文献速递心血管胸部CT

评估人工智能在非门控胸部CT上检测和分级冠状动脉钙化的诊断准确性和预后效用

Assessing the diagnostic accuracy and prognostic utility of artificial intelligence detection and grading of coronary artery calcification on nongated computed tomography (CT) thorax.
PubMed 文献 · Clin Radiol · 2025-03-22

本研究为单中心回顾性分析,纳入291例(平均年龄64±19岁,51%女性)接受非门控非对比胸部CT的患者,评估AI工具检测冠状动脉钙化(CAC)的诊断准确性和预后价值。AI检测CAC的敏感度96%、特异度96%、阳性预测值95%、阴性预测值97%,观察者间一致性CAC存在为κ=0.92、严重程度分级为κ=0.60,AI检测的CAC存在和严重程度可预测全因死亡率(p<0.001)。结论认为该AI工具在非对比非门控胸部CT上具有可行的分析潜力,但手动质量评估仍必不可少。

要点

  • AI检测CAC的敏感度96%、特异度96%、阳性预测值95%、阴性预测值97%。
  • AI与放射科医生对CAC存在的一致性κ=0.92,对严重程度分级的一致性κ=0.60。
  • AI检测的CAC存在和严重程度可预测全因死亡率(p<0.001)。

核心结论

  • AI工具在非对比非门控胸部CT上检测CAC具有高敏感度和特异度,其检测的CAC存在和严重程度可预测全因死亡率(p<0.001),但手动质量评估仍必不可少。

研究设计与样本

  • 单中心回顾性分析,按年龄组(<40、40-49、50-59、60-69、70-79、80-89、≥90岁)每组连续纳入75例患者,接受非门控非对比CT(2015年1月至12月),最终纳入291例(平均年龄64±19岁,51%女性),AI分析报告CAC存在并生成Agatston评分,与基线CT报告及放射科医生重新审阅比较,使用Cohen‘s κ评估观察者间变异,记录全因死亡率并检验其与AI检测CAC的关联。

诊断标准与关键数值

  • 以放射科医生重新审阅为参考,AI检测CAC的敏感度96%、特异度96%、阳性预测值95%、阴性预测值97%;CAC存在的一致性κ=0.92,严重程度分级的一致性κ=0.60;80%(234/291)的AI报告通过放射科医生质量评估;初始临床报告CAC报告率为7%(17/234),放射科医生重新审阅为58%(135/234),AI分析为57%(134/234)。

临床应用与阅片要点

  • 作者认为该AI工具在非对比非门控胸部CT上具有可行的分析潜力,若整合到常规实践可提供预后信息,但手动质量评估仍必不可少。

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

AIMS: This study assessed the diagnostic accuracy and prognostic implications of an artificial intelligence (AI) tool for coronary artery calcification (CAC) assessment on nongated, noncontrast thoracic computed tomography (CT).

MATERIALS AND METHODS: A single-centre retrospective analysis of 75 consecutive patients per age group (<40, 40-49, 50-59, 60-69, 70-79, 80-89, and ≥90 years) undergoing non-gated, non-contrast CT (January-December 2015) was conducted. AI analysis reported CAC presence and generated an Agatston score, and the performance was compared with baseline CT reports and a dedicated radiologist re-review. Interobserver variability between AI and radiologist assessments was measured using Cohen's κ. All-cause mortality was recorded, and its association with AI-detected CAC was tested.

RESULTS: A total of 291 patients (mean age: 64 ± 19, 51% female) were included, with 80% (234/291) of AI reports passing radiologist quality assessment. CAC was reported on 7% (17/234) of initial clinical reports, 58% (135/234) on radiologist re-review, and 57% (134/234) by AI analysis. After manual quality assurance (QA) assessment, the AI tool demonstrated high sensitivity (96%), specificity (96%), positive predictive value (95%), and negative predictive value (97%) for CAC detection compared with radiologist re-review. Interobserver agreement was strong for CAC prevalence (κ = 0.92) and moderate for severity grading (κ = 0.60). AI-detected CAC presence and severity predicted all-cause mortality (p < 0.001).

CONCLUSION: The AI tool exhibited feasible analysis potential for non-contrast, non-gated thoracic CTs, offering prognostic insights if integrated into routine practice. Nonetheless, manual quality assessment remains essential.

ADVANCES IN KNOWLEDGE: This AI tool represents a potential enhancement to CAC detection and reporting on routine noncardiac chest CT.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Shear B, Graby J, Murphy D, et al. Assessing the diagnostic accuracy and prognostic utility of artificial intelligence detection and grading of coronary artery calcification on nongated computed tomography (CT) thorax. Clin Radiol. 2025. PMID: 40300276. doi:10.1016/j.crad.2025.106909

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。