文献速递心脏核医学

机器学习和深度学习模型用于心肌血流量正电子发射断层显像准确检测缺血和瘢痕

Machine and deep learning models for accurate detection of ischemia and scar with myocardial blood flow positron emission tomography imaging.
PubMed 文献 · J Nucl Cardiol · 2024-01-05

本研究纳入3245例静息和负荷铷-82正电子发射断层显像(PET)检查及匹配的灌注报告诊断标签,比较传统统计学、机器学习和深度学习技术仅用静息和负荷心肌血流量(MBF)值诊断疾病的能力,发现机器学习模型在逐患者检测疾病时AUC显著高于传统统计学模型,但在逐血管定位缺血或瘢痕时无显著差异。

要点

  • 机器学习模型逐患者检测疾病的AUC为0.92-0.95,显著高于传统统计学模型的0.87。
  • 随机森林在比较的模型中AUC最高,达0.95。
  • 在最终留出集上,随机森林检测的AUC为0.92,定位灌注异常的AUC为0.89。

核心结论

  • 对于逐血管定位,在节段数据上训练的简单模型与在极图数据上训练的卷积神经网络表现相似,突出表明需要通过与传统简单方法比较来证明使用复杂预测算法的合理性。

研究设计与样本

  • 本研究纳入3245例静息和负荷铷-82正电子发射断层显像(PET)检查及匹配的灌注报告诊断标签。
  • 比较了标准逻辑回归、套索逻辑回归、支持向量机、随机森林、多层感知机和密集U-Net用于逐患者检测和逐血管定位瘢痕和缺血。

主要发现

  • 机器学习模型逐患者检测疾病的受试者工作特征曲线下面积(AUC)为0.92-0.95,显著高于传统统计学模型的0.87。
  • 机器学习模型与统统计学模型在逐血管定位缺血或瘢痕方面无显著差异。
  • 随机森林在比较的不同模型中AUC最高,为0.95。
  • 在用于泛化性的最终留出集上,随机森林检测的AUC为0.92,定位灌注异常的AUC为0.89。

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: Quantification of myocardial blood flow (MBF) is used for the noninvasive diagnosis of patients with coronary artery disease (CAD). This study compared traditional statistics, machine learning, and deep learning techniques in their ability to diagnose disease using only the rest and stress MBF values. METHODS: This study included 3245 rest and stress rubidium-82 positron emission tomography (PET) studies and matching diagnostic labels from perfusion reports. Standard logistic regression, lasso logistic regression, support vector machine, random forest, multilayer perceptron, and dense U-Net were compared for per-patient detection and per-vessel localization of scars and ischemia. RESULTS: Receiver-operator characteristic area under the curve (AUC) of machine learning models was significantly higher than those of traditional statistics models for per-patient detection of disease (0.92-0.95 vs. 0.87) but not for per-vessel localization of ischemia or scar. Random forest showed the highest AUC = 0.95 among the different models compared. On the final hold-out set for generalizability, random forest showed an AUC of 0.92 for detection and 0.89 for localization of perfusion abnormalities. CONCLUSIONS: For per-vessel localization, simple models trained on segmental data performed similarly to a convolutional neural network trained on polar-map data, highlighting the need to justify the use of complex predictive algorithms through comparison with simpler methods.

来源:J Nucl Cardiol,查看原文。版权归原作者所有。

引用

  1. Berman D, Hunter C, Hossain A, et al. Machine and deep learning models for accurate detection of ischemia and scar with myocardial blood flow positron emission tomography imaging. J Nucl Cardiol. 2024. PMID: 38185409. doi:10.1016/j.nuclcard.2024.101797

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。