An End-to-End Integrated Clinical and CT-Based Radiomics Nomogram for Predicting Disease Severity and Need for Ventilator Support in COVID-19 Patients: A Large Multisite Retrospective Study

Objective: The disease COVID-19 has caused a widespread global pandemic with ~3. 93 million deaths worldwide. In this work, we present three models—radiomics (MRM), clinical (MCM), and combined clinical–radiomics (MRCM) nomogram to predict COVID-19-positive patients who will end up needing invasive mechanical ventilation from the baseline CT scans. Methods: We performed a retrospective multicohort study of individuals with COVID-19-positive findings for a total of 897 patients from two different institutions (Renmin Hospital of Wuhan University, D1 = 787, and University Hospitals, US D2 = 110). The patients from institution-1 were divided into 60% training, Results: The three out of the top five features identified using Conclusion: The novel integrated imaging and clinical model (MRCM) outperformed both models (MRM) and (MCM). Our results across multiple sites suggest that the integrated nomogram could help identify COVID-19 patients with more severe disease phenotype and potentially require mechanical ventilation.

Deep-learning-based hepatic fat assessment (DeHFt) on non-contrast chest CT and its association with disease severity in COVID-19 infections: A multi-site retrospective study.

BACKGROUND: Hepatic steatosis (HS) identified on CT may provide an integrated cardiometabolic and COVID-19 risk assessment. This study presents a deep-learning-based hepatic fat assessment (DeHFt) pipeline for (a) more standardised measurements and (b) investigating the association between HS (liver-to-spleen attenuation ratio <1 in CT) and COVID-19 infections severity, wherein severity is defined as requiring invasive mechanical ventilation, extracorporeal membrane oxygenation, death. METHODS: DeHFt comprises two steps. First, a deep-learning-based segmentation model (3D residual-UNet) is trained (N.ß=.ß80) to segment the liver and spleen. Second, CT attenuation is estimated using slice-based and volumetric-based methods. DeHFt-based mean liver and liver-to-spleen attenuation are compared with an expert's ROI-based measurements. We further obtained the liver-to-spleen attenuation ratio in a large multi-site cohort of patients with COVID-19 infections (D1, N.ß=.ß805; D2, N.ß=.ß1917; D3, N.ß=.ß169) using the DeHFt pipeline and investigated the association between HS and COVID-19 infections severity. FINDINGS: The DeHFt pipeline achieved a dice coefficient of 0.95, 95% CI [0.93...0.96] on the independent validation cohort (N.ß=.ß49). The automated slice-based and volumetric-based liver and liver-to-spleen attenuation estimations strongly correlated with expert's measurement. In the COVID-19 cohorts, severe infections had a higher proportion of patients with HS than non-severe infections (pooled OR.ß=.ß1.50, 95% CI [1.20...1.88], P.ß<.ß.001). INTERPRETATION: The DeHFt pipeline enabled accurate segmentation of liver and spleen on non-contrast CTs and automated estimation of liver and liver-to-spleen attenuation ratio. In three cohorts of patients with COVID-19 infections (N.ß=.ß2891), HS was associated with disease severity. Pending validation, DeHFt provides an automated CT-based metabolic risk assessment. FUNDING: For a full list of funding bodies, please see the Acknowledgements.

Integrated Clinical and CT Based Artificial Intelligence Nomogram for Predicting Severity and Need for Ventilator Support in COVID-19 Patients: A Multi-Site Study.

Almost 25% of COVID-19 patients end up in ICU needing critical mechanical ventilation support. There is currently no validated objective way to predict which patients will end up needing ventilator support, when the disease is mild and not progressed. N = 869 patients from two sites (D1: N = 822, D2: N = 47) with baseline clinical characteristics and chest CT scans were considered for this study. The entire dataset was randomly divided into 70% training, D1train (N = 606) and 30% test-set (Dtest: D1test (N = 216) + D2 (N = 47)). An expert radiologist delineated ground-glass-opacities (GGOs) and consolidation regions on a subset of D1train, (D1train_sub, N = 88). These regions were automatically segmented and used along with their corresponding CT volumes to train an imaging AI predictor (AIP) on D1train to predict the need of mechanical ventilators for COVID-19 patients. Finally, top five prognostic clinical factors selected using univariate analysis were integrated with AIP to construct an integrated clinical and AI imaging nomogram (ClAIN). Univariate analysis identified lactate dehydrogenase, prothrombin time, aspartate aminotransferase, %lymphocytes, albumin as top five prognostic clinical features. AIP yielded an AUC of 0.81 on Dtest and was independently prognostic irrespective of other clinical parameters on multivariable analysis (p<0.001). ClAIN improved the performance over AIP yielding an AUC of 0.84 (p = 0.04) on Dtest. ClAIN outperformed AIP in predicting which COVID-19 patients ended up needing a ventilator. Our results across multiple sites suggest that ClAIN could help identify COVID-19 with severe disease more precisely and likely to end up on a life-saving mechanical ventilation.

Computational pathology reveals unique spatial patterns of immune response in H&E images from COVID-19 autopsies: preliminary findings.

Purpose: We used computerized image analysis and machine learning approaches to characterize spatial arrangement features of the immune response from digitized autopsied H&E tissue images of the lung in coronavirus disease 2019 (COVID-19) patients. Additionally, we applied our approach to tease out potential morphometric differences from autopsies of patients who succumbed to COVID-19 versus H1N1. Approach: H&E lung whole slide images from autopsy specimens of nine COVID-19 and two H1N1 patients were computationally interrogated. 606 image patches ( ∼ 55 per patient) of 1024 × 882 pixels were extracted from the 11 autopsied patient studies. A watershed-based segmentation approach in conjunction with a machine learning classifier was employed to identify two types of nuclei families: lymphocytes and non-lymphocytes (i.e., other nucleated cells such as pneumocytes, macrophages, and neutrophils). Based off the proximity of the individual nuclei, clusters for each nuclei family were constructed. For each of the resulting clusters, a series of quantitative measurements relating to architecture and density of nuclei clusters were calculated. A receiver operating characteristics-based feature selection method, violin plots, and the t-distributed stochastic neighbor embedding algorithm were employed to study differences in immune patterns. Results: In COVID-19, the immune response consistently showed multiple small-size lymphocyte clusters, suggesting that lymphocyte response is rather modest, possibly due to lymphocytopenia. In H1N1, we found larger lymphocyte clusters that were proximal to large clusters of non-lymphocytes, a possible reflection of increased prevalence of macrophages and other immune cells. Conclusion: Our study shows the potential of computational pathology to uncover immune response features that may not be obvious by routine histopathology visual inspection.