COVID-19 severity stratification using quantitative computed tomography analysis

Abstract

Aim: This study aimed to examine the utility of computer-assisted quantitative assessment of chest computed tomography (CT) images in the stratification of Coronavirus Disease 2019 (COVID-19) severity. Materials and Methods: This study was designed as a retrospective, single-center study and included a total of 142 RT-PCR-confirmed COVID-19 patients. CT findings were visually evaluated and noted for their morphology and distribution characteristics. Visual semi-quantitative score (VSS) and computer-aided quantitative score (CQS) were calculated. The utility of the approach was assessed based on its ability to predict the patients who would require intensive care. Results: The presence of underlying fibrosis, air bubble sign, and co-occurrence of central and peripheral lung area involvement were the CT findings that were significantly more commonly encountered in patients with intensive care requirements during the follow-up period. We found a significant positive correlation between total VSS and CQS (p