CMM: A CNN-MLP Model for COVID-19 Lesion Segmentation and Severity Grading.

In this paper, a CNN-MLP model (CMM) is proposed for COVID-19 lesion segmentation and severity grading in CT images. The CMM starts by lung segmentation using UNet, and then segmenting the lesion from the lung region using a multi-scale deep supervised UNet (MDS-UNet), finally implementing the severity grading by a multi-layer preceptor (MLP). In MDS-UNet, shape prior information is fused with the input CT image to reduce the searching space of the potential segmentation outputs. The multi-scale input compensates for the loss of edge contour information in convolution operations. In order to enhance the learning of multiscale features, the multi-scale deep supervision extracts supervision signals from different upsampling points on the network. In addition, it is empirical that the lesion which has a whiter and denser appearance tends to be more severe in the COVID-19 CT image. So, the weighted mean gray-scale value (WMG) is proposed to depict this appearance, and together with the lung and lesion area to serve as input features for the severity grading in MLP. To improve the precision of lesion segmentation, a label refinement method based on the Frangi vessel filter is also proposed. Comparative experiments on COVID-19 public datasets show that our proposed CMM achieves high accuracy on COVID-19 lesion segmentation and severity grading. Source codes and datasets are available at our GitHub repository (https://github.com/RobotvisionLab/COVID-19-severity-grading.git).

Multi-Attention Segmentation Networks Combined with the Sobel Operator for Medical Images.

Medical images are used as an important basis for diagnosing diseases, among which CT images are seen as an important tool for diagnosing lung lesions. However, manual segmentation of infected areas in CT images is time-consuming and laborious. With its excellent feature extraction capabilities, a deep learning-based method has been widely used for automatic lesion segmentation of COVID-19 CT images. However, the segmentation accuracy of these methods is still limited. To effectively quantify the severity of lung infections, we propose a Sobel operator combined with multi-attention networks for COVID-19 lesion segmentation (SMA-Net). In our SMA-Net method, an edge feature fusion module uses the Sobel operator to add edge detail information to the input image. To guide the network to focus on key regions, SMA-Net introduces a self-attentive channel attention mechanism and a spatial linear attention mechanism. In addition, the Tversky loss function is adopted for the segmentation network for small lesions. Comparative experiments on COVID-19 public datasets show that the average Dice similarity coefficient (DSC) and joint intersection over union (IOU) of the proposed SMA-Net model are 86.1% and 77.8%, respectively, which are better than those in most existing segmentation networks.

FAM: focal attention module for lesion segmentation of COVID-19 CT images.

The novel coronavirus pneumonia (COVID-19) is the world's most serious public health crisis, posing a serious threat to public health. In clinical practice, automatic segmentation of the lesion from computed tomography (CT) images using deep learning methods provides an promising tool for identifying and diagnosing COVID-19. To improve the accuracy of image segmentation, an attention mechanism is adopted to highlight important features. However, existing attention methods are of weak performance or negative impact to the accuracy of convolutional neural networks (CNNs) due to various reasons (e.g. low contrast of the boundary between the lesion and the surrounding, the image noise). To address this issue, we propose a novel focal attention module (FAM) for lesion segmentation of CT images. FAM contains a channel attention module and a spatial attention module. In the spatial attention module, it first generates rough spatial attention, a shape prior of the lesion region obtained from the CT image using median filtering and distance transformation. The rough spatial attention is then input into two 7 × 7 convolution layers for correction, achieving refined spatial attention on the lesion region. FAM is individually integrated with six state-of-the-art segmentation networks (e.g. UNet, DeepLabV3+, etc.), and then we validated these six combinations on the public dataset including COVID-19 CT images. The results show that FAM improve the Dice Similarity Coefficient (DSC) of CNNs by 2%, and reduced the number of false negatives (FN) and false positives (FP) up to 17.6%, which are significantly higher than that using other attention modules such as CBAM and SENet. Furthermore, FAM significantly improve the convergence speed of the model training and achieve better real-time performance. The codes are available at GitHub (https://github.com/RobotvisionLab/FAM.git).

Release and Demand of Public Health Information in Social Media During the Outbreak of COVID-19 in China.

Information release is a key to the macro-economy during the outbreak of the Coronavirus Diosease-2019 (COVID-19). To explore the relationship between information supply by the government and public information demand in the pandemic, this study collected over 4,000 posts published on the most popular social media platform, i.e., WeChat. Many approaches, such as text mining, are employed to explore the information at different stages during the pandemic. According to the results, the government attached great importance to the information related to the pandemic. The main topics of information released by the government included the latest situation of the pandemic, announcements by the State Council, and prevention policies for COVID-19. Information mismatch between the public and Chinese governments contributed to the economic depression caused by the pandemic. Specifically, the topics of "the latest situation" and "popular scientific knowledge regarding the pandemic" have gained the most attention of the public. The information demand of the public has changed from the pandemic itself to the recovery of social life and industrial activities after the authority announced the control of the pandemic. However, during the recession phase, the information demand has shifted to asymptomatic infections and global pandemic trends. By contrast, some of the main topics provided by the government, such as "How beautiful you are," were excessive because the public demand is insufficient. Therefore, severe mismatches existed between information release of the government and public information demand during the pandemic, which impeded the recovery of the economy. The results in this study provide strategical suggestions of information release and opinion guidance for the authorities.

Innate immunology in COVID-19-a living review. Part II: dysregulated inflammation drives immunopathology.

The current pandemic of coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) poses a global health crisis and will likely continue to impact public health for years. As the effectiveness of the innate immune response is crucial to patient outcome, huge efforts have been made to understand how dysregulated immune responses may contribute to disease progression. Here we have reviewed current knowledge of cellular innate immune responses to SARS-CoV-2 infection, highlighting areas for further investigation and suggesting potential strategies for intervention. We conclude that in severe COVID-19 initial innate responses, primarily type I interferon, are suppressed or sabotaged which results in an early interleukin (IL)-6, IL-10 and IL-1ß-enhanced hyperinflammation. This inflammatory environment is driven by aberrant function of innate immune cells: monocytes, macrophages and natural killer cells dispersing viral pathogen-associated molecular patterns and damage-associated molecular patterns into tissues. This results in primarily neutrophil-driven pathology including fibrosis that causes acute respiratory distress syndrome. Activated leukocytes and neutrophil extracellular traps also promote immunothrombotic clots that embed into the lungs and kidneys of severe COVID-19 patients, are worsened by immobility in the intensive care unit and are perhaps responsible for the high mortality. Therefore, treatments that target inflammation and coagulation are promising strategies for reducing mortality in COVID-19.

Innate immunology in COVID-19-a living review. Part I: viral entry, sensing and evasion.

The coronavirus infectious disease 2019 (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) remains a world health concern and can cause severe disease and high mortality in susceptible groups. While vaccines offer a chance to treat disease, prophylactic and anti-viral treatments are still of vital importance, especially in context of the mutative ability of this group of viruses. Therefore, it is essential to elucidate the molecular mechanisms of viral entry, innate sensing and immune evasion of SARS-CoV-2, which control the triggers of the subsequent excessive inflammatory response. Viral evasion strategies directly target anti-viral immunity, counteracting host restriction factors and hijacking signalling pathways to interfere with interferon production. In Part I of this review, we examine SARS-CoV-2 viral entry and the described immune evasion mechanisms to provide a perspective on how the failure in initial viral sensing by infected cells can lead to immune dysregulation causing fatal COVID-19, discussed in Part II.

The Effects of Diabetes and Hypertension on the Severity of COVID-19 - Yichang, Hubei Province, 2020.

What is already known on this topic? COVID-19 has become a serious public health issue. A higher proportion of severe patients were senior patients with underlying diseases such as diabetes and hypertension and had a lack of statistical evidence so far. What is added by this report? When severe illness was compared with non-severe illness, senior patients were at a greater risk (4.71) than young and middle-aged patients, as well as the odds ratio was about 2.99 patients with diabetes compared to patients without diabetes and hypertension. COVID-19-infectious senior patients with diabetes were inclined to suffer severe illness. What are the implications for public health practice? Much more attention should be provided for the elderly and individuals with diabetes, for which a community-based education and surveillance program could be considered.