Dual attention fusion UNet for COVID-19 lesion segmentation from CT images.

BACKGROUND: Chest CT scan is an effective way to detect and diagnose COVID-19 infection. However, features of COVID-19 infection in chest CT images are very complex and heterogeneous, which make segmentation of COVID-19 lesions from CT images quite challenging. OBJECTIVE: To overcome this challenge, this study proposes and tests an end-to-end deep learning method called dual attention fusion UNet (DAF-UNet). METHODS: The proposed DAF-UNet improves the typical UNet into an advanced architecture. The dense-connected convolution is adopted to replace the convolution operation. The mixture of average-pooling and max-pooling acts as the down-sampling in the encoder. Bridge-connected layers, including convolution, batch normalization, and leaky rectified linear unit (leaky ReLU) activation, serve as the skip connections between the encoder and decoder to bridge the semantic gap differences. A multiscale pyramid pooling module acts as the bottleneck to fit the features of COVID-19 lesion with complexity. Furthermore, dual attention feature (DAF) fusion containing channel and position attentions followed the improved UNet to learn the long-dependency contextual features of COVID-19 and further enhance the capacity of the proposed DAF-UNet. The proposed model is first pre-trained on the pseudo label dataset (generated by Inf-Net) containing many samples, then fine-tuned on the standard annotation dataset (provided by the Italian Society of Medical and Interventional Radiology) with high-quality but limited samples to improve performance of COVID-19 lesion segmentation on chest CT images. RESULTS: The Dice coefficient and Sensitivity are 0.778 and 0.798 respectively. The proposed DAF-UNet has higher scores than the popular models (Att-UNet, Dense-UNet, Inf-Net, COPLE-Net) tested using the same dataset as our model. CONCLUSION: The study demonstrates that the proposed DAF-UNet achieves superior performance for precisely segmenting COVID-19 lesions from chest CT scans compared with the state-of-the-art approaches. Thus, the DAF-UNet has promising potential for assisting COVID-19 disease screening and detection.

Trait anxiety affects attentional bias to emotional stimuli across time: A growth curve analysis.

Many studies have illustrated the close relationship between anxiety disorders and attentional functioning, but the relationship between trait anxiety and attentional bias remains controversial. This study examines the effect of trait anxiety on the time course of attention to emotional stimuli using materials from the International Affective Picture System. Participants with high vs. low trait anxiety (HTA vs. LTA) viewed four categories of pictures simultaneously: dysphoric, threatening, positive, and neutral. Their eye-movements for each emotional stimulus were recorded for static and dynamic analysis. Data were analyzed using a mixed linear model and growth curve analysis. Specifically, the HTA group showed a greater tendency to avoid threatening stimuli and more pupil diameter variation in the early period of stimulus presentation (0-7.9 s). The HTA group also showed a stronger attentional bias toward positive and dysphoric stimuli in the middle and late period of stimulus presentation (7.9-30 s). These results suggest that trait anxiety has a significant temporal effect on attention to emotional stimuli, and that this effect mainly manifests after 7 s. In finding stronger attentional avoidance of threatening stimuli and more changes in neural activity, as well as a stronger attentional bias toward positive stimuli, this study provides novel insights on the relationship between trait anxiety and selective attention.

Mortality burden due to long-term exposure to ambient PM2.5 above the new WHO air quality guideline based on 296 cities in China.

OBJECTIVE: Quantifying the spatial and socioeconomic variation of mortality burden attributable to particulate matters with aerodynamic diameter ≤ 2.5 µm (PM2.5) has important implications for pollution control policy. This study aims to examine the regional and socioeconomic disparities in the mortality burden attributable to long-term exposure to ambient PM2.5 in China. METHODS: Using data of 296 cities across China from 2015 to 2019, we estimated all-cause mortality (people aged ≥ 16 years) attributable to the long-term exposure to ambient PM2.5 above the new WHO air quality guideline (5 µg/m3). Attributed fraction (AF), attributed deaths (AD), attributed mortality rate (AMR) and total value of statistical life lost (VSL) by regional and socioeconomic levels were reported. RESULTS: Over the period of 2015-2019, 17.0% [95% confidence interval (CI): 7.4-25.2] of all-cause mortality were attributable to long-term exposure to ambient PM2.5, corresponding to 1,425.2 thousand deaths (95% CI: 622.4-2,099.6), 103.5/105 (95% CI: 44.9-153.3) AMR, and 1006.9 billion USD (95% CI: 439.8-1483.4) total VSL per year. The AMR decreased from 120.5/105 (95% CI: 52.9-176.6) to 92.7/105 (95% CI:39.9-138.5) from 2015 to 2019. The highest mortality burden was observed in the north region (annual average AF = 24.2%, 95% CI: 10.8-35.1; annual average AMR = 137.0/105, 95% CI: 60.9-198.5). The highest AD and economic loss were observed in the east region (annual average AD = 390.0 thousand persons, 95% CI: 170.3-574.6; annual total VSL = 275.6 billion USD, 95% CI: 120.3-406.0). Highest AMR was in the cities with middle level of GDP per capita (PGDP)/urbanization. The majority of the top ten cities of AF, AMR and VSL were in high and middle PGDP/urbanization regions. CONCLUSION: There were significant regional and socioeconomic disparities in PM2.5 attributed mortality burden among Chinese cities, suggesting differential mitigation policies are required for different regions in China.

Could the ambient higher temperature decrease the transmissibility of COVID-19 in China?

BACKGROUND: Existing literatures demonstrated that meteorological factors could be of importance in affecting the spread patterns of the respiratory infectious diseases. However, how ambient temperature may influence the transmissibility of COVID-19 remains unclear. OBJECTIVES: We explore the association between ambient temperature and transmissibility of COVID-19 in different regions across China. METHODS: The surveillance data on COVID-19 and meteorological factors were collected from 28 provincial level regions in China, and estimated the instantaneous reproductive number (Rt). The generalized additive model was used to assess the relationship between mean temperature and Rt. RESULTS: There were 12,745 COVID-19 cases collected in the study areas. We report the associated effect of temperature on Rt is likely to be negative but not of statistical significance, which holds for most Chinese regions. CONCLUSIONS: We found little statistical evidence for that the higher temperature may reduce the transmissibility of COVID-19. Since intensive control measures against the COVID-19 epidemics were implemented in China, we acknowledge this may impact the underlying effect size estimation, and thus cautiousness should be taken when interpreting our findings.