respectively, compared with the normal GAP. In addition, fusion images between the CT images and the highlighted area from the deep learning model using the Grad-CAM method, indicating the lesion region detected using the deep learning method, were drawn and could also be confirmed by radiologists. Conclusions This study proposed a mask-weighted GAP-based deep learning method and obtained promising results for COVID-19 triage based on chest CT images. Furthermore, it can be considered a convenient tool to assist doctors in diagnosing COVID-19.

Computed tomography-based COVID-19 triage through a deep neural network using mask-weighted global average pooling.

Background: There is an urgent need to find an effective and accurate method for triaging coronavirus disease 2019 (COVID-19) patients from millions or billions of people. Therefore, this study aimed to develop a novel deep-learning approach for COVID-19 triage based on chest computed tomography (CT) images, including normal, pneumonia, and COVID-19 cases. Methods: A total of 2,809 chest CT scans (1,105 COVID-19, 854 normal, and 850 non-3COVID-19 pneumonia cases) were acquired for this study and classified into the training set (n = 2,329) and test set (n = 480). A U-net-based convolutional neural network was used for lung segmentation, and a mask-weighted global average pooling (GAP) method was proposed for the deep neural network to improve the performance of COVID-19 classification between COVID-19 and normal or common pneumonia cases. Results: The results for lung segmentation reached a dice value of 96.5% on 30 independent CT scans. The performance of the mask-weighted GAP method achieved the COVID-19 triage with a sensitivity of 96.5% and specificity of 87.8% using the testing dataset. The mask-weighted GAP method demonstrated 0.9% and 2% improvements in sensitivity and specificity, respectively, compared with the normal GAP. In addition, fusion images between the CT images and the highlighted area from the deep learning model using the Grad-CAM method, indicating the lesion region detected using the deep learning method, were drawn and could also be confirmed by radiologists. Conclusions: This study proposed a mask-weighted GAP-based deep learning method and obtained promising results for COVID-19 triage based on chest CT images. Furthermore, it can be considered a convenient tool to assist doctors in diagnosing COVID-19.

SARS-CoV-2 nucleocapsid protein triggers hyperinflammation via protein-protein interaction-mediated intracellular Cl- accumulation in respiratory epithelium.

SARS-CoV-2, the culprit pathogen of COVID-19, elicits prominent immune responses and cytokine storms. Intracellular Cl- is a crucial regulator of host defense, whereas the role of Cl- signaling pathway in modulating pulmonary inflammation associated with SARS-CoV-2 infection remains unclear. By using human respiratory epithelial cell lines, primary cultured human airway epithelial cells, and murine models of viral structural protein stimulation and SARS-CoV-2 direct challenge, we demonstrated that SARS-CoV-2 nucleocapsid (N) protein could interact with Smad3, which downregulated cystic fibrosis transmembrane conductance regulator (CFTR) expression via microRNA-145. The intracellular Cl- concentration ([Cl-]i) was raised, resulting in phosphorylation of serum glucocorticoid regulated kinase 1 (SGK1) and robust inflammatory responses. Inhibition or knockout of SGK1 abrogated the N protein-elicited airway inflammation. Moreover, N protein promoted a sustained elevation of [Cl-]i by depleting intracellular cAMP via upregulation of phosphodiesterase 4 (PDE4). Rolipram, a selective PDE4 inhibitor, countered airway inflammation by reducing [Cl-]i. Our findings suggested that Cl- acted as the crucial pathological second messenger mediating the inflammatory responses after SARS-CoV-2 infection. Targeting the Cl- signaling pathway might be a novel therapeutic strategy for COVID-19.