文献速递心脏核医学

使用CZT相机的心肌灌注图像通过深度学习预测定量冠状动脉造影值

Deep learning prediction of quantitative coronary angiography values using myocardial perfusion images with a CZT camera.
PubMed 文献 · J Nucl Cardiol · 2022-05-24

本研究纳入546例在CZT相机行仰卧位和俯卧位负荷99mTc-替曲膦心肌灌注显像的患者(共1092次MPI),分为冠状动脉造影组271例和对照组275例,训练深度学习模型预测定量冠状动脉造影值。外部测试队列中,预测冠状动脉狭窄>50%的受试者工作特征曲线下面积按患者为85%(95%CI 84%-87%),按血管LAD为74%(CI 72%-76%)、RCA为85%(CI 83%-86%)、LCx为81%(CI 78%-84%),平均80%(CI 77%-83%)。

要点

  • 深度学习可从MPI预测QCA所示冠状动脉狭窄>50%的存在。
  • 外部测试队列按患者的AUC为85%(95%CI 84%-87%)。
  • 按血管AUC为LAD 74%、RCA 85%、LCx 81%,平均80%。

核心结论

  • 深度学习可从MPI预测不同QCA百分比冠状动脉狭窄的存在。

研究设计与样本

  • 研究纳入546例(67%为男性)在CZT相机行仰卧位和俯卧位负荷99mTc-替曲膦MPI的患者,共1092次MPI。
  • 患者分为ICA组271例(MPI后6个月内行ICA)和对照组275例(CAD验前概率低且MPI正常)。
  • QCA分析使用放射学软件并由专家读者核实,左心室心肌使用临床核心脏病学软件分割并由专家读者核实。
  • 深度学习模型采用双重交叉验证方案训练,使所有数据也可用作测试数据。

主要发现

  • 外部测试队列中,深度学习预测QCA冠状动脉狭窄>50%的AUC按患者为85%(95%CI 84%-87%)。
  • 外部测试队列中,按血管AUC为LAD 74%(CI 72%-76%)、RCA 85%(CI 83%-86%)、LCx 81%(CI 78%-84%),平均80%(CI 77%-83%)。

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)。

原文

PURPOSE: Evaluate the prediction of quantitative coronary angiography (QCA) values from MPI, by means of deep learning. METHODS: 546 patients (67% men) undergoing stress 99mTc-tetrofosmin MPI in a CZT camera in the upright and supine position were included (1092 MPIs). Patients were divided into two groups: ICA group included 271 patients who performed an ICA within 6 months of MPI and a control group with 275 patients with low pre-test probability for CAD and a normal MPI. QCA analyses were performed using radiologic software and verified by an expert reader. Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. A deep learning model was trained using a double cross-validation scheme such that all data could be used as test data as well. RESULTS: Area under the receiver-operating characteristic curve for the prediction of QCA, with > 50% narrowing of the artery, by deep learning for the external test cohort: per patient 85% [95% confidence interval (CI) 84%-87%] and per vessel; LAD 74% (CI 72%-76%), RCA 85% (CI 83%-86%), LCx 81% (CI 78%-84%), and average 80% (CI 77%-83%). CONCLUSION: Deep learning can predict the presence of different QCA percentages of coronary artery stenosis from MPIs.

来源:J Nucl Cardiol,查看原文。版权归原作者所有。

引用

  1. Arvidsson I, Davidsson A, Overgaard NC, et al. Deep learning prediction of quantitative coronary angiography values using myocardial perfusion images with a CZT camera. J Nucl Cardiol. 2022. PMID: 35610536. doi:10.1007/s12350-022-02995-6

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。