Comparing Visual and Software-Based Quantitative Assessment Scores of Lung Parenchymal Involvement Quantification in COVID-19 Patients

Abstract

BACKGROUND. Computed tomography (CT) plays a paramount role in the characterization and follow-up of Covid-19. Several scoring systems have been implemented to properly assess the lung parenchyma involved in patients suffering from Sars-Cov-2 infection, such as visual quantitative assessment score (VQAS) and software-based quantitative assessment score (SBQAS). PURPOSE. This study aims to compare VQAS and SBQAS with two different software. MATERIAL AND METHODS. This was a retrospective study; 90 patients were enrolled with the following criteria: patients’ age more than 18 years old, positive test for Covid-19, and unenhanced chest CT scans obtained between March and June 2021. The VQAS was independently assessed, and the SBQAS was performed with two different Artificial Intelligence-driven softwares (Icolung and CT-COPD). The Intraclass Correlation Coefficient (ICC) statistical index and Bland-Altman test were employed. RESULTS. The agreement score between radiologists (R1 and R2) for the VQAS of the lung parenchyma involved in the CT images was good (ICC = 0.871). The agreement score between the two software applications for the SBQAS was moderate (ICC = 0.584). The accordance between Icolung and the median of the visual evaluations (Median R1-R2) is good (ICC = 0.885). The correspondence between CT-COPD and the median of the VQAS (Median R1-R2) is moderate (ICC = 0.622). CONCLUSION. This study showed moderate and good agreement regarding the VQAS and the SBQAS, enhancing this approach as a valuable tool to manage Covid-19 patients.