Estimating COVID-19 Pneumonia Extent and Severity From Chest Computed Tomography

Alysson Roncally Silva Carvalho; Alan Guimarães; Thiego de Souza Oliveira Garcia; Gabriel Madeira Werberich; Victor Fraga Ceotto; Fernando Augusto Bozza; Rosana Souza Rodrigues; Joana Sofia F Pinto; Willian Rebouças Schmitt; Walter Araujo Zin; Manuela França

doi:10.3389/fphys.2021.617657

Estimating COVID-19 Pneumonia Extent and Severity From Chest Computed Tomography

Front Physiol. 2021 Feb 15:12:617657. doi: 10.3389/fphys.2021.617657. eCollection 2021.

Authors

Alysson Roncally Silva Carvalho^{1

2

3}, Alan Guimarães², Thiego de Souza Oliveira Garcia⁴, Gabriel Madeira Werberich⁵, Victor Fraga Ceotto⁶, Fernando Augusto Bozza^{7

8}, Rosana Souza Rodrigues^{5

7}, Joana Sofia F Pinto⁹, Willian Rebouças Schmitt⁹, Walter Araujo Zin³, Manuela França^{9

10}

Affiliations

¹ Cardiovascular R&D Centre (UnIC), Department of Surgery and Physiology, Faculty of Medicine, University of Porto, Porto, Portugal.
² Laboratory of Pulmonary Engineering, Biomedical Engineering Program, Alberto Luiz Coimbra Institute of Post-Graduation and Research in Engineering, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil.
³ Laboratory of Respiration Physiology, Carlos Chagas Filho Institute of Biophysics, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil.
⁴ Medical Faculty, Universidade Estácio de Sá, Rio de Janeiro, Brazil.
⁵ Department of Radiology, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil.
⁶ Hospital Niteroi D'Or, Niterói, Brazil.
⁷ D'Or Institute for Research and Education, Rio de Janeiro, Brazil.
⁸ National Institute of Infectious Disease, Oswaldo Cruz Foundation, Rio de Janeiro, Brazil.
⁹ Radiology Department, Complexo Hospitalar Universitário do Porto, Porto, Portugal.
¹⁰ Instituto de Ciências Biomeìdicas Abel Salazar, Porto University, Porto, Portugal.

Abstract

Background: COVID-19 pneumonia extension is assessed by computed tomography (CT) with the ratio between the volume of abnormal pulmonary opacities (PO) and CT-estimated lung volume (CT_LV). CT-estimated lung weight (CT_LW) also correlates with pneumonia severity. However, both CT_LV and CT_LW depend on demographic and anthropometric variables.

Purposes: To estimate the extent and severity of COVID-19 pneumonia adjusting the volume and weight of abnormal PO to the predicted CT_LV (pCT_LV) and CT_LW (pCT_LW), respectively, and to evaluate their possible association with clinical and radiological outcomes.

Methods: Chest CT from 103 COVID-19 and 86 healthy subjects were examined retrospectively. In controls, predictive equations for estimating pCT_LV and pCT_LW were assessed. COVID-19 pneumonia extent and severity were then defined as the ratio between the volume and the weight of abnormal PO expressed as a percentage of the pCT_LV and pCT_LW, respectively. A ROC analysis was used to test differential diagnosis ability of the proposed method in COVID-19 and controls. The degree of pneumonia extent and severity was assessed with Z-scores relative to the average volume and weight of PO in controls. Accordingly, COVID-19 patients were classified as with limited, moderate and diffuse pneumonia extent and as with mild, moderate and severe pneumonia severity.

Results: In controls, CT_LV could be predicted by sex and height (adjusted R ² = 0.57; P < 0.001) while CT_LW by age, sex, and height (adjusted R ² = 0.6; P < 0.001). The cutoff of 20% (AUC = 0.91, 95%CI 0.88-0.93) for pneumonia extent and of 50% (AUC = 0.91, 95%CI 0.89-0.92) for pneumonia severity were obtained. Pneumonia extent were better correlated when expressed as a percentage of the pCT_LV and pCT_LW (r = 0.85, P < 0.001), respectively. COVID-19 patients with diffuse and severe pneumonia at admission presented significantly higher CRP concentration, intra-hospital mortality, ICU stay and ventilatory support necessity, than those with moderate and limited/mild pneumonia. Moreover, pneumonia severity, but not extent, was positively and moderately correlated with age (r = 0.46) and CRP concentration (r = 0.44).

Conclusion: The proposed estimation of COVID-19 pneumonia extent and severity might be useful for clinical and radiological patient stratification.

Keywords: COVID-19; CT-estimated lung volume; CT-estimated lung weight; computed tomography; deep learning.