深度学习量化冠状动脉斑块体积的增量预测价值:SCAPIS 队列分析
本研究基于瑞典 SCAPIS 人群队列 23314 名 50-64 岁无动脉粥样硬化性心血管病史参与者,采用深度学习软件自动量化冠状动脉 CTA 总斑块体积(TPV)与非钙化斑块体积(NCPV),中位随访 7.8 年,共发生 287 例冠心病死亡或心肌梗死事件。结果显示 TPV 与 NCPV 均与事件风险呈阶梯式正相关,TPV 加入含 SCORE2 与节段受累积分(SIS)的模型后 C 统计量由 0.783 升至 0.798(P=0.022),净重分类改善指数为 0.093(95%CI:0.041-0.146)。最高 TPV 分类的 HR 达 6.36(95%CI:3.00-13.52)。
要点
- 冠状动脉 CTA 自动量化斑块体积可独立于 SCORE2、CAC 积分及人工 CTA 指标预测首次冠脉事件
- TPV 最高分类的 HR 达 6.36,报告时应标注斑块体积分类而非仅报有无斑块
- CAC 积分为 0 或人工判读无粥样硬化者中斑块体积仍与事件风险正相关
核心结论
- 深度学习自动量化的 TPV 在 SCORE2、CAC 积分及人工 CTA 指标基础上改善首次冠脉事件预测
- 即使小斑块体积也与一般无确诊动脉粥样硬化性心血管疾病人群的风险增加相关
研究设计与样本
- 研究类型为基于人群的前瞻性队列分析,样本量 23314 人,来自瑞典 SCAPIS 单中心人群队列
- 纳入 50-64 岁随机选取的无动脉粥样硬化性心血管病史参与者,具备 SCORE2 数据及可接受质量的冠状动脉 CTA
- TPV 与 NCPV 采用自动化深度学习软件量化并分为 6 个等级,随访终点为冠心病死亡或心肌梗死,中位随访 7.8 年
关键影像表现/征象
- 事件风险随 TPV 与 NCPV 增高呈阶梯式上升,包括 CAC 积分为 0 及人工判读无粥样硬化的参与者
- 加入 ≥50% 狭窄或仅有非钙化斑块的任何节段均未实质改善 C 统计量
诊断标准与关键数值
- 事件风险随 TPV 与 NCPV 增高呈阶梯式上升,最高 TPV 分类的 HR 为 6.36(95%CI:3.00-13.52)
- 加入 TPV 后模型 C 统计量为 0.798,对照模型为 0.783,P=0.022
- TPV 的净重分类改善指数为 0.093(95%CI:0.041-0.146)
- 以 NCPV 替代 TPV 得到相近结果
临床应用与阅片要点
- 在报告中记录自动量化的冠脉斑块体积分类,有助于在传统风险模型之外识别高危患者
- CAC 积分为 0 或人工读片未见粥样硬化时仍需关注斑块体积所提示的残余风险
局限性
- 研究人群仅限 50-64 岁瑞典一般人群,结果外推至其他年龄段或种族人群需谨慎
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
BACKGROUND: Coronary plaque volume assessed by coronary computed tomography angiography (CTA) may refine risk assessment beyond established risk models.
OBJECTIVES: This study aims to evaluate whether deep learning-derived coronary plaque volume from coronary CTA improves prediction beyond established risk models and imaging markers in a general population.
METHODS: Participants were randomly selected men and women 50-64 years of age from a population-based cohort, without prior atherosclerotic cardiovascular disease, with available SCORE2 (Systematic Coronary Risk Evaluation 2) data and coronary CTAs of acceptable quality. Total plaque volume (TPV) and noncalcified plaque volume (NCPV) were quantified using automated deep learning software and stratified into 6 categories. Participants were followed for coronary heart disease death or myocardial infarction over a median of 7.8 years.
RESULTS: Among 23,314 participants, 287 coronary events occurred. Risk of events increased stepwise with increasing TPV and NCPV, including among participants with coronary artery calcium score = 0 and in those without manually detected atherosclerosis. In Cox regression analyses, adding TPV to a model including SCORE2 and segment involvement score significantly improved model performance (C-statistic: 0.798 vs 0.783; P = 0.022) and net reclassification index (0.093; 95% CI: 0.041-0.146). HRs increased with higher TPV categories, reaching 6.36 (95% CI: 3.00-13.52) in the highest category. Adding presence of stenosis ≥50% or any segment with only noncalcified plaque did not materially improve the C-statistic. Replacing TPV with NCPV yielded similar results.
CONCLUSIONS: Automated deep learning-quantified TPV improved prediction of first coronary events beyond SCORE2, coronary artery calcium score, and manually derived coronary CTA measurements, and identified even small plaque volumes associated with increased risk in a general population without established atherosclerotic cardiovascular disease.
引用
- Malmqvist, Wang, Bergström, et al. Incremental Predictive Value of Deep Learning-Quantified Coronary Atherosclerotic Volume: A SCAPIS Cohort Analysis. JACC Cardiovasc Imaging. 2026. PMID: 42663364. doi:10.1016/j.jcmg.2026.08.004
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。