CodnNet: A lightweight CNN architecture for detection of COVID-19 infection.

The application of Convolutional Neural Network (CNN) on the detection of COVID-19 infection has yielded favorable results. However, with excessive model parameters, the CNN detection of COVID-19 is low in recall, highly complex in computation. In this paper, a novel lightweight CNN model, CodnNet is proposed for quick detection of COVID-19 infection. CodnNet builds a more effective dense connections based on DenseNet network to make features highly reusable and enhances interactivity of local and global features. It also uses depthwise separable convolution with large convolution kernels instead of traditional convolution to improve the range of receptive field and enhances classification performance while reducing model complexity. The 5-Fold cross validation results on Kaggle's COVID-19 Dataset showed that CodnNet has an average precision of 97.9%, recall of 97.4%, F1score of 97.7%, accuracy of 98.5%, mAP of 99.3%, and mAUC of 99.7%. Compared to the typical CNNs, CodnNet with fewer parameters and lower computational complexity has achieved better classification accuracy and generalization performance. Therefore, the CodnNet model provides a good reference for quick detection of COVID-19 infection.

CrodenseNet: An efficient parallel cross DenseNet for COVID-19 infection detection.

Purpose At present, though the application of Convolution Neural Network (CNN) to detect COVID-19 infection significantly enhance the detection performance and efficiency, it often causes low sensitivity and poor generalization performance. Methods In this article, an effective CNN, CrodenseNet is proposed for COVID-19 detection. CrodenseNet consists of two parallel DenseNet Blocks, each of which contains dilated convolutions with different expansion scales and traditional convolutions. We employ cross-dense connections and one-sided soft thresholding to the layers for filtering of noise-related features, and increase information interaction of local and global features. Results Cross-validation experiments on COVID-19x dataset shows that via CrodenseNet the COVID-19 detection attains the precision of 0.967 ± 0.010, recall of 0.967 ± 0.010, F1-score of 0.973 ± 0.005, AP (area under P-R curve) of 0.991 ± 0.002, and AUC (area under ROC curve) of 0.996 ± 0.001. Conclusion CrodenseNet outperforms a variety of state-of-the-art models in terms of evaluation metrics so it assists clinicians to prompt diagnosis of COVID-19 infection.

Corticosteroid, oseltamivir and delayed admission are independent risk factors for prolonged viral shedding in patients with Coronavirus Disease 2019.

INTRODUCTION: Coronavirus Disease 2019 (COVID-19) has spread worldwide, and it has reached to more than 14.5 million cases. Although Hubei province is the epicenter of China, little is known about epidemiological and clinical features of COVID-19 in other areas in Hubei province around Wuhan. In addition, the virological data, particularly the factors associated with viral shedding of COVID-19 has not been well described. OBJECTIVE: To describe the epidemiological and clinical features of patients with COVID-19 in Tianmen city, and identify risk factors associated with prolonged viral shedding of COVID-19. METHODS: Inpatients with COVID-19 admitted before February 9, 2020 were included. Characteristics were compared between patients with early and late viral RNA shedding. Multivariate cox regression model was used to investigate variables associated with prolonged viral shedding. RESULTS: One hundred and eighty-three patients were included. About 8.2% patients were categorized as critical degree of severity. All patients received antiviral therapy, with arbidol and interferon being the commonest. About 38.3% and 16.9% patients were treated with corticosteroid and immunoglobulin, respectively. Time from onset to admission (HR = 0.829, P < 0.001), and administration of corticosteroid (HR = 0.496, P = 0.002), arbidol (HR = 2.605, P = 0.008) and oseltamivir (HR = 0.416, P < 0.001) were independently associated with duration of viral shedding. CONCLUSION: Symptoms of patients from Tianmen are relatively mild. Treatment should be started as early as possible, but corticosteroid and oseltamivir should be initiated with caution. In addition, clinical trials on arbidol should be conducted to demonstrate its effectiveness.