Semi-quantitative software evaluation of COVID-19 CT examinations-correlation with clinical parameters

Software-guided semi-quantitative analysis of coronavirus disease 2019 (COVID-19) pneumonia in lung computed tomography (CT) datasets for severity assessment. Further to correlate imaging findings with the need of intensive care medicine and clinical parameters.

This single-center retrospective study analyzed 66 consecutive patients (31 females, mean age 64.6±16.2 years) with lung CT datasets from 12/2020 to 05/2021 and confirmed COVID-19 pneumonia. Lung CT datasets were evaluated using a semi-quantitative software for segmentation and quantification. Correlation with underlying diseases, laboratory parameters and further course were assessed, including intubation and need for intensive care.

Total lung volume was 3,903.65±1,185.67 mL, mean volume of opacities was 866.52±829.29 mL, reflecting 23.54%±21.92% of total lung volume. Volume of high opacities was 186.88±208.15 mL reflecting 0.06%±0.07% of total lung volume. Overall, 12 patients died (18.2%), 10 patients (15.2%) required intubation and in 27 cases (40.9%) intensive care was necessary. In patients who died volume of opacities and high opacities were significantly higher (P<0.05). Significant differences with a risk for needing intensive care medicine were extensive pulmonary opacities, volume of high opacities, and percentage of high opacities (P<0.001 each).

COVID-19 pneumonia may be semi-quantified using an artificial intelligence (AI)-based software approach. Quantitative methods could provide precise information on the volume of opacities and may allow detecting connections to patient therapy, including the need for intensive care.