A Light Deep Learning Algorithm for CT Diagnosis of COVID-19 Pneumonia.

A large number of reports present artificial intelligence (AI) algorithms, which support pneumonia detection caused by COVID-19 from chest CT (computed tomography) scans. Only a few studies provided access to the source code, which limits the analysis of the out-of-distribution generalization ability. This study presents Cimatec-CovNet-19, a new light 3D convolutional neural network inspired by the VGG16 architecture that supports COVID-19 identification from chest CT scans. We trained the algorithm with a dataset of 3000 CT Scans (1500 COVID-19-positive) with images from different parts of the world, enhanced with 3000 images obtained with data augmentation techniques. We introduced a novel pre-processing approach to perform a slice-wise selection based solely on the lung CT masks and an empirically chosen threshold for the very first slice. It required only 16 slices from a CT examination to identify COVID-19. The model achieved a recall of 0.88, specificity of 0.88, ROC-AUC of 0.95, PR-AUC of 0.95, and F1-score of 0.88 on a test set with 414 samples (207 COVID-19). These results support Cimatec-CovNet-19 as a good and light screening tool for COVID-19 patients. The whole code is freely available for the scientific community.

Exposure and dose assessment of school children to air pollutants in a tropical coastal-urban area.

This study estimates exposure and inhaled dose to air pollutants of children residing in a tropical coastal-urban area in Southeast Brazil. For that, twenty-one children filled their time-activities diaries and wore the passive samplers to monitor NO2. The personal exposure was also estimated using data provided by the combination of WRF-Urban/GEOS-Chem/CMAQ models, and the nearby monitoring station. Indoor/outdoor ratios were used to consider the amount of time spent indoors by children in homes and schools. The model's performance was assessed by comparing the modelled data with concentrations measured by urban monitoring stations. A sensitivity analyses was also performed to evaluate the impact of the model's height on the air pollutant concentrations. The results showed that the mean children's personal exposure to NO2 predicted by the model (22.3 µg/m3) was nearly twice to those measured by the passive samplers (12.3 µg/m3). In contrast, the nearest urban monitoring station did not represent the personal exposure to NO2 (9.3 µg/m3), suggesting a bias in the quantification of previous epidemiological studies. The building effect parameterisation (BEP) together with the lowering of the model height enhanced the air pollutant concentrations and the exposure of children to air pollutants. With the use of the CMAQ model, exposure to O3, PM10, PM2.5, and PM1 was also estimated and revealed that the daily children's personal exposure was 13.4, 38.9, 32.9, and 9.6 µg/m3, respectively. Meanwhile, the potential inhalation daily dose was 570-667 µg for PM2.5, 684-789 µg for PM10, and 163-194 µg for PM1, showing to be favourable to cause adverse health effects. The exposure of children to air pollutants estimated by the numerical model in this work was comparable to other studies found in the literature, showing one of the advantages of using the modelling approach since some air pollutants are poorly spatially represented and/or are not routinely monitored by environmental agencies in many regions.

WRF-SMOKE-CMAQ modeling system for air quality evaluation in São Paulo megacity with a 2008 experimental campaign data.

Atmospheric pollutants are strongly affected by transport processes and chemical transformations that alter their composition and the level of contamination in a region. In the last decade, several studies have employed numerical modeling to analyze atmospheric pollutants. The objective of this study is to evaluate the performance of the WRF-SMOKE-CMAQ modeling system to represent meteorological and air quality conditions over São Paulo, Brazil, where vehicular emissions are the primary contributors to air pollution. Meteorological fields were modeled using the Weather Research and Forecasting model (WRF), for a 12-day period during the winter of 2008 (Aug. 10th-Aug. 22nd), using three nested domains with 27-km, 9-km, and 3-km grid resolutions, which covered the most polluted cities in São Paulo state. The 3-km domain was aligned with the Sparse Matrix Operator Kernel Emissions (SMOKE), which processes the emission inventory for the Models-3 Community Multiscale Air Quality Modeling System (CMAQ). Data from an aerosol sampling campaign was used to evaluate the modeling. The PM10 and ozone average concentration of the entire period was well represented, with correlation coefficients for PM10, varying from 0.09 in Pinheiros to 0.69 in ICB/USP, while for ozone, the correlation coefficients varied from 0.56 in Pinheiros to 0.67 in IPEN. However, the model underestimated the concentrations of PM2.5 during the experiment, but with ammonium showing small differences between predicted and observed concentrations. As the meteorological model WRF underestimated the rainfall and overestimated the wind speed, the accuracy of the air quality model was expected to be below the desired value. However, in general, the CMAQ model reproduced the behavior of atmospheric aerosol and ozone in the urban area of São Paulo.