文献速递心血管MR

预测ST段抬高型心肌梗死主要不良心脏事件的影像组学列线图

A radiomic nomogram for prediction of major adverse cardiac events in ST-segment elevation myocardial infarction.
PubMed 文献 · Eur Radiol · 2020-08-27

本研究回顾性纳入157例接受经皮冠状动脉介入治疗的急性ST段抬高型心肌梗死患者,基于非增强T1 mapping构建并验证影像组学列线图预测主要不良心脏事件。影像组学标签在训练集AUC为0.94、测试集为0.90;联合影像组学评分与心肌肌钙蛋白I的列线图训练集AUC为0.96、测试集为0.94。

要点

  • 非增强T1 mapping影像组学标签可用于急性STEMI患者PCI术后MACE预测。
  • 影像组学列线图联合影像组学评分与心肌肌钙蛋白I,训练集AUC 0.96、测试集AUC 0.94。
  • T1 mapping影像组学标签预测MACE优于传统心脏MRI参数。

核心结论

  • 基于非增强T1 mapping的影像组学列线图是预测急性STEMI患者PCI术后MACE的有用工具,可辅助临床医生对个体患者进行优化风险分层。

研究设计与样本

  • 回顾性研究,纳入157例连续接受PCI的急性STEMI患者,训练集109例、测试集48例。
  • 使用开源影像组学软件在非增强T1 mapping上分割心肌并提取特征,采用最小绝对收缩和选择算子法构建影像组学标签。
  • 通过区分度、校准度和临床实用性评估影像组学列线图在训练集和测试集中预测MACE的性能。

诊断标准与关键数值

  • 影像组学标签预测MACE:训练集AUC 0.94(95%CI 0.86至1.00),F1评分0.71;测试集AUC 0.90(95%CI 0.74至1.00),F1评分0.62。
  • 影像组学列线图(影像组学评分+心肌肌钙蛋白I)预测MACE:训练集AUC 0.96(95%CI 0.91至1.00),F1评分0.71;测试集AUC 0.94(95%CI 0.83至1.00),F1评分0.70。

临床应用与阅片要点

  • 原文结论认为该列线图可辅助临床医生对急性STEMI患者进行优化的个体化风险分层。
  • T1 mapping影像组学标签在预测MACE方面优于传统心脏MRI参数。

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)。

英文原文(摘要)· 点击展开

OBJECTIVES: This study was conducted to establish and validate a non-contrast T1 map-based radiomic nomogram for predicting major adverse cardiac events (MACEs) in patients with acute ST-segment elevation myocardial infarction (STEMI) undergoing percutaneous coronary intervention (PCI).

METHODS: This retrospective study included 157 consecutive patients (training sets, 109 patients; test sets, 48 patients) with acute STEMI undergoing PCI. An open-source radiomics software was used to segment the myocardium on the non-contrast T1 mapping and extract features. A radiomic signature was constructed to predict MACEs using the least absolute shrinkage and selection operator method. The performance of the radiomic nomogram for predicting MACEs in both the training and test sets was evaluated by its discrimination, calibration, and clinical usefulness.

RESULTS: The radiomic signature showed a good prognostic ability in the training sets with an AUC of 0.94 (95% CI, 0.86 to 1.00) and F1 score of 0.71, which was confirmed in the test sets with an AUC of 0.90 (95% CI, 0.74 to 1.00) and F1 score of 0.62. The nomogram consisting of the radiomic scores and cardiac troponin I showed good discrimination ability in the training and test sets with AUCs of 0.96 (95% CI, 0.91 to 1.00; F1 score, 0.71) and 0.94 (95% CI, 0.83 to 1.00; F1 score, 0.70), respectively.

CONCLUSIONS: The non-contrast T1 map-based radiomic nomogram is a useful tool for the prediction of MACEs in patients with acute STEMI undergoing PCI that can assist clinicians for optimised risk stratification of individual patients.

KEY POINTS: • Radiomic signature improved MACE prediction in acute STEMI patients. • T1 mapping-derived radiomic signature outperformed conventional cardiac MRI parameters in predicting MACEs in acute STEMI patients. • The non-contrast T1 mapping-based radiomic nomogram can be used for prediction of MACEs and improvement of risk stratification in acute STEMI.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Ma Q, Ma Y, Wang X, et al. A radiomic nomogram for prediction of major adverse cardiac events in ST-segment elevation myocardial infarction. Eur Radiol. 2020. PMID: 32856164. doi:10.1007/s00330-020-07176-y

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。