An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection (preprint)

Coronavirus 2019 has brought severe challenges to social stability and public health worldwide. One effective way of curbing the epidemic is to require people to wear masks in public places and monitor mask-wearing states by utilizing suitable automatic detectors. However, existing deep learning based models struggle to simultaneously achieve the requirements of both high precision and real-time performance. To solve this problem, we propose an improved lightweight face mask detector based on YOLOv5, which can achieve an excellent balance of precision and speed. Firstly, a novel backbone ShuffleCANet that combines ShuffleNetV2 network with Coordinate Attention mechanism is proposed as the backbone. Afterwards, an efficient path aggression network BiFPN is applied as the feature fusion neck. Furthermore, the localization loss is replaced with alpha-CIoU in model training phase to obtain higher-quality anchors. Some valuable strategies such as data augmentation, adaptive image scaling, and anchor cluster operation are also utilized. Experimental results on AIZOO face mask dataset show the superiority of the proposed model. Compared with the original YOLOv5, the proposed model increases the inference speed by 28.3% while still improving the precision by 0.58%. It achieves the best mean average precision of 95.2% compared with other seven existing models, which is 4.4% higher than the baseline.

Chinese Society of Anesthesiology expert consensus on anesthetic management of cardiac surgical patients with suspected or confirmed Coronavirus disease 2019

The outbreak of a new coronavirus (severe acute respiratory syndrome coronavirus 2 [SARS-CoV-2]) in China in December 2019 has brought serious challenges to disease prevention and public health. Patients with severe coronavirus disease 2019 (COVID-19) who undergo cardiovascular surgery necessitate extremely high demands from anesthesia personnel, and face high risks of mortality and morbidity. Based on the current understanding of COVID-19 and the clinical characteristics of cardiovascular surgical patients, the authors provide anesthesia management guidelines for cardiovascular surgery along with the prevention and control of COVID-19.

Rapid Artificial Intelligence Solutions in a Pandemic - The COVID-19-20 Lung CT Lesion Segmentation Challenge (preprint)

Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge - 2020.

The interplay of policy, institutions, and culture in the time of COVID-19

This paper examines cross-country evidence of how the Covid-19 pandemic spread and the mortality rates associated with preexisting vulnerabilities, the government's mobility restriction policy, institutions (democracy), and culture (individualistic culture and trust). Preexisting vulnerabilities (that is, the share of the elderly, urbanization, obesity prevalence, and air pollution) increase the spread of the pandemic and/or the mortality rate. On average, the government policy delay in mobility restriction, democracy, and culture indicators are not significantly associated with the pandemic outcomes. However, government delay in restricting mobility drastically amplifies the positive association between preexisting vulnerabilities and pandemic mortality. Individualistic culture and general trust amplify the positive links between pandemic mortality and the share of elderly people or urbanization. The analysis shows that in modeling the pandemic outcomes, it is important to consider cross-country spatial interactions.

Heterogeneous Shareholders’ Participation, COVID-19 Impact, and Innovation Decisions of State-Owned Firms: Evidence from China

Innovation ability has become an important factor affecting the global competitiveness and sustainable development of state-owned enterprises (SOEs) in China, particularly during the COVID-19 period. This study examined the association between heterogeneous shareholders and SOE innovation, in addition to the moderating impact of corporate governance characteristics and the COVID-19 pandemic on this association. Using data from Chinese A-share listed mixed ownership enterprises (MOEs), we found that the mixed ownership reform of SOEs positively affected firm innovation compared to other MOEs by reducing agency costs, indicating that the manager view channel was proven. We also found that heterogeneous shareholders resulted in more innovation output in state-owned holding mixed ownership enterprises (SHMOEs) with affiliated managers, in those audited by lower reputation accounting firms or that had a lower external marketization, or during the COVID-19 period. The implications of this study are of importance for improving heterogeneous shareholders’ active participation in the mixed ownership reform of SOEs.

Federated Learning used for predicting outcomes in SARS-COV-2 patients (preprint)

‘Federated Learning’ (FL) is a method to train Artificial Intelligence (AI) models with data from multiple sources while maintaining anonymity of the data thus removing many barriers to data sharing. During the SARS-COV-2 pandemic, 20 institutes collaborated on a healthcare FL study to predict future oxygen requirements of infected patients using inputs of vital signs, laboratory data, and chest x-rays, constituting the “EXAM” (EMR CXR AI Model) model. EXAM achieved an average Area Under the Curve (AUC) of over 0.92, an average improvement of 16%, and a 38% increase in generalisability over local models. The FL paradigm was successfully applied to facilitate a rapid data science collaboration without data exchange, resulting in a model that generalised across heterogeneous, unharmonized datasets. This provided the broader healthcare community with a validated model to respond to COVID-19 challenges, as well as set the stage for broader use of FL in healthcare.

Federated Semi-Supervised Learning for COVID Region Segmentation in Chest CT using Multi-National Data from China, Italy, Japan (preprint)

The recent outbreak of COVID-19 has led to urgent needs for reliable diagnosis and management of SARS-CoV-2 infection. As a complimentary tool, chest CT has been shown to be able to reveal visual patterns characteristic for COVID-19, which has definite value at several stages during the disease course. To facilitate CT analysis, recent efforts have focused on computer-aided characterization and diagnosis, which has shown promising results. However, domain shift of data across clinical data centers poses a serious challenge when deploying learning-based models. In this work, we attempt to find a solution for this challenge via federated and semi-supervised learning. A multi-national database consisting of 1704 scans from three countries is adopted to study the performance gap, when training a model with one dataset and applying it to another. Expert radiologists manually delineated 945 scans for COVID-19 findings. In handling the variability in both the data and annotations, a novel federated semi-supervised learning technique is proposed to fully utilize all available data (with or without annotations). Federated learning avoids the need for sensitive data-sharing, which makes it favorable for institutions and nations with strict regulatory policy on data privacy. Moreover, semi-supervision potentially reduces the annotation burden under a distributed setting. The proposed framework is shown to be effective compared to fully supervised scenarios with conventional data sharing instead of model weight sharing.