ABSTRACT
Lung and lobe segmentation are two crucial techniques for lung imaging analysis that interact in clinical settings. Lung segmentation assists physicians in comparing different images to select the most appropriate surgical plan, while lobe segmentation provides precise anatomical information to help plan surgical procedures. However, inaccurate lung segmentation edges, mis-segmented lobe boundaries, and tiny targets remain challenging. To address these issues, we propose a dual-branch guided convolutional neural network,SCLMnet, for lung and lobe segmentation. To completely leverage the semantic information of feature maps, the first branch adds the SLM module to focus on low-level features at different spatial levels, highlighting feature representations of lung edges and lobe boundaries. The CLM module is added by Matrix inner product to model channel relations, emphasizing the relevance and similarity of feature maps and capturing the interdependency of high-level feature channels to highlight feature representations of the entire lung lobe region. The TSL module and the multiscale fusion strategy guide the feature information of the CLM and SLM modules and the deep features extracted by the second branch ResUNet network to jointly explore useful information in chest CT images. To evaluate the performance of the state-of-the-art model, we use three publicly available datasets: LUNA16, COVID-19-CT-Seg, and VESSEL12. Compared to existing methods,SCLMnet achieves average Dice scores of 92.17%, 97.80% and 99.12% respectively, demonstrating remarkable performance. These results suggest that lung and lobe segmentation using CT images with SCLMnet can play an essential role in clinical research.
Subject(s)
COVID-19ABSTRACT
Background: With more and more countries entering the phase of COVID-19 low transmission, there is an urgent need to study the implementation of community prevention in this stage. This study investigated the implementation of community prevention measures in China and whether residents consent they have adequate community protection during the Spring Festival of 2021, with exploring the differences in the sense of security caused by different measures.Methods: A cross-sectional survey was conducted in China from 4 to 26 February 2021. Convenient sampling strategy was adopted to recruit participators. Participants were asked to filled out the questions that assessed questionnaire on the implementation of community protection and residents' perception. Descriptive statistics were used to assess the public's attitudes. A binary logistic regression analysis was performed to identify the risk factors affecting the residents' attitudes.Results: A total of 2,361 residents filled out the questionnaire. The results showed 24.95% of community/village issued personal protective equipment, 62.98% implemented epidemic screening , and 46.59% implemented health propaganda and education of COVID-19. For people outside the community/village entering the community/village, 19.78% of community/village implemented that appointment of people are admitted, 4.57 implemented that only occupants are admitted. 1910 (80.90%) of residents agreed they acquire adequate community prevention during the Spring Festival. In addition, age of residents, “personal protective equipment will been issued by the community/village”, “resident epidemic screening is implemented by the community/village”, “health propaganda and education of COVID-19 is implemented by the community/village”, “appointment of people are admitted can enter the community/village”, “be satisfied with regularly cleaning and disinfecting by the community/village”, and “be satisfied with community service” were the mainly factors associated with residents’ attitudes.Conclusions: This research is based on an innovative perspective to explore whether residents perceive themselves to be adequately protected after experiencing measures; at the same time, the differences in the sense of security brought to residents by various measures were discussed, which can provide a reference for Chinese and global public health policy makers.
Subject(s)
COVID-19ABSTRACT
The coronavirus disease 2019 (COVID-19) is highly infectious, and the mortality of severe patients with the novel coronavirus pneumonia is high. Its pathogenesis is still unclear, and there is a lack of specific treatment method. The cytokine storm and imbalance of immune response may be the pathophysiological basis of acute respiratory distress syndrome (ARDS), multiple organ failure (MOF) and even death for the novel coronavirus pneumonia. Mesenchymal stem cells (MSC) has shown initial efficacy and clinical prospect in the treatment of severe patients by the immune regulation, tissue repair and anti-fibrosis properties. This article reviews the potential pathogenic mechanism of the COVID-19, the possible mechanism and application of MSC in the treatment of the COVID-19, which will provide reference for clinical treatment.