Comparing fully automated AI body composition biomarkers at differing virtual monoenergetic levels using dual-energy CT.

Abstract

To investigate the behavior of artificial intelligence (AI) CT-based body composition biomarkers at different virtual monoenergetic imaging (VMI) levels using dual-energy CT (DECT). This retrospective study included 88 contrast-enhanced abdominopelvic CTs acquired with rapid-kVp switching DECT. Images were reconstructed into five VMI levels (40, 55, 70, 85, 100keV). Fully automated algorithms for quantifying CT number (HU) in abdominal fat (subcutaneous and visceral), skeletal muscle, bone, calcium (abdominal Agatston score), and organ size (area or volume) were applied. Biomarker median difference relative to 70keV and interquartile range were reported by energy level to characterize variation. Linear regression was performed to calibrate non-70keV data and to estimate their equivalent 70keV biomarker attenuation values. Relative to 70keV, absolute median differences in attenuation-based biomarkers (excluding Agatston score) ranged 39-358, 12-102, 5-48, 9-75 HU for 40, 55, 85, 100keV, respectively. For area-based biomarkers, differences ranged 6-15, 3-4, 2-7, 0-5 cm2 for 40, 55, 85, 100keV. For volume-based biomarkers, differences ranged 12-34, 8-68, 12-52, 1-57 cm3 for 40, 55, 85, 100keV. Agatston score behavior was more spurious with median differences ranging 70-204 HU. In general, VMI < 70keV showed more variation in median biomarker measurement than VMI > 70keV. This study characterized the behavior of a fully automated AI CT biomarker toolkit across varying VMI levels obtained with DECT. The data showed relatively little biomarker value change when measured at or greater than 70keV. Lower VMI datasets should be avoided due to larger deviations in measured value as compared to 70keV, a level considered equivalent to conventional 120 kVp exams.