文献速递心脏核医学

在接受心肌灌注显像的患者中应用全自动深度学习进行钙化评分

Fully automated deep learning powered calcium scoring in patients undergoing myocardial perfusion imaging.
PubMed 文献 · J Nucl Cardiol · 2022-03-17

本研究为前瞻性研究(NCT03637231)的一部分,纳入56例因疑似冠心病接受心脏SPECT-MPI的患者,每例患者接受两次用于衰减校正的非增强CT扫描,共112次扫描。以人工评估的CACS为标准参考,与基于云端的深度学习工具进行比较,CAC评分一致性为0.986,风险分类一致性为0.977,重分类率为3.6%。结论认为深度学习工具能够全自动且准确地估计接受SPECT-MPI衰减校正非增强CT患者的CAC评分。

要点

  • 56例患者共112次非增强CT扫描,深度学习工具与人工CACS评分一致性为0.986。
  • CAC评分风险分类一致性为0.977,重分类率为3.6%。
  • 心率、图像噪声、BMI和扫描次数对CAC评分绝对百分比差异无显著影响(p=0.09至p=0.76)。

核心结论

  • 深度学习工具能够全自动且准确地估计接受SPECT-MPI衰减校正非增强CT患者的CAC评分。

研究设计与样本

  • 前瞻性研究(NCT03637231)的一部分,纳入56例因疑似冠心病接受心脏SPECT-MPI的患者。
  • 所有患者接受两次用于SPECT-MPI衰减校正的非增强CT扫描,共112次扫描。
  • 以人工评估的CACS作为标准参考,与基于云端的深度学习工具进行比较。

主要发现

  • 112次扫描中,标准参考与深度学习工具的CAC评分一致性为0.986。
  • 风险分类一致性为0.977,重分类率为3.6%。
  • 心率、图像噪声、BMI和扫描次数对CAC评分绝对百分比差异无显著影响(p=0.09至p=0.76)。

关键数值与推荐

  • CAC评分一致性为0.986。
  • 风险分类一致性为0.977。
  • 重分类率为3.6%。
  • 心率、图像噪声、BMI和扫描次数对CAC评分绝对百分比差异无显著影响(p=0.09至p=0.76)。

临床怎么用

  • 原文未据此给出推荐。

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

BACKGROUND: To assess the accuracy of fully automated deep learning (DL) based coronary artery calcium scoring (CACS) from non-contrast computed tomography (CT) as acquired for attenuation correction (AC) of cardiac single-photon-emission computed tomography myocardial perfusion imaging (SPECT-MPI). METHODS AND RESULTS: Patients were enrolled in this study as part of a larger prospective study (NCT03637231). In this study, 56 Patients who underwent cardiac SPECT-MPI due to suspected coronary artery disease (CAD) were prospectively enrolled. All patients underwent non-contrast CT for AC of SPECT-MPI twice. CACS was manually assessed (serving as standard of reference) on both CT datasets (n = 112) and by a cloud-based DL tool. The agreement in CAC scores and CAC score risk categories was quantified. For the 112 scans included in the analysis, interscore agreement between the CAC scores of the standard of reference and the DL tool was 0.986. The agreement in risk categories was 0.977 with a reclassification rate of 3.6%. Heart rate, image noise, body mass index (BMI), and scan did not significantly impact (p=0.09 - p=0.76) absolute percentage difference in CAC scores. CONCLUSION: A DL tool enables a fully automated and accurate estimation of CAC scores in patients undergoing non-contrast CT for AC of SPECT-MPI.

来源:J Nucl Cardiol,查看原文。版权归原作者所有。

引用

  1. Sartoretti T, Gennari AG, Sartoretti E, et al. Fully automated deep learning powered calcium scoring in patients undergoing myocardial perfusion imaging. J Nucl Cardiol. 2022. PMID: 35301677. doi:10.1007/s12350-022-02940-7

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。