Automated Screening of COVID-19 from chest CT is of emergency and importance during the outbreak of SARS-CoV-2 worldwide in 2020. However, accurate screening of COVID-19 is still a massive challenge due to the spatial complexity of 3D volumes, the labeling difficulty of infection areas, and the slight discrepancy between COVID-19 and other viral pneumonia in chest CT. While a few pioneering works have made significant progress, they are either demanding manual annotations of infection areas or lack of interpretability. In this paper, we report our attempt towards achieving highly accurate and interpretable screening of COVID-19 from chest CT with weak labels. We propose an attention-based deep 3D multiple instance learning (AD3D-MIL) where a patient-level label is assigned to a 3D chest CT that is viewed as a bag of instances. AD3D-MIL can semantically generate deep 3D instances following the possible infection area. AD3D-MIL further applies an attention-based pooling approach to 3D instances to provide insight into each instance's contribution to the bag label. AD3D-MIL finally learns Bernoulli distributions of the bag-level labels for more accessible learning. We collected 460 chest CT examples: 230 CT examples from 79 patients with COVID-19, 100 CT examples from 100 patients with common pneumonia, and 130 CT examples from 130 people without pneumonia. A series of empirical studies show that our algorithm achieves an overall accuracy of 97.9%, AUC of 99.0%, and Cohen kappa score of 95.7%. These advantages endow our algorithm as an efficient assisted tool in the screening of COVID-19.
Oxidative damage is a major cause of lung diseases, including pulmonary fibrosis. Laminarin is a kind of polysaccharide extracted from brown algae and plays vital roles in various biological processes. However, the functions and mechanisms of laminarin in pulmonary oxidative damage are poorly understood. This study aimed at investigating the protective effect of laminarin against pulmonary oxidative damage and underlying mechanisms. Human lung fibroblasts MRC-5 cells were treated with hydrogen peroxide to induce oxidative damage. Laminarin treatment was performed before or after hydrogen peroxide treatment, and then major indexes of oxidative damage, including superoxide dismutase (SOD), malondialdehyde (MDA), reduced glutathione (GSH) and catalase (CAT), were quantified by biochemical assays. The expression of oxidation-related factor, nuclear factor erythroid 2 like 2 (NRF2) was analyzed by qPCR, Western blot and immunofluorescence assay. NRF2 knockdown and overexpression were performed by cell transfection to reveal possible mechanisms. Results showed that laminarin treatment of 0.020 mg/mL for 24 h, especially the pre-treatment, could significantly relieve changes in SOD, MDA, GSH and CAT that were altered by hydrogen peroxide, and promote NRF2 mRNA (P < 0.001). NRF2 protein was also elevated by laminarin, and nuclear translocation was observed. Factors in NRF2 signaling pathways, including KEAP1, NQO1, GCLC and HO1, were all regulated by laminarin. Roles of NRF2 were tested, suggesting that NRF2 regulated the concentration of SOD, MDA, GSH and CAT, suppressed KEAP1, and promoted NQO1, GCLC and HO1. These findings suggested the protective role of laminarin against pulmonary oxidative damage, which might involve the regulation of NRF2 signaling pathways. This study provided information for the clinical application of laminarin to pulmonary diseases like pulmonary fibrosis.
Background: The number of patients infected with novel coronavirus disease (COVID–19) has exceeded 10 million in 2020, and a large proportion of them are asymptomatic. At present, there is still no effective treatment for this disease. Traditional Chinese medicine (TCM) shows a good therapeutic effect on COVID–19, especially for asymptomatic patients. According to the search results, we found that although there are many studies on COVID–19, there are no studies targeting asymptomatic infections. Therefore, we design a network meta-analysis (NMA) to evaluate the therapeutic effect of TCM on asymptomatic COVID–19. Methods: We will search Chinese and English databases to collect all randomized controlled trials (RCTs) of TCM combined with conventional western medicine or using only TCM to treat asymptomatic COVID–19 from December 2019 to July 2020. Then, two investigators will independently filter the articles, extract data, and evaluate the risk of bias. We will conduct a Bayesian NMA to evaluate the effects of different therapies. All data will be processed by Stata 16.0 and WinBUGS. Results: This study will evaluate the effectiveness of various treatments for asymptomatic COVID–19. The outcome indicators include the time when the nucleic acid turned negative, the proportion of patients with disease progression, changes in laboratory indicators, and the side effects of drugs. Conclusion: This analysis will further improve the treatment of asymptomatic COVID–19. INPLASY registration number: INPLASY202070022.
Nowadays, in order to secure supply and realize the energy and water saving, the monitoring automation has become a basic need for the city water supply pipe network. A remote wireless monitoring system is proposed for the city water supply pipe network based on Zigbee and GPRS. The Zigbee nodes are mainly used to detect and gather information and data of city water supply pipe network. The GPRS is used to upload information to monitoring center and download orders to coordinators. No wiring necessary, which makes the system very convenient.
This paper presents a predictive control method of heating system of heating power station. Firstly, the forecast of heating load is introduced using time series analysis, and the obtained result is used as an energy-saving initial value of predictive control system. Secondly, model simplification method is given and immediate control law is derived, the predictive model order is decreased from N to n. Simplification model satisfies the demand of real-time property of the control system. Thirdly, predictive error correction is used to replace error correction to implement the correction of optimum control of the system, which can improve adaptability and robustness of the system. Finally, simulation of heating system of heating power station is conducted and the results prove that the algorithm is effective in ensuring real-time control, improving tracking and robustness property.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.