文献速递心血管胸部技术与安全CT

人工智能在心脏CT的临床应用综述

Clinical Applications of Artificial Intelligence in Cardiac CT: From Coronary CT Angiography to CT-Derived Fractional Flow Reserve and Myocardial Perfusion Imaging.
PubMed 文献 · Korean J Radiol · 2026-01-01

本综述回顾人工智能在心脏CT中的应用进展,涵盖冠状动脉CT血管成像、CT血流储备分数及CT心肌灌注成像。文章指出AI可自动完成钙化积分、血管分割与斑块特征分析,并在狭窄检测、功能评估及心肌缺血定量方面表现良好。目前证据仍受回顾性设计及验证队列局限。

要点

  • AI可自动完成CCTA钙化积分、血管分割与斑块定量,提高工作效率与可重复性。
  • 机器学习CT血流储备分数可从常规CCTA获得病变特异性功能评估,计算效率优于传统流体力学。
  • AI自动定量心肌血流量与缺血心肌容积,与手动测量一致性良好,可用于缺血检测与危险分层。

核心结论

  • AI已从CCTA延伸至CT-MPI,覆盖解剖、功能与预后维度,具备改善心脏CT临床应用效率与精度的潜力。
  • AI在狭窄检测与斑块量化方面的诊断和预后性能可与有创参考标准相当。
  • 当前证据受回顾性设计、选择性验证队列及缺乏外部和前瞻性测试所限,尚需标准化验证框架。

研究设计与样本

  • 本文为综述,回顾人工智能在心脏CT领域的研究进展与未来方向。
  • 涉及CCTA、CT血流储备分数及CT心肌灌注成像的AI应用研究。

关键影像表现/征象

  • AI可自动完成冠状动脉钙化积分、血管分割与斑块特征分析。
  • AI可自动定量心肌血流量与缺血心肌容积。

诊断标准与关键数值

  • AI在CCTA狭窄检测和斑块量化方面的诊断及预后性能与有创参考标准相当。
  • 机器学习CT血流储备分数在保持诊断准确性的同时,计算效率较传统流体力学显著提升。
  • AI自动定量心肌血流量与缺血心肌容积与手动测量一致性良好,对缺血检测与危险分层表现强劲。

临床应用与阅片要点

  • AI辅助CCTA可减轻放射科医生后处理负担,缩短钙化积分、血管分割与斑块分析时间。
  • CT血流储备分数可在常规CCTA基础上提供病变特异性功能信息,避免额外功能检查。
  • AI心肌灌注定量可用于缺血心肌容积的客观测量,辅助缺血检测与风险分层。
  • 现阶段AI结果仍需结合原始影像复核,不宜完全替代人工判读。

局限性

  • 证据多来自回顾性设计,前瞻性验证不足。
  • 验证队列经过选择,外部验证及复杂真实世界环境中的测试不足。
  • AI开发与临床需求对齐、多样化高质量数据获取及算法转化为验证工具仍存在未解决的挑战。

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

Artificial intelligence (AI) has rapidly transformed cardiac CT, extending its clinical utility from coronary CT angiography (CCTA) to CT myocardial perfusion imaging (CT-MPI). This review outlines the current advances in and future perspectives on AI-aided cardiac CT across anatomical, functional, and prognostic dimensions. In CCTA, AI can automate calcium scoring, vessel segmentation, and plaque characterization, markedly improving workflow efficiency and reproducibility. Deep-learning models can allow accurate detection of coronary stenosis and plaque quantification, achieving diagnostic and prognostic performances comparable to those of invasive reference standards. Beyond anatomical assessment, machine learning-based CT-derived fractional flow reserve measurements can provide lesion-specific functional evaluation directly from routine CCTA scans, substantially improving computational efficiency over conventional fluid dynamics while maintaining diagnostic accuracy. In functional imaging, AI can facilitate automated quantification of myocardial blood flow and ischemic myocardial volume, showing excellent agreement with manual measurements and strong performance for ischemia detection and risk stratification. Emerging approaches for virtual perfusion modeling and deep-learning-based denoising have further expanded the noninvasive assessment of myocardial physiology and tissue characterization. Despite these advances, challenges in aligning AI development with clinical requirements, acquiring diverse and high-quality datasets, and translating algorithms into validated tools remain unresolved. Furthermore, the current evidence is limited by retrospective designs, selected validation cohorts, and insufficient external and prospective testing in complex real-world settings. Addressing these challenges through multidisciplinary collaboration, standardized protocols, and robust validation frameworks is critical for responsible integration of AI into routine cardiovascular imaging and for realizing its full potential in precision cardiovascular care.

来源:Korean J Radiol,查看原文。版权归原作者所有。

引用

  1. Yu, Zhang. Clinical Applications of Artificial Intelligence in Cardiac CT: From Coronary CT Angiography to CT-Derived Fractional Flow Reserve and Myocardial Perfusion Imaging. Korean J Radiol. 2026. PMID: 42683639. doi:10.3348/kjr.2025.1963

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。