AIGAN: Attention-encoding Integrated Generative Adversarial Network for the reconstruction of low-dose CT and low-dose PET images.

X-ray computed tomography (CT) and positron emission tomography (PET) are two of the most commonly used medical imaging technologies for the evaluation of many diseases. Full-dose imaging for CT and PET ensures the image quality but usually raises concerns about the potential health risks of radiation exposure. The contradiction between reducing the radiation exposure and remaining diagnostic performance can be addressed effectively by reconstructing the low-dose CT (L-CT) and low-dose PET (L-PET) images to the same high-quality ones as full-dose (F-CT and F-PET). In this paper, we propose an Attention-encoding Integrated Generative Adversarial Network (AIGAN) to achieve efficient and universal full-dose reconstruction for L-CT and L-PET images. AIGAN consists of three modules: the cascade generator, the dual-scale discriminator and the multi-scale spatial fusion module (MSFM). A sequence of consecutive L-CT (L-PET) slices is first fed into the cascade generator that integrates with a generation-encoding-generation pipeline. The generator plays the zero-sum game with the dual-scale discriminator for two stages: the coarse and fine stages. In both stages, the generator generates the estimated F-CT (F-PET) images as like the original F-CT (F-PET) images as possible. After the fine stage, the estimated fine full-dose images are then fed into the MSFM, which fully explores the inter- and intra-slice structural information, to output the final generated full-dose images. Experimental results show that the proposed AIGAN achieves the state-of-the-art performances on commonly used metrics and satisfies the reconstruction needs for clinical standards.

Influence of Online Learning Environment and Student Engagement on International Students' Sustainable Chinese Learning

The outbreak of COVID-19 has forced Chinese international education to move online. An emerging number of studies have been published on online teaching and learning during the pandemic, few of which, however, focus on international students in China. This study examined the predictive effects of an online learning environment and student engagement on international students' learning of Chinese as a foreign language (CFL). Self-reported data were collected in an online questionnaire survey involving 447 international CFL students at eight universities located in different geographical regions in China. Descriptive statistics revealed the participants' favorable perceptions of an online learning environment, student engagement and Chinese learning achievement. The results of multiple linear regression revealed that three online learning environment factors, i.e., course accessibility, student interaction, course organization, and student engagement exerted significant positive effects on Chinese learning achievement. The implications of the study are discussed for the sustainable enhancement of the online learning environment to improve international students' online language learning.

Influences of Online Learning Environment on International Students' Intrinsic Motivation and Engagement in the Chinese Learning

With the impact of the COVID-19 pandemic, Chinese teaching for international students in Chinese universities has largely moved online. Despite the comprehensive literature regarding the influences of environmental factors on domestic students' learning in traditional learning environment, few studies have addressed the influences of online learning environment (OLE) on international students' Chinese learning experiences. We focus on international students in intensive Chinese courses at a Chinese university, and explores the influences of OLE on these students' intrinsic motivation (IM) towards and engagement in Chinese learning during the COVID-19 pandemic. Data were collected from an online questionnaire survey and follow-up interviews. The results revealed that the participants had positive perceptions of the online Chinese learning environment, and that the participants had high levels of IM towards and engagement in their Chinese learning. The results also showed the positive impact of the participants' perceived OLE on their IM towards and engagement in Chinese learning. The research, though with several limitations, has implications for teachers teaching Chinese as a foreign language and institutions promoting international students' IM and SE in online teaching contexts.

Teaching, Learning, and Management: International Student in China During the COVID-19 Pandemic

The COVID-19 pandemic presents unprecedented challenges to the management, teaching, and learning in Chinese international education. This special issue focuses on national policies on international student education, institutional riskmanagement strategies, quality assurance practices, online teaching pedagogy, international student engagement, and factors affecting their satisfaction. We hope that the discussions in this special issue will allow us to share the lessons that we have learned during this crisis, promote international cooperation to cope with common challenges, and support the sustainable development and transformation of international education in China and worldwide in the post-COVID era.

Online learning satisfaction and its associated factors among international students in China

The outbreak of the COVID-19 pandemic has caused a substantial transition of Chinese international education to online learning. This article discusses the impact of online learning from international students’ perspectives. Data were collected from exploratory interviews with a small group of international students at a research university and a nationwide survey involving 1,010 international students at 41 universities in China. A synthesis of the two studies’ findings pointed to low levels of online learning satisfaction, particularly among international students from Africa, those in undergraduate programs, those in life sciences and medical disciplines, and those studying at research-centered universities. Moreover, both studies revealed low emotional engagement significantly predicted international students’ online learning dissatisfaction. To enhance international students’ satisfaction, it is suggested that universities and teachers prioritize the building of student-centered online learning environments supporting international students’ emotional involvement and helping them feel a greater sense of belonging in online intercultural learning.

RCoNet: Deformable Mutual Information Maximization and High-Order Uncertainty-Aware Learning for Robust COVID-19 Detection.

The novel 2019 Coronavirus (COVID-19) infection has spread worldwide and is currently a major healthcare challenge around the world. Chest computed tomography (CT) and X-ray images have been well recognized to be two effective techniques for clinical COVID-19 disease diagnoses. Due to faster imaging time and considerably lower cost than CT, detecting COVID-19 in chest X-ray (CXR) images is preferred for efficient diagnosis, assessment, and treatment. However, considering the similarity between COVID-19 and pneumonia, CXR samples with deep features distributed near category boundaries are easily misclassified by the hyperplanes learned from limited training data. Moreover, most existing approaches for COVID-19 detection focus on the accuracy of prediction and overlook uncertainty estimation, which is particularly important when dealing with noisy datasets. To alleviate these concerns, we propose a novel deep network named RCoNet ks for robust COVID-19 detection which employs Deformable Mutual Information Maximization (DeIM), Mixed High-order Moment Feature (MHMF), and Multiexpert Uncertainty-aware Learning (MUL). With DeIM, the mutual information (MI) between input data and the corresponding latent representations can be well estimated and maximized to capture compact and disentangled representational characteristics. Meanwhile, MHMF can fully explore the benefits of using high-order statistics and extract discriminative features of complex distributions in medical imaging. Finally, MUL creates multiple parallel dropout networks for each CXR image to evaluate uncertainty and thus prevent performance degradation caused by the noise in the data. The experimental results show that RCoNet ks achieves the state-of-the-art performance on an open-source COVIDx dataset of 15 134 original CXR images across several metrics. Crucially, our method is shown to be more effective than existing methods with the presence of noise in the data.

Positron emission tomography in the COVID-19 pandemic era.

Coronavirus disease 2019 (COVID-19) has become a major public health problem worldwide since its outbreak in 2019. Currently, the spread of COVID-19 is far from over, and various complications have roused increasing awareness of the public, calling for novel techniques to aid at diagnosis and treatment. Based on the principle of molecular imaging, positron emission tomography (PET) is expected to offer pathophysiological alternations of COVID-19 in the molecular/cellular perspectives and facilitate the clinical management of patients. A number of PET-related cases and research have been reported on COVID-19 over the past one year. This article reviews the current studies of PET in the diagnosis and treatment of COVID-19, and discusses potential applications of PET in the development of management strategy for COVID-19 patients in the pandemic era.

The Pathways from Type A Personality to Physical and Mental Health Amid COVID-19: A Multiple-Group Path Model of Frontline Anti-Epidemic Medical Staff and Ordinary People.

During the COVID-19 pandemic, a survey was conducted using the questionnaire method among participants consisting of both ordinary people (n = 325) and frontline anti-epidemic medical staff (n = 310), and physiological data was obtained on the basis of physical examination. This study aimed to scrutinize the influence of Type A personality on the biochemical indicators of aspartate aminotransferase (AST) and the behavioral indicators of appetite and sleep disorder, and to analyze the mediating effect of depression. Meanwhile, multiple-group path analysis was used to evaluate path differences between the models of two samples. The results of the mediation analysis for both samples demonstrated that depression significantly mediated the relationship between Type A personality and appetite and sleep disorder. The results of multiple-group path analysis showed that the relationship between Type A personality and appetite and sleep disorder seems to be significantly stronger in ordinary people, whereas the relationship between depression and appetite and sleep disorder, as well as with the path towards AST, seems to be significantly stronger in frontline anti-epidemic medical staff. This paper provides ideas for the selection and distribution of medical personnel based on personality characteristics in major public health emergencies, and physical and mental health status should be taken into account to provide relative health assistance.

Mental health outcomes among patients from Fangcang shelter hospitals exposed to coronavirus disease 2019: An observational cross-sectional study.

BACKGROUND: The coronavirus disease 2019 (COVID-19) is not only attacking physical health, but it is also increasing psychological suffering. This study aimed to observe the impact of the COVID-19 pandemic on mental health outcomes among patients with mild to moderate illness in Fangcang shelter hospitals. METHODS: We conducted an observational, cross-sectional study of 129 patients with mild to moderate illness from Jiangxia Fangcang shelter hospitals in Wuhan, China. The participants were assessed by quantifying their symptoms of depression, anxiety, insomnia, and stressful life events and analyzing potential risk factors associated with these symptoms. Using correlation analysis, we examined associations between exposure to COVID-19 and subsequent psychological distress in response to the outbreak. RESULTS: In total, 49.6% of participants had depressive or anxiety symptoms. The depressive and anxiety symptoms were highly related to sleep disturbances and hypochondriasis (all r > 0.50, P < 0.01). The impact of the event was positively related to depressive symptoms, anxiety symptoms, sleep disturbances, hypochondriasis and life events (all r > 0.35, P < 0.01) but was negatively related to psychological resilience (r = -0.41, P < 0.01). The presence of the COVID-19 infection in this setting was associated with increased anxiety, depression and stress levels, and decreased sleep quality, and seriously affected patients' quality of life as well as adversely affecting the course and prognosis of physical diseases. CONCLUSION: The sleep quality, anxiety, and depression of COVID-19 patients in Fangcang shelter hospitals were significantly related to the impact of the epidemic.

Post-COVID-19 Epidemic: Allostatic Load among Medical and Nonmedical Workers in China.

BACKGROUND: As the fight against the COVID-19 epidemic continues, medical workers may have allostatic load. OBJECTIVE: During the reopening of society, medical and nonmedical workers were compared in terms of allostatic load. METHODS: An online study was performed; 3,590 Chinese subjects were analyzed. Socio-demographic variables, allostatic load, stress, abnormal illness behavior, global well-being, mental status, and social support were assessed. RESULTS: There was no difference in allostatic load in medical workers compared to nonmedical workers (15.8 vs. 17.8%; p = 0.22). Multivariate conditional logistic regression revealed that anxiety (OR = 1.24; 95% CI 1.18-1.31; p < 0.01), depression (OR = 1.23; 95% CI 1.17-1.29; p < 0.01), somatization (OR = 1.20; 95% CI 1.14-1.25; p < 0.01), hostility (OR = 1.24; 95% CI 1.18-1.30; p < 0.01), and abnormal illness behavior (OR = 1.49; 95% CI 1.34-1.66; p < 0.01) were positively associated with allostatic load, while objective support (OR = 0.84; 95% CI 0.78-0.89; p < 0.01), subjective support (OR = 0.84; 95% CI 0.80-0.88; p < 0.01), utilization of support (OR = 0.80; 95% CI 0.72-0.88; p < 0.01), social support (OR = 0.90; 95% CI 0.87-0.93; p < 0.01), and global well-being (OR = 0.30; 95% CI 0.22-0.41; p < 0.01) were negatively associated. CONCLUSIONS: In the post-COVID-19 epidemic time, medical and nonmedical workers had similar allostatic load. Psychological distress and abnormal illness behavior were risk factors for it, while social support could relieve it.