SSA-Net: Spatial self-attention network for COVID-19 pneumonia infection segmentation with semi-supervised few-shot learning.

Coronavirus disease (COVID-19) broke out at the end of 2019, and has resulted in an ongoing global pandemic. Segmentation of pneumonia infections from chest computed tomography (CT) scans of COVID-19 patients is significant for accurate diagnosis and quantitative analysis. Deep learning-based methods can be developed for automatic segmentation and offer a great potential to strengthen timely quarantine and medical treatment. Unfortunately, due to the urgent nature of the COVID-19 pandemic, a systematic collection of CT data sets for deep neural network training is quite difficult, especially high-quality annotations of multi-category infections are limited. In addition, it is still a challenge to segment the infected areas from CT slices because of the irregular shapes and fuzzy boundaries. To solve these issues, we propose a novel COVID-19 pneumonia lesion segmentation network, called Spatial Self-Attention network (SSA-Net), to identify infected regions from chest CT images automatically. In our SSA-Net, a self-attention mechanism is utilized to expand the receptive field and enhance the representation learning by distilling useful contextual information from deeper layers without extra training time, and spatial convolution is introduced to strengthen the network and accelerate the training convergence. Furthermore, to alleviate the insufficiency of labeled multi-class data and the long-tailed distribution of training data, we present a semi-supervised few-shot iterative segmentation framework based on re-weighting the loss and selecting prediction values with high confidence, which can accurately classify different kinds of infections with a small number of labeled image data. Experimental results show that SSA-Net outperforms state-of-the-art medical image segmentation networks and provides clinically interpretable saliency maps, which are useful for COVID-19 diagnosis and patient triage. Meanwhile, our semi-supervised iterative segmentation model can improve the learning ability in small and unbalanced training set and can achieve higher performance.

Perceived psychological stress and associated factors in the early stages of the coronavirus disease 2019 (COVID-19) epidemic: Evidence from the general Chinese population.

INTRODUCTION: Coronavirus disease 2019 (COVID-19) is an acute respiratory infection caused by novel coronavirus 2019. Many individuals suffered psychological symptoms in the early stage when the epidemic was uncertain. We explored the perceived psychological stress and associated factors in the early stage of COVID-19 epidemic. METHOD: The Perceived Stress Scale, Simplified Coping Style Questionnaire, Social Support Rating Scale and a general information questionnaire were integrated in an on-line survey conducted from February 1, 2020 until February 4, 2020. Multiple linear regression analysis was performed to explore whether coping style, social support or other factors contributed to psychological stress. RESULTS: A total of 1638 participants were included, of whom 44.3% showed moderate psychological stress. Individuals who were younger, female, unmarried, spent more time on the disease, felt more concern about it, reported lower social support (Subjective Social support; Objective social support; Utilization social support), or showed a negative coping style were more likely to suffer higher psychological stress in the early stages of the COVID-19 epidemic. CONCLUSION: Psychological interventions may be targeted to individuals with the risk characteristics identified in this study. It may be helpful to promote social support and positive coping style in the early stage of infectious disease epidemics. This initial evidence from the general Chinese population may be relevant to interventions in other countries for dealing with the COVID-19 and other epidemics.

Coping style, social support and psychological distress in the general Chinese population in the early stages of the COVID-19 epidemic.

BACKGROUND: The purpose of this study was to investigate the psychological status of the general population in mainland China during the outbreak of coronavirus disease 2019 (COVID-19), and to explore the factors influencing psychological distress, in order to provide the basis for further psychological intervention programs. METHODS: We administered three questionnaires on-line to a convenience sample of the general population from different regions of mainland China from February 1 to February 4, 2020. We used the Mandarin versions of the six-item Kessler psychological distress scale (K6), the Simplified Coping Style Questionnaire (SCSQ), and the Social Support Rating Scale (SSRS). We also collected demographic data and other information related to the COVID-19 outbreak. Multivariate binary logistic regression analysis was used to identify factors influencing psychological distress. RESULTS: Of 1607 respondents, 1588 returned valid questionnaires and were included in the analysis. Nearly one quarter (22.8%) had high levels of psychological distress (K6 score ≥ 13). Individuals with higher psychological distress were more likely to be unmarried, spend more than 6 h per day searching for information about COVID-19, more frequently adopt a passive coping style, and report less social support than those with lower psychological distress. CONCLUSIONS: The COVID-19 outbreak in China has a great impact on the mental health status of the general population. Active coping strategies and increased social support are significantly correlated with decreased psychological distress, and may serve as the basis for psychological interventions.

The mental state and risk factors of Chinese medical staff and medical students in early stages of the COVID-19 epidemic.

OBJECTIVE: This study aimed to investigate the mental state of medical staff and medical students in the early stages of the SARS-CoV-2 outbreak, as well as analyze the risk factors of serious mental illness (SMI), so as to provide a scientific basis for further psychological intervention and management. METHOD: A cross-sectional survey was conducted from February 2-7, 2020. The Kessler 6 Psychological Distress Scale and a general information questionnaire were administered on-line to a convenience sample of 548 medical staff and medical students in China. Multivariate binary logistic regression analysis was used to screen the risk factors of SMI in medical staff and medical students. RESULTS: Of the 505 respondents in the final analysis, 188 (37.23%) were at high risk of SMI. Respondents were at significantly higher risk of SMI if they had been suspected of being infected with the SARS-CoV-2 (OR = 7.00, 95% CI: 1.19-41.14), had relatives suspected of being infected with the SARS-CoV-2 (OR = 23.60, 95% CI: 1.11-501.30), felt concerned towards media coverage of outbreak-related information (OR = 11.95, 95% CI: 3.07-46.57), recently dreamed related to SARS-CoV-2 (OR = 4.21, 95% CI: 2.22-8.01), experienced difficulty in controlling emotions during SARS-CoV-2 epidemic (OR = 3.25, 95% CI: 1.66-6.37), or spent hours watching outbreaks per day (OR = 1.29, 95% CI: 1.13-1.46). CONCLUSION: Our findings highlight that medical staff and medical students were vulnerable to SMI during the early stages of the SARS-CoV-2 outbreak and identify the factors associated with SMI which can be used to formulate psychological interventions to improve the mental health. The independent risk factors for SMI among them are suspicion that they or relatives were infected with the SARS-CoV-2, greater interest in media reports about the epidemic, frequency of recent dreams related to SARS-CoV-2, difficulty in controlling emotions during the epidemic, and hours spent watching outbreaks per day.