Value of Radiomics Features From Adrenal Gland and Periadrenal Fat in CT Images for Predicting COVID-19 Prognosis (preprint)

Background: Endocrine system plays an important role in infectious disease prognosis. Our goal is to assess the value of radiomics features extracted from adrenal gland and periadrenal fat CT images in predicting disease prognosis in patients with COVID-19. Methods: : A total of 1,325 patients (765 moderate and 560 severe patients) from three centers were enrolled in the retrospective study. We proposed a 3D cascade V-Net to automatically segment adrenal glands in onset CT images. Periadrenal fat areas were obtained using inflation operations. Then, the radiomics features were automatically extracted. Five models were established to predict the disease prognosis in patients with COVID-19: a clinical model (CM), three radiomics models (adrenal gland model [AM], periadrenal fat model [PM], fusion of adrenal gland and periadrenal fat model [FM]), and a radiomics nomogram model (RN).Data from one center (1,183 patients) were utilized as training and validation sets. The remaining two (36 and 106 patients) were used as 2 independent test sets to evaluate the models’ performance. Results: : The auto-segmentation framework achieved an average dice of 0.79 in the test set. CM, AM, PM, FM, and RN obtained AUCs of 0.716, 0.755, 0.796, 0.828, and 0.825, respectively in the training set, and the mean AUCs of 0.754, 0.709, 0.672, 0.706 and 0.778 for 2 independent test sets. Decision curve analysis showed that if the threshold probability was more than 0.3, 0.5, and 0.1 in the validation set, the independent-test set 1 and the independent-test set 2 could gain more net benefits using RN than FM and CM, respectively. Conclusion: Radiomics features extracted from CT images of adrenal glands and periadrenal fat are related to disease prognosis in patients with COVID-19 and have great potential for predicting its severity.

A Radiomics Based Approach Using Adrenal Gland and Periadrenal Fat CT Images to Fairly Allocate COVID-19 Health Care Resources (preprint)

Background: COVID-19 disease severity is associated with endocrine system. We hypothesis radiomics features from the adrenal gland and periadrenal fat CT images can assess possibilities of disease exacerbation.Methods: A total of 1,245 patients (685 moderate and 560 severe patients) were enrolled in a retrospective study. We proposed 3D V-Net to segment adrenal glands in onset CT images automatically, and periadrenal fat was obtained using inflation operation around the adrenal gland. Next, we built a clinical model (CM), three radiomics models (adrenal gland model [AM], periadrenal fat model [PM], and fusion of adrenal gland and periadrenal fat model [FM]), and radiomics nomogram (RN) after radiomics features extracted.Findings: The auto-segmentation framework yielded a dice value of 0.79 in the training set. CM, AM, PM, FM, and RN obtained AUCs of 0.717, 0.716, 0.736, 0.760, and 0.833, respectively in the validation set. FM and RN had better predictive efficacy than CM (P < 0.0001) in the training set. RN showed that there was no significant difference in the validation set (mean absolute error [MAE] = 0.04) and test set (MAE = 0.075) between predictive and actual results. Decision curve analysis showed that if the threshold probability was more than 0.3 in the validation set or between 0.4 and 0.8 in the test set, it could gain more net benefits using RN than FM and CM.Interpretation: Radiomics features extracted from adrenal gland and periadrenal fat CT images are related to disease exacerbation in patients with COVID-19.Funding Information: The study was supported by the Non-profit Central Research Institute Fund of Chinese Academy of Medical Sciences (2019PT320003）; The Science and Technology Foundation of Guizhou Province (QKHPTRC[2019]5803); The Guiyang Science and Technology Project (ZKXM[2020]4); Beijing Medical and Health Foundation (YWJKJJHKYJJ-B20261CS) and Chongqing Science and Health Joint Medical Research Project (2021MSXM052).Declaration of Interests: The authors have declared that no conflict of interest exists.Ethics Approval Statement: This multicenter study was approved by the ethics committees of all participating hospitals (2020,NO.01). Because of its retrospective nature, the need to obtain informed consent in advance was waived. The study was performed according to the principles of the declaration of Helsinki.

[Response of Air Quality to COVID-19 Lockdown in Xiamen Bay].

Air pollutant concentrations in the Xiamen Bay cities during the period before and after COVID-19 lockdown(from January 11 to February 21, 2020) were studied to determine the influence of human activities on air quality in this region. During the Chinese Spring Festival holiday and the lockdown period, the concentrations of SO2, NO2, CO, PM10, and PM2.5 decreased by 6%-22%, 53%-70%, 34%-48%, 47%-64%, and 53%-60%, respectively. However, the changes in O3 concentrations were not consistent with the variations of human activities. The reduction rates for PM2.5, PM10, CO, and NO2 during the Spring Festival were greater than in previous years(2018 and 2019), but the reduction rates for SO2 were comparable. The concentrations of NO2 increased sharply(38%-138%), and much higher those of SO2(2%-42%), after the resumption of socioeconomic activities, indicating the importance of traffic reductions due to the lockdown measures on NO2. Higher wind speeds and rainfall after the Spring Festival were also favorable for the decline of SO2, NO2, and PM. The spatio-temporal distributions of the six criterial pollutants in the Xiamen Bay city cluster were obtained based on the Inverse Distance Weight method. The variability in regions with high NO2 concentrations was strongly linked to traffic emissions, while spatial patterns for CO and SO2 changed little over the six-week study period. The concentrations of PM2.5 and PM10 increased notably in the region, linked to more construction activity, but changed comparatively little in regions with dense populations and traffic networks. O3 remained relatively stable but low-value regions corresponded to those regions with high NO2 concentrations, indicating the significant titration effect of NO2 on O3. These results provide valuable information that can inform O3 pollution reduction measures.

Computing Infection Distributions and Longitudinal Evolution Patterns in Lung CT Images (preprint)

Background: Spatial and temporal lung infection distributions of coronavirus disease 2019 (COVID-19) and their changes could reveal important patterns to better understand the disease and its time course. This paper presents a pipeline to analyze statistically these patterns by automatically segmenting the infection regions and registering them onto a common template. Methods: : A VB-Net is designed to automatically segment infection regions in CT images. After training and validating the model, we segmented all the CT images in the study. The segmentation results are then warped onto a pre-defined template CT image using deformable registration based on registering CT images within the lung fields. Then, the spatial distributions of infection regions and those during the course of the disease are calculated at the voxel level. Visualization and quantitative comparison can be performed between different groups. As a result, we compared the distribution maps between COVID-19 and community acquired pneumonia (CAP), between severe and critical COVID-19, and across different course of the disease. Results: : For the performance of infection segmentation, comparing the segmentation results with manually annotated ground truth, the average Dice is 91.6%±10.0%, which is close to the inter-rater difference between two radiologists (the Dice is 96.1%±3.5%). The distribution map of infection regions shows that high probability regions are in the peripheral subpleural (up to 35.1% in probability). COVID-19 GGO lesions are more widely spread than consolidations, and the latter are located more peripherally. Onset images of severe COVID-19 (inpatients) show similar lesion distributions but with smaller areas of significant difference in the right lower lobe compared to critical COVID-19 (intensive care unit patients). About the disease course, critical COVID-19 patients showed four distinct patterns (progression, absorption, enlargement, and further absorption) with remarkable concurrent HU patterns for GGO and consolidations. Conclusions: : By segmenting the infection regions with a VB-Net and registering all the CT images and the segmentation results onto a template, spatial distribution patterns of infections can be computed automatically. The algorithm provides an effective tool to visualize and quantify the spatial patterns of lung infection diseases and their changes during the disease course. Our results demonstrate different patterns between COVID-19 and CAP, between severe and critical COVID-19, as well as four distinct disease course patterns of the severe COVID-19 patients studied, with remarkable concurrent HU patterns for GGO and consolidations.

Host genetic effects in pneumonia.

Given the coronavirus disease 2019 (COVID-19) pandemic, investigations into host susceptibility to infectious diseases and downstream sequelae have never been more relevant. Pneumonia is a lung disease that can cause respiratory failure and hypoxia and is a common complication of infectious diseases, including COVID-19. Few genome-wide association studies (GWASs) of host susceptibility and severity of pneumonia have been conducted. We performed GWASs of pneumonia susceptibility and severity in the Vanderbilt University biobank (BioVU) with linked electronic health records (EHRs), including Illumina Expanded Multi-Ethnic Global Array (MEGAEX)-genotyped European ancestry (EA, n= 69,819) and African ancestry (AA, n = 15,603) individuals. Two regions of large effect were identified: the CFTR locus in EA (rs113827944; OR = 1.84, p value = 1.2 × 10-36) and HBB in AA (rs334 [p.Glu7Val]; OR = 1.63, p value = 3.5 × 10-13). Mutations in these genes cause cystic fibrosis (CF) and sickle cell disease (SCD), respectively. After removing individuals diagnosed with CF and SCD, we assessed heterozygosity effects at our lead variants. Further GWASs after removing individuals with CF uncovered an additional association in R3HCC1L (rs10786398; OR = 1.22, p value = 3.5 × 10-8), which was replicated in two independent datasets: UK Biobank (n = 459,741) and 7,985 non-overlapping BioVU subjects, who are genotyped on arrays other than MEGAEX. This variant was also validated in GWASs of COVID-19 hospitalization and lung function. Our results highlight the importance of the host genome in infectious disease susceptibility and severity and offer crucial insight into genetic effects that could potentially influence severity of COVID-19 sequelae.

Lung Infection Quantification of COVID-19 in CT Images with Deep Learning (preprint)

CT imaging is crucial for diagnosis, assessment and staging COVID-19 infection. Follow-up scans every 3-5 days are often recommended for disease progression. It has been reported that bilateral and peripheral ground glass opacification (GGO) with or without consolidation are predominant CT findings in COVID-19 patients. However, due to lack of computerized quantification tools, only qualitative impression and rough description of infected areas are currently used in radiological reports. In this paper, a deep learning (DL)-based segmentation system is developed to automatically quantify infection regions of interest (ROIs) and their volumetric ratios w.r.t. the lung. The performance of the system was evaluated by comparing the automatically segmented infection regions with the manually-delineated ones on 300 chest CT scans of 300 COVID-19 patients. For fast manual delineation of training samples and possible manual intervention of automatic results, a human-in-the-loop (HITL) strategy has been adopted to assist radiologists for infection region segmentation, which dramatically reduced the total segmentation time to 4 minutes after 3 iterations of model updating. The average Dice simiarility coefficient showed 91.6% agreement between automatic and manual infaction segmentations, and the mean estimation error of percentage of infection (POI) was 0.3% for the whole lung. Finally, possible applications, including but not limited to analysis of follow-up CT scans and infection distributions in the lobes and segments correlated with clinical findings, were discussed.