文献速递腹部技术与安全CT

比较薄层与厚层CT图像数据衍生的全自动人工智能身体成分测量

Comparing fully automated AI body composition measures derived from thin and thick slice CT image data.
PubMed 文献 · Abdom Radiol (NY) · 2023-12-29

本回顾性研究比较了薄层(1.25 mm)与厚层(5 mm)腹部CT数据经全自动人工智能算法得出的身体成分测量值,共评估9882例CT扫描。软组织测量指标相关性很强(r²≥0.92),骨密度相关性中等(r²=0.35),作者认为两种序列均可用于这些基于CT的身体成分算法。

要点

  • 软组织测量在薄层与厚层CT间相关性很强(r²≥0.92),骨密度相关性中等(r²=0.35)。
  • 肌肉面积、肝脏衰减、肝脏体积、内脏脂肪比的平均百分比差异均小于5%。
  • 主动脉钙化厚层较薄层在Agatston评分0–100和>400区间分别高估3.1%和0.3%,在100–400区间低估。

核心结论

  • 薄层与厚层腹部CT衍生的自动身体成分测量值高度相关且一致,尤其适用于软组织应用,两种序列均可用于这些基于CT的身体成分算法。

研究设计与样本

  • 回顾性研究,共评估9882例CT扫描(平均年龄57.0岁;女性4527例,男性5355例),包括8947例平扫和935例增强扫描。
  • 两个队列:无症状成人结直肠癌筛查的平扫CT,以及结直肠癌患者的增强CT。
  • 薄层参数为1.25×0.625 mm,厚层参数为5×3 mm;使用全自动CT身体成分算法量化骨衰减、肌肉衰减、肌肉面积、肝脏衰减、肝脏体积、脾脏体积、内脏脂肪比和主动脉钙化。
  • 比较薄层与厚层数据衍生的身体成分测量值,包括相关系数和Bland-Altman分析。

诊断标准与关键数值

  • 所有软组织测量呈很强正相关:肌肉衰减r²=0.97、肌肉面积r²=0.98、肝脏衰减r²=0.99、肝脏体积r²=0.98、脾脏体积r²=0.99、内脏脂肪比r²=0.98、主动脉钙化r²=0.92(均p<0.001)。
  • 骨衰减呈中等正相关(r²=0.35)。
  • Bland-Altman分析显示肌肉衰减、肌肉面积、肝脏衰减、肝脏体积和脾脏体积一致性很强。
  • 平均百分比差异:内脏脂肪比4.6%、肌肉面积-0.5%、肝脏衰减0.4%、肝脏体积2.7%、肌肉衰减-5.5%、脾脏体积5.1%。
  • 主动脉钙化:厚层较薄层在Agatston评分0–100和>400区间分别高估3.1%和0.3%,在100–400区间低估。

临床应用与阅片要点

  • 原文结论认为,薄层与厚层腹部CT衍生的自动身体成分测量值高度相关且一致,尤其软组织应用,使得两种序列均可用于这些基于CT的身体成分算法。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

PURPOSE: To compare fully automated artificial intelligence body composition measures derived from thin (1.25 mm) and thick (5 mm) slice abdominal CT data.

METHODS: In this retrospective study, fully automated CT-based body composition algorithms for quantifying bone attenuation, muscle attenuation, muscle area, liver attenuation, liver volume, spleen volume, visceral-to-subcutaneous fat ratio (VSR) and aortic calcium were applied to both thin (1.25 × 0.625 mm) and thick (5 × 3 mm) abdominal CT series from two patient cohorts: unenhanced scans in asymptomatic adults undergoing colorectal cancer screening, and post-contrast scans in patients with colorectal cancer. Body composition measures derived from thin and thick slice data were compared, including correlation coefficients and Bland-Altman analysis.

RESULTS: A total of 9882 CT scans (mean age, 57.0 years; 4527 women, 5355 men) were evaluated, including 8947 non-contrast and 935 contrast-enhanced CT exams. Very strong positive correlation was observed for all soft tissue measures: muscle attenuation (r2 = 0.97), muscle area (r2 = 0.98), liver attenuation (r2 = 0.99), liver volume (r2 = 0.98) and spleen volume (r2 = 0.99), VSR (r2 = 0.98), and aortic calcium (r2 = 0.92); (p < 0.001 for all). Moderate positive correlation was observed for bone attenuation (r2 = 0.35). Bland-Altman analysis showed strong agreement for muscle attenuation, muscle area, liver attenuation, liver volume and spleen volume. Mean percentage differences amongst body composition measures were less than 5% for VSR (4.6%), muscle area (- 0.5%), liver attenuation (0.4%) and liver volume (2.7%) and less than 10% for muscle attenuation (- 5.5%) and spleen volume (5.1%). For aortic calcium, thick slice overestimated for Agatston scores between 0 and 100 and > 400 burden in 3.1% and 0.3% relative to thin slice, respectively, but underestimated scores between 100 and 400.

CONCLUSION: Automated body composition measures derived from thin and thick abdominal CT data are strongly correlated and show agreement, particularly for soft tissue applications, making it feasible to use either series for these CT-based body composition algorithms.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Lee MH, Liu D, Garrett JW, et al. Comparing fully automated AI body composition measures derived from thin and thick slice CT image data. Abdom Radiol (NY). 2023. PMID: 38158424. doi:10.1007/s00261-023-04135-1

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。