Toia Giuseppe V, Garret John W, Rose Sean D, Szczykutowicz Timothy P, Pickhardt Perry J
University of Wisconsin School of Medicine and Public Health, Madison, USA.
The University of Texas Health Science Center at Houston, Houston, USA.
Abdom Radiol (NY). 2025 Jun;50(6):2758-2769. doi: 10.1007/s00261-024-04733-7. Epub 2024 Dec 7.
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, 100 keV). 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 70 keV and interquartile range were reported by energy level to characterize variation. Linear regression was performed to calibrate non-70 keV data and to estimate their equivalent 70 keV biomarker attenuation values.
Relative to 70 keV, absolute median differences in attenuation-based biomarkers (excluding Agatston score) ranged 39-358, 12-102, 5-48, 9-75 HU for 40, 55, 85, 100 keV, respectively. For area-based biomarkers, differences ranged 6-15, 3-4, 2-7, 0-5 cm for 40, 55, 85, 100 keV. For volume-based biomarkers, differences ranged 12-34, 8-68, 12-52, 1-57 cm for 40, 55, 85, 100 keV. Agatston score behavior was more spurious with median differences ranging 70-204 HU. In general, VMI < 70 keV showed more variation in median biomarker measurement than VMI > 70 keV.
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 70 keV. Lower VMI datasets should be avoided due to larger deviations in measured value as compared to 70 keV, a level considered equivalent to conventional 120 kVp exams.
使用双能CT（DECT）研究基于人工智能（AI）的CT人体成分生物标志物在不同虚拟单能量成像（VMI）水平下的表现。
这项回顾性研究纳入了88例通过快速千伏切换DECT获得的腹部盆腔增强CT图像。图像被重建为五个VMI水平（40、55、70、85、100keV）。应用全自动算法来量化腹部脂肪（皮下和内脏）、骨骼肌、骨骼、钙（腹部阿加斯顿评分）的CT值（HU）以及器官大小（面积或体积）。按能量水平报告相对于70keV的生物标志物中位数差异和四分位间距，以描述其变化情况。进行线性回归以校准非70keV数据，并估计其等效的70keV生物标志物衰减值。
相对于70keV，基于衰减的生物标志物（不包括阿加斯顿评分）的绝对中位数差异在40、55、85、100keV时分别为39 - 358、12 - 102、5 - 48、9 - 75 HU。基于面积的生物标志物差异在40、55、85、100keV时分别为6 - 15、3 - 4、2 - 7、0 - 5 cm。基于体积的生物标志物差异在40、55、85、100keV时分别为12 - 34、8 - 68、12 - 52、1 - 57 cm。阿加斯顿评分的表现更不稳定，中位数差异为70 - 204 HU。总体而言，VMI < 70keV时生物标志物测量中位数的变化比VMI > 70keV时更多。
本研究描述了在通过DECT获得的不同VMI水平下全自动AI CT生物标志物工具包的表现。数据显示，在70keV及以上进行测量时，生物标志物值变化相对较小。由于与70keV相比测量值偏差较大，应避免使用较低VMI数据集，70keV这一水平被认为等同于传统的120 kVp检查。
