Two-stage hybrid network for segmentation of COVID-19 pneumonia lesions in CT images: a multicenter study.

COVID-19 has been spreading continuously since its outbreak, and the detection of its manifestations in the lung via chest computed tomography (CT) imaging is essential to investigate the diagnosis and prognosis of COVID-19 as an indispensable step. Automatic and accurate segmentation of infected lesions is highly required for fast and accurate diagnosis and further assessment of COVID-19 pneumonia. However, the two-dimensional methods generally neglect the intraslice context, while the three-dimensional methods usually have high GPU memory consumption and calculation cost. To address these limitations, we propose a two-stage hybrid UNet to automatically segment infected regions, which is evaluated on the multicenter data obtained from seven hospitals. Moreover, we train a 3D-ResNet for COVID-19 pneumonia screening. In segmentation tasks, the Dice coefficient reaches 97.23% for lung segmentation and 84.58% for lesion segmentation. In classification tasks, our model can identify COVID-19 pneumonia with an area under the receiver-operating characteristic curve value of 0.92, an accuracy of 92.44%, a sensitivity of 93.94%, and a specificity of 92.45%. In comparison with other state-of-the-art methods, the proposed approach could be implemented as an efficient assisting tool for radiologists in COVID-19 diagnosis from CT images.

A Heterologous V-01 or Variant-Matched Bivalent V-01D-351 Booster following Primary Series of Inactivated Vaccine Enhances the Neutralizing Capacity against SARS-CoV-2 Delta and Omicron Strains.

Immune escape of emerging SARS-CoV-2 variants of concern (VOCs) and waning immunity over time following the primary series suggest the importance and necessity of booster shot of COVID-19 vaccines. With the aim to preliminarily evaluate the potential of heterologous boosting, we conducted two pilot studies to evaluate the safety and immunogenicity of the V-01 or a bivalent V-01D-351 (targeting Delta and Beta strain) booster after 5-7 months of the primary series of inactivated COVID-9 vaccine (ICV). A total of 77 participants were enrolled, with 20 participants in the V-01D-351 booster study, and 27, 30 participants in the age stratified participants of V-01 booster study. The safety results showed that V-01 or V-01D-351 was safe and well-tolerated as a heterologous booster shot, with overall adverse reactions predominantly being absent or mild in severity. The immunogenicity results showed that the heterologous prime-boost immunization with V-01 or bivalent V-01D-351 booster induced stronger humoral immune response as compared with the homologous booster with ICV. In particular, V-01D-351 booster showed the highest pseudovirus neutralizing antibody titers against prototype SARS-CoV-2, Delta and Omicron BA.1 strains at day 14 post boosting, with GMTs 22.7, 18.3, 14.3 times higher than ICV booster, 6.2, 6.1, 3.8 times higher than V-01 booster (10 µg), and 5.2, 3.8, 3.5 times higher than V-01 booster (25 µg), respectively. The heterologous V-01 booster also achieved a favorable safety and immunogenicity profile in older participants. Our study has provided evidence for a flexible roll-out of heterologous boosters and referential approaches for variant-specific vaccine boosters, with rationally conserved but diversified epitopes relative to primary series, to build herd immunity against the ongoing pandemic.

Artificial intelligence for stepwise diagnosis and monitoring of COVID-19.

BACKGROUND: Main challenges for COVID-19 include the lack of a rapid diagnostic test, a suitable tool to monitor and predict a patient's clinical course and an efficient way for data sharing among multicenters. We thus developed a novel artificial intelligence system based on deep learning (DL) and federated learning (FL) for the diagnosis, monitoring, and prediction of a patient's clinical course. METHODS: CT imaging derived from 6 different multicenter cohorts were used for stepwise diagnostic algorithm to diagnose COVID-19, with or without clinical data. Patients with more than 3 consecutive CT images were trained for the monitoring algorithm. FL has been applied for decentralized refinement of independently built DL models. RESULTS: A total of 1,552,988 CT slices from 4804 patients were used. The model can diagnose COVID-19 based on CT alone with the AUC being 0.98 (95% CI 0.97-0.99), and outperforms the radiologist's assessment. We have also successfully tested the incorporation of the DL diagnostic model with the FL framework. Its auto-segmentation analyses co-related well with those by radiologists and achieved a high Dice's coefficient of 0.77. It can produce a predictive curve of a patient's clinical course if serial CT assessments are available. INTERPRETATION: The system has high consistency in diagnosing COVID-19 based on CT, with or without clinical data. Alternatively, it can be implemented on a FL platform, which would potentially encourage the data sharing in the future. It also can produce an objective predictive curve of a patient's clinical course for visualization. KEY POINTS: • CoviDet could diagnose COVID-19 based on chest CT with high consistency; this outperformed the radiologist's assessment. Its auto-segmentation analyses co-related well with those by radiologists and could potentially monitor and predict a patient's clinical course if serial CT assessments are available. It can be integrated into the federated learning framework. • CoviDet can be used as an adjunct to aid clinicians with the CT diagnosis of COVID-19 and can potentially be used for disease monitoring; federated learning can potentially open opportunities for global collaboration.

Temporary vaccination clinic for COVID-19 in Zhuhai, China.

Vaccines are urgently needed to control the COVID-19 pandemic. To gradually increase the vaccination rate among residents, temporary vaccination clinic for COVID-19 plays an important role. It should be located in an area with convenient transportation and concentrated population. Functional zones including waiting and inquiry, registration and notification, injection, observation and emergency room should be established. All vaccine recipients' information should be uploaded to the national immunization information system. Medical staff at the temporary vaccination clinic should be professionally trained. A cautious disinfection and wiping are essential for the temporary vaccination clinic.

A Deep Learning Radiomics Model to Identify Poor Outcome in COVID-19 Patients With Underlying Health Conditions: A Multicenter Study.

OBJECTIVE: Coronavirus disease 2019 (COVID-19) has caused considerable morbidity and mortality, especially in patients with underlying health conditions. A precise prognostic tool to identify poor outcomes among such cases is desperately needed. METHODS: Total 400 COVID-19 patients with underlying health conditions were retrospectively recruited from 4 centers, including 54 dead cases (labeled as poor outcomes) and 346 patients discharged or hospitalized for at least 7 days since initial CT scan. Patients were allocated to a training set (n = 271), a test set (n = 68), and an external test set (n = 61). We proposed an initial CT-derived hybrid model by combining a 3D-ResNet10 based deep learning model and a quantitative 3D radiomics model to predict the probability of COVID-19 patients reaching poor outcome. The model performance was assessed by area under the receiver operating characteristic curve (AUC), survival analysis, and subgroup analysis. RESULTS: The hybrid model achieved AUCs of 0.876 (95% confidence interval: 0.752-0.999) and 0.864 (0.766-0.962) in test and external test sets, outperforming other models. The survival analysis verified the hybrid model as a significant risk factor for mortality (hazard ratio, 2.049 [1.462-2.871], P < 0.001) that could well stratify patients into high-risk and low-risk of reaching poor outcomes (P < 0.001). CONCLUSION: The hybrid model that combined deep learning and radiomics could accurately identify poor outcomes in COVID-19 patients with underlying health conditions from initial CT scans. The great risk stratification ability could help alert risk of death and allow for timely surveillance plans.

COVID-19 emergencies around the globe: China's experience in controlling COVID-19 and lessons learned.

MOTIVATION: Nations around the world have been significantly impacted during the COVID-19 pandemic. China's strategies for controlling COVID-19 offer valuable lessons for the global community. By learning from China's experience and lessons, other countries could also find appropriate methods to control the pandemic. PROBLEM STATEMENT: What measures has China taken to control the pandemic? What lessons has China learned through this pandemic? APPROACH/METHODS: The literature on China's lessons and experience in controlling the COVID-19 pandemic was searched and reviewed. Related newspapers and magazines were also searched. RESULTS: China's experience can be summed up as establishing temporary hospitals, strict isolation, experts with a knowledge of COVID-19, and measures that increase social distancing. CONCLUSIONS: By learning from the experience of China, other countries in the world could eventually find the methods to control the COVID-19 pandemic. An emergency response system should be established in each country. Doctors and nurses are not alone in fighting COVID-19, and the entire world is helping them. With cooperation, current difficulties could be overcome.

A Potential Role of Interleukin 10 in COVID-19 Pathogenesis.

A unique feature of the cytokine storm in coronavirus disease 2019 (COVID-19) is the dramatic elevation of interleukin 10 (IL-10). This was thought to be a negative feedback mechanism to suppress inflammation. However, several lines of clinical evidence suggest that dramatic early proinflammatory IL-10 elevation may play a pathological role in COVID-19 severity.

Antibody response and therapy in COVID-19 patients: what can be learned for vaccine development?

The newly emerged severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has infected millions of people and caused tremendous morbidity and mortality worldwide. Effective treatment for coronavirus disease 2019 (COVID-19) due to SARS-CoV-2 infection is lacking, and different therapeutic strategies are under testing. Host humoral and cellular immunity to SARS-CoV-2 infection is a critical determinant for patients' outcomes. SARS-CoV-2 infection results in seroconversion and production of anti-SARS-CoV-2 antibodies. The antibodies may suppress viral replication through neutralization but might also participate in COVID-19 pathogenesis through a process termed antibody-dependent enhancement. Rapid progress has been made in the research of antibody response and therapy in COVID-19 patients, including characterization of the clinical features of antibody responses in different populations infected by SARS-CoV-2, treatment of COVID-19 patients with convalescent plasma and intravenous immunoglobin products, isolation and characterization of a large panel of monoclonal neutralizing antibodies and early clinical testing, as well as clinical results from several COVID-19 vaccine candidates. In this review, we summarize the recent progress and discuss the implications of these findings in vaccine development.

Early triage of critically ill COVID-19 patients using deep learning.

The sudden deterioration of patients with novel coronavirus disease 2019 (COVID-19) into critical illness is of major concern. It is imperative to identify these patients early. We show that a deep learning-based survival model can predict the risk of COVID-19 patients developing critical illness based on clinical characteristics at admission. We develop this model using a cohort of 1590 patients from 575 medical centers, with internal validation performance of concordance index 0.894 We further validate the model on three separate cohorts from Wuhan, Hubei and Guangdong provinces consisting of 1393 patients with concordance indexes of 0.890, 0.852 and 0.967 respectively. This model is used to create an online calculation tool designed for patient triage at admission to identify patients at risk of severe illness, ensuring that patients at greatest risk of severe illness receive appropriate care as early as possible and allow for effective allocation of health resources.

Preventing Mortality in COVID-19 Patients: Which Cytokine to Target in a Raging Storm?

Coronavirus disease 2019 (COVID-19) from severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection has resulted in tremendous morbidity and mortality worldwide. A major underlying cause of COVID-19 mortality is a hyperinflammatory cytokine storm in severe/critically ill patients. Although many clinical trials are testing the efficacy of targeting inflammatory cytokines/chemokines in COVID-19 patients, the critical inflammatory mediator initiating COVID-19 patient death is undefined. Here we suggest that the immunopathological pathway leading to COVID-19 mortality can be divided into three stages with distinct clinical features that can be used to guide therapeutic strategies. Our interpretation of the recently published clinical trials from COVID-19 patients suggests that the clinical efficacy in preventing COVID-19 mortality using IL-1 blockade is subjected to notable caveats, while that for IL-6 blockade is suboptimal. We discuss critical factors in determining appropriate inflammatory cytokine/chemokine targets, timing, and combination of treatments to prevent COVID-19 mortality.

Chinese Society of Interventional Radiology Expert Consensus on the prevention and control of COVID-19 in interventional radiology procedures (first edition).

The COVID-19 pandemic seriously threatens the lives of the general public and poses momentous challenges to all medical workers, including those engaged in interventional radiology, who play an important role in the diagnosis and treatment of various diseases. To further standardize the prevention and control of nosocomial infections and ensure the safety of doctors and patients, the Chinese Society of Interventional Radiology (CSIR) organized multidisciplinary experts in the field of interventional radiology in China to prepare an "Expert Consensus" elaborating and summarizing the protective strategies and suggestions for medical workers in the field of interventional radiology when they engage in interventional diagnosis and treatment activities against the background of novel coronavirus infection control. The aim is to provide a reference for interventional procedures in hospitals and other medical institutions at all levels in China and worldwide. The key points include the following: (I) non-emergency interventional diagnosis and treatment should be suspended while work is ongoing to prevent and control the spread of COVID-19; (II) protective measures should be taken according to the appropriate level designated for COVID-19 infection prevention and control; (III) patients should take measures to protect themselves when they want to see a doctor, including accessing outpatient services online and other relevant channels of consultation.

Complex emergencies of COVID-19: management and experience in Zhuhai, China.

The impact of communicable diseases (infectious diseases) on human health is obvious. The sudden outbreak of COVID-19 (Corona Virus Disease 2019) has made people realise the threat of communicable diseases to mankind. As a city of many migrants, Zhuhai Special Economic Zone experienced great challenges brought about by the COVID-19 epidemic. Experience has been acquired from all aspects of this. A highly reactive, multifunctional and efficient emergency management system should be established, and the significance of information communication should be fully understood for the future.