Quantitative analysis of muscle volumes in COVID-19 pneumonia with an automated segmentation system

Abstract

Aim: The aim of this study was to quantitatively analyze volume of the erector spinae muscle in COVID-19 pneumonia using an artificial intelligence-based automated segmentation program, and to investigate the relationship between pulmonary infiltration ratio and volume of the erector spinae muscle. Methods: In this retrospective study, thoracic CT images of patients who tested positive for SARS-CoV-2 on RT-PCR and had COVID-19 pneumonia were analyzed. Based on the percentage of pulmonary involvement, the study cohort was divided into two groups (Group I: less than 25% involvement and Group II: more than %25 involvement). Volume of the erector spinae muscle and severity of lung involvement were quantitatively analyzed using an artificial intelligence-based automated segmentation program. The data of group I and group II were compared. Results: The study population consisted of 74 subjects; 35 in Group I and 39 in Group II. Significant negative correlations were observed between the total pulmonary infiltration ratio and the volume of the erector spinae muscle. Furthermore, the analysis demonstrated that lung density, total lung infiltration volume, serum C-reactive protein (CRP) level, serum ESR level, and total erector spinae muscle volume can serve as valuable indicators for assessing the severity of lung involvement in patients with COVID-19 pneumonia. Conclusion: Measurement of erector spinae muscle volume may be useful for assessment of pulmonary infiltration in patients with COVID-19 pneumonia

Keywords

• Erector spinae muscle volume
• COVID-19 pneumonia
• pulmonary infiltration
• automated segmentation
• artificial intelligence