文献速递心血管胸部CT

心脏与胸部CT自动钙化评分人工智能软件的验证

Validation of artificial intelligence software for automatic calcium scoring in cardiac and chest computed tomography.
PubMed 文献 · Eur J Radiol · 2025-07-16

在684例接受心脏CT和非心电触发胸部CT的参与者中,基于人工智能的冠状动脉钙化评分与手动评分相比,心脏CT和胸部CT的钙化检出率分别为98.1%和92.4%,ICC分别为0.997和0.992,AS分层分类的Cohen kappa分别为0.952和0.901。作者结论认为AI可缩短评估时间并实现低剂量胸部CT上CAC的机会性筛查。

要点

  • AI在心脏CT和胸部CT的CAC检出率分别为98.1%和92.4%,准确率分别为97.1%和92.1%。
  • AI与手动AS的ICC在心脏CT和胸部CT分别为0.997和0.992,AS分层分类kappa分别为0.952和0.901。
  • AI可能缩短评估时间并支持低剂量胸部CT上CAC的机会性筛查。

核心结论

  • 与手动CACS相比,基于AI的CACS显示出高检出率和强相关性,并具有极佳的风险分类一致性。
  • AI可能缩短评估时间并实现低剂量胸部CT上CAC的机会性筛查。

研究设计与样本

  • 本研究为验证性研究,纳入684名参与者(59±4.8岁;48.8%为男性),均接受心脏CT和非心电触发胸部CT,其中484名参与者在心脏CT上AS>0。
  • 将基于AI的结果与手动AS和VS进行比较,评估敏感度和准确率、组内相关系数(ICC)、Bland-Altman分析以及AS分层(0;1-99;100-299;≥300)分类的Cohen kappa。

诊断标准与关键数值

  • AI在心脏CT的CAC检出率为98.1%(准确率97.1%),在胸部CT为92.4%(准确率92.1%)。
  • AI与手动AS的ICC在心脏CT为0.997、胸部CT为0.992;与手动VS的ICC在心脏CT为0.997、胸部CT为0.991。
  • Bland-Altman分析:心脏CT AS平均差异2.3(一致性限-42.7,47.4);心脏CT VS平均差异1.9(一致性限-36.4,40.2);胸部CT AS平均差异-0.3(一致性限-74.8,74.2);胸部CT VS平均差异-0.6(一致性限-65.7,64.5)。
  • AS分层分类的Cohen kappa在心脏CT为0.952(95%CI:0.934-0.970)、胸部CT为0.901(95%CI:0.875-0.926),分类一致率分别为95.9%和91.4%。

临床应用与阅片要点

  • 原文结论指出AI可能缩短评估时间并实现低剂量胸部CT上CAC的机会性筛查。

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

OBJECTIVE: Coronary artery calcium scoring (CACS), i.e. quantification of Agatston (AS) or volume score (VS), can be time consuming. The aim of this study was to compare automated, artificial intelligence (AI)-based CACS to manual scoring, in cardiac and chest CT for lung cancer screening.

METHODS: We selected 684 participants (59 ± 4.8 years; 48.8 % men) who underwent cardiac and non-ECG-triggered chest CT, including 484 participants with AS > 0 on cardiac CT. AI-based results were compared to manual AS and VS, by assessing sensitivity and accuracy, intraclass correlation coefficient (ICC), Bland-Altman analysis and Cohen's kappa for classification in AS strata (0;1-99;100-299;≥300).

RESULTS: AI showed high CAC detection rate: 98.1% in cardiac CT (accuracy 97.1%) and 92.4% in chest CT (accuracy 92.1%). AI showed excellent agreement with manual AS (ICC:0.997 and 0.992) and manual VS (ICC:0.997 and 0.991), in cardiac CT and chest CT, respectively. In Bland-Altman analysis, there was a mean difference of 2.3 (limits of agreement (LoA):-42.7, 47.4) for AS on cardiac CT; 1.9 (LoA:-36.4, 40.2) for VS on cardiac CT; -0.3 (LoA:-74.8, 74.2) for AS on chest CT; and -0.6 (LoA:-65.7, 64.5) for VS on chest CT. Cohen's kappa was 0.952 (95%CI:0.934-0.970) for cardiac CT and 0.901 (95%CI:0.875-0.926) for chest CT, with concordance in 95.9 and 91.4% of cases, respectively.

CONCLUSION: AI-based CACS shows high detection rate and strong correlation compared to manual CACS, with excellent risk classification agreement. AI may reduce evaluation time and enable opportunistic screening for CAC on low-dose chest CT.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Hamelink II, Nie ZZ, Severijn TEJT, et al. Validation of artificial intelligence software for automatic calcium scoring in cardiac and chest computed tomography. Eur J Radiol. 2025. PMID: 40690836. doi:10.1016/j.ejrad.2025.112323

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。