Multi-Attentional U-Net for Medical Image Segmentation

Deep learning (DL) approaches for image segmentation have been gaining state-of-the-art performance in recent years. Particularly, in deep learning, U-Net model has been successfully used in the field of image segmentation. However, traditional U-Net methods extract features, aggregate remote information, and reconstruct images by stacking convolution, pooling, and up sampling blocks. The traditional approach is very inefficient due of the stacked local operators. In this paper, we propose the multi-attentional U-Net that is equipped with non-local blocks based self-attention, channel-attention, and spatial-attention for image segmentation. These blocks can be inserted into U-Net to flexibly aggregate information on the plane and spatial scales. We perform and evaluate the multi-attentional U-Net model on three benchmark data sets, which are COVID-19 segmentation, skin cancer segmentation, thyroid nodules segmentation. Results show that our proposed models achieve better performances with faster computation and fewer parameters. The multi-attention U-Net can improve the medical image segmentation results. © 2022 IEEE.

Recent advances in the study of a novel Omicron variant of SARS-CoV-2

Due to the continued emergence of multiple variants of SARS-CoV-2, the ongoing pandemic has resulted in severe mortality over the past two years. After the Alpha, Beta, Gamma and Delta variants, the most recent new variant of concern (VOC) strain to emerge is Omicron (B.1.1.529), which evolved as a result of the accumulation of a large number of mutations. The Omicron variant, which has a much higher transmission rate than the Delta variant, soon replaced the Delta variant and others, is now the dominant variant worldwide. The emergence of Omicron poses new challenges for the prevention and control of COVID-19 and has raised a number of concerns worldwide. Recently, cases of Omicron infection have been reported in several parts of China, and therefore this paper provides a comprehensive analysis and summary of the epidemiology and immune escape mechanisms of the Omicron variant. We also suggest some therapeutic strategies against the Omicron variant, including rapid diagnosis, genome analysis of emerging variants, ramping up of vaccination drives and receiving booster doses, updating the available vaccines, designing of multivalent vaccines able to generate hybrid immunity, up-gradation of medical facilities and strict implementation of adequate prevention and control measures need to be given high priority to handle the on-going COVID-19 pandemic successfully. © 2022 by the Author(s).

Design and Implementation of COVID-19 Assistant Diagnostic System Based on Deep Learning

In recent years, novel coronavirus pneumonia has spread rapidly around the world due to its strong infectiousness, and the medical systems of related countries are facing huge challenges. As the most intuitive and effective supplementary diagnostic basis for the results of nucleic acid tests, medical imaging screening has gradually become more and more important in epidemic prevention and control. In this context, this paper develops a novel coronavirus pneumonia-auxiliary diagnostic system by using deep learning techniques. This system can help medical staffs to diagnose the condition through X-Ray images quickly. This system builds a sample dataset by collecting lung X-ray images from two datasets and uses a neural network for auxiliary diagnosis training, which achieves an accuracy rate of 98%. Furthermore, two interactive visual interfaces in the form of PC-side applet and Web page are supported in the system, which makes it much easier for medical personnel to operate the system. © 2021 IEEE.

The value of ROX index in evaluating the efficacy of high-flow nasal cannula oxygen therapy in patients with COVID-19

Objective: To assess the value of the ROX index in evaluating the efficacy of highflow nasal cannula oxygen therapy (HFNC) in patients with coronavirus infected disease (COVID-19). Methods: This is a retrospective study. The included patients were diagnosed as COVID-19 in the intensive care unit (ICU) of the Cancer Center of Union Hospital affiliated to Tongji Medical College of Huazhong University of Science and Technology from February 15, 2020 to March 15, 2020. All the patients were treated by HFNC. According to whether the patient subsequently received non-invasive positive pressure ventilation or invasive positive pressure ventilation, patients were divided into the HFNC success group and the HFNC failure group. Parameters in the two groups such as basic characteristics, lactic acid, number of chest radiographs, APACHE II, lymphocyte count, baseline respiratory rate, baseline percutaneous oxygen saturation, baseline PaO2/FiO2, baseline ROX index, and ROX index after 2, 6 and 12 h HFNC treatment were analyzed with t test, Chi-square test or rank sum test. Results: A total of 57 cases were included in this study. There were no significant differences in sex, age, comorbidities, lactic acid, quadrants of chest radiograph lung infection, APACHE II, lymphocyte count, and baseline respiratory frequency, transcutaneous oxygen saturation, oxygenation index, and ROX index between the HFNC success group and the HFNC faliure group (P>0.05). Logistic regression analysis showed that ROX index after 2 h HFNC treatment (OR=0.069), ROX index after 6 h HFNC treatment (OR=0.194) and ROX index after 12 h HFNC treatment (OR=0.036) were all protective factors for the therapeutic effect of HFNC treatment in COVID-19 patients. ROC curve showed that there were significant differences in ROX index after 2 h HFNC treatment, ROX index after 6 h HFNC treatment, and ROX index after 12 h HFNC treatment (P<0.05). In the evaluation index, the area under the ROC curve of the ROX index after 2 h HFNC treatment was 0.838, the sensitivity was 64.5%, and the specificity was 100%. After 6 h HFNC treatment, the area under the ROX index ROC curve was 0.762, the sensitivity was 64.5%, and the specificity was 92.3%. After 12 h HFNC treatment, the ROX index ROC curve area was 0.866, the sensitivity was 67.7%, and the specificity was 100%. Conclusions: The ROX index can be used to evaluate the efficacy of HFNC in COVID-19 patients in a timely, simple and real-time manner. © 2021 Chinese Medical Association. All rights reserved.

Identification of the anti-COVID-19 mechanism of action of Han-Shi Blocking Lung using network pharmacology-integrated molecular docking

Purpose: To investigate the bio-active components and the potential mechanism of the prescription remedy, Han-Shi blocking lung, with network pharmacology with a view to expanding its application. Methods: Chemical components were first collected from the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform (TCMSP). Pharmmapper database and GeneCards were used to predict the targets related to active components and COVID-19. Using DAVIDE and KOBAS 3.0 databases, Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) were enriched. A "components-targets-pathways" (C-T-P) network was conducted by Cytoscape 3.7.1 software. With the aid of Discovery Studio 2016 software, bio-active components were selected to dock with SARS-COV-2 3CL and ACE2. Results: From the prescription, 47 bio-active components, 83 targets and 103 signaling pathways were obtained in total (p < 0.05). 126 GO entries (p < 0.05) were screened by GO enrichment analysis. Molecular docking results showed that procyanidin B1 eriodictyol, (4E, 6E)-1, 7-bis(4-hydroxyphenyl)hepta-4, 6-dien-3-one, and quercetin had higher docking scores with SARS-COV-2 3CL and ACE2. Conclusion: With network pharmacology and molecular docking, the bio-active components and targets of this prescription, Han-Shi blocking lung, against COVID-19 were identified. Taken together, this study provided a basis for the treatment of COVID-19 and further promotion of this prescription.

Design of Omnidirectional Mobile Robot Platform Controlled by Remote Visualization

Mobile Robot can realize non-contact operation of medical and rehabilitation services in the outbreak of CoVID-19, and Mobile Robot Platform (MRP) is the key component in Mobile Robots. By using Mecanum wheels, the omnidirectional MRP (OMRP) of four-wheel layout is realized. Combined with raspberry PI and STM32 micro-controller, the OMRP is driven by motion control algorithm to moves and rotates in all directions. The remote visual control link is built through 4G data transmission and 4G diagram transmission to realize the 4G visual control mode. Also, combined with the digital control mode of RS-485 data transmission and the Bluetooth controller, the multi-mode control of OMRP is realized. Finally, a prototype of OMRP is made. Experiments of the prototype verify the feasibility of OMRP, and the effectiveness of the 4G remote visual control. Overall, this paper provides a new way of robot remote control in wireless communication for the upcoming 5G era. © 2021, Springer Nature Singapore Pte Ltd.

Vegetable production under COVID-19 pandemic in China: An analysis based on the data of 526 households

The COVID-19 pandemic had an enormous impact on the vegetable supply chain in China. Effective evaluation of the pandemic's influences on vegetable production is vital for policy settings to enhance the security of vegetable supply. Based on first-hand data from 526 households, we explored regional differences in different types of loss and potential factors affecting the severity farmer households suffered during the pandemic. The results underline that sales contraction and price volatility in the context of interruption of supply chain dominate the total losses during the pandemic. Such losses differ across provinces and are more substantial in provinces with stricter confinement measures. Farmer households' participation in local market and modern marketing methods helps mitigate the negative effects of the COVID-19 shock, while labor hiring and facilities adoption in production widen the losses due to the shortage in the workforce. In the future, the vegetable industry practitioners and relevant government departments should work together to coordinate the development of short and long supply chains and strengthen the stability and security of the vegetable supply chain.

Prediction of 2019-nCoV Epidemic by Linear Regression Model

The Linear Regression Model is a useful prediction tool. In this paper, a linear regression model was used to analyze and predict the death toll of the novel corona virus (2019-nCov) outbreaks in 2019. Besides, an improved linear regression method was proposed to obtain a more accurate epidemic prediction model. In this paper, the author used one parameter to predict the data. Therefore, in the further research, more factors will be added to conduct a more accurate prediction. © 2020 ACM.

Network Pharmacology Integrated Molecular Docking Analysis of Potential Common Mechanisms of Shu-Feng-Jie-Du Capsule in the Treatment of SARS, MERS, and COVID-19

Shu-Feng-Jie-Du Capsules (SFJDCs) have been clinically proven to have a good therapeutic effect on COVID-19 in China. This study aimed to analyze the common mechanisms of SFJDC in the treatment of severe acute respiratory syndrome (SARS), Middle East respiratory syndrome (MERS), and COVID-19 via network pharmacology and molecular docking. We further explored the potential application value of SFJDC in the treatment of coronavirus infection. All components of SFJDC were collected from the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform. The viral associated targets of the active components were forecast using the Pharmmapper database and GeneCards. The Database for Annotation, Visualization, and Integrated Discovery and KOBAS 3.0 system were used for gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis of SFJDC’s core targets. Further, the protein–protein interaction network was built using STRING database. The herb–component network and component–target–pathway network were constructed using Cytoscape 3.7.2. The core active components of SFJDC were docked with core targets and COVID-19 coronavirus 3 Cl hydrolase and angiotensin-converting enzyme 2 (ACE2) via Discovery Studio 2016 software. A total of 110 active components were filtered from SFJDC, with 47 core targets, including epidermal growth factor receptor, mitogen-activated protein kinase 1, mitogen-activated protein kinase 3, and interleukin 6. There were 416 GO items in the GO enrichment analysis (P <.05) and 57 signaling pathways (P <.05) in KEGG, mainly including pathways in cancer, pancreatic cancer, colorectal cancer, apoptosis, and neurotrophin signaling pathway, among others. The results of molecular docking showed that luteolin and rhein had a higher docking score with 3 Cl, ACE2, and core targets of SFJDC for antiviral effect. SFJDC is characterized by multicomponent, multitarget, and multisignaling pathways for the treatment of coronavirus infection. The mechanism of action of SFJDC in the treatment of MERS, SARS, and COVID-19 may be associated with the regulation of genes coexpressed with ACE2 and immune- related signaling pathways.

Preliminary Analysis of the Therapeutic Mechanism of Feiluoning in Convalescent Patients With COVID-19

Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2), is often accompanied by injury to pulmonary function and pulmonary fibrosis. Feiluoning (FLN) is a new Chinese medicine prescription which is available for the treatment of severe and critical convalescence of COVID-19 patients. FLN also has a positive effect on pulmonary function injury and pulmonary fibrosis. We explored the potential mechanism of FLN’s effect on the convalescent treatment of COVID-19. According to the pharmacodynamic activity parameters, we screened the active chemical constituents of FLN by comparing the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform. The Uniprot database was used to querying the corresponding target genes, and Cytoscape 3.6.1 was used to construct a herb-compound-target network. Protein interaction analysis, target gene function enrichment analysis, and signal pathway analysis were performed using the STRING, DAVID, and Kyoto Encyclopedia of Genes and Genomes pathway databases. Molecular docking was used to predict the binding capacity of the core compound with COVID-19 hydrolase 3 Cl and angiotensin-converting enzyme 2 (ACE2). The herb-compound-target network was successfully constructed and key targets identified, including prostaglandin G/H synthase 2, estrogen receptor 1, heat shock protein HSP 90, and androgen receptor. The major affected metabolic pathways were pathways in cancer, pancreatic cancer, nonsmall cell lung cancer, and toll-like receptor signaling. The core compounds of FLN, including quercetin, luteolin, kaempferol, and stigmasterol, could strongly bind to COVID-19 3 Cl hydrolase, and other compounds, including 7-O-methylisomucronulatol and medicocarpin, could strongly bind to ACE2. Thus, it is predicted that FLN has the characteristics of a multicomponent, multitarget, and multichannel overall control compound. FLN’s mechanism of action in the treatment of COVID-19 may be associated with the regulation of inflammation and immune-related signaling pathways, and the influence of COVID-19 3 Cl hydrolase binding ability.

Management of people with epilepsy during the COVID-19 pandemic: a national survey among epileptologists in China

Background: Compared to the healthy people, people with comorbid medical conditions are more vulnerable in the context of the coronavirus disease 2019 (COVID-19) pandemic, including the people with epilepsy. Besides a consensus recommendation by multi-national epilepsy specialists, the situation of the epilepsy management during the pandemic has seldom been reported. Methods: The China Association Against Epilepsy carried out an online nationwide survey among its board members in April 2020. One hundred and thirty board members from 22 provinces, 5 autonomous regions, and 4 municipalities across China responded to the questionnaires. They reported the situation of clinical practice and gave opinions on the management of people with epilepsy between January 13th and March 31st, 2020, a time period concentrated with confirmed COVID-19 cases. Results: The proportions of patients consulting through telephone or online (88.4%) and of patients with regular case review (93.9%) were highest in the high-risk area, as reported by the responders. The patients in the high-risk area were more likely to have increased episodes of seizures (17.7%), aggravated psychological disorders (30.2%), and less accessibility to anti-seizure medications (ASMs) (77.2%). Regular ASMs supply (74.6%), medical consultation (69.2%), and psychological aids (29.2%) were urgently needed for people with epilepsy. Conclusions: This study demonstrated the most common dilemma faced by people with epilepsy in policy circumstances during the COVID-19 epidemic in China. The opinions raised by Chinese epileptologists may provide reference for epilepsy care in other countries.