Abstract：
OBJECTIVE: This study investigated the additional prognostic value of epicardial adipose tissue (EAT) volume for major adverse cardiovascular events (MACE) in patients undergoing stress cardiac magnetic resonance (CMR) imaging.
METHODS: 730 consecutive patients [mean age: 63 ± 10 years; 616 men] who underwent stress CMR for known or suspected coronary artery disease were randomly divided into derivation (n = 365) and validation (n = 365) cohorts. MACE was defined as non-fatal myocardial infarction and cardiac deaths. A deep learning algorithm was developed and trained to quantify EAT volume from CMR. EAT volume was adjusted for height (EAT volume index). A composite CMR-based risk score by Cox analysis of the risk of MACE was created.
RESULTS: In the derivation cohort, 32 patients (8.7 %) developed MACE during a follow-up of 2103 days. Left ventricular ejection fraction (LVEF) < 35 % (HR 4.407 [95 % CI 1.903-10.202]; p<0.001), stress perfusion defect (HR 3.550 [95 % CI 1.765-7.138]; p<0.001), late gadolinium enhancement (LGE) (HR 4.428 [95%CI 1.822-10.759]; p = 0.001) and EAT volume index (HR 1.082 [95 % CI 1.045-1.120]; p<0.001) were independent predictors of MACE. In a multivariate Cox regression analysis, adding EAT volume index to a composite risk score including LVEF, stress perfusion defect and LGE provided additional value in MACE prediction, with a net reclassification improvement of 0.683 (95%CI, 0.336-1.03; p<0.001). The combined evaluation of risk score and EAT volume index showed a higher Harrel C statistic as compared to risk score (0.85 vs. 0.76; p<0.001) and EAT volume index alone (0.85 vs.0.74; p<0.001). These findings were confirmed in the validation cohort.
CONCLUSIONS: In patients with clinically indicated stress CMR, fully automated EAT volume measured by deep learning can provide additional prognostic information on top of standard clinical and imaging parameters.
METHODS: 730 consecutive patients [mean age: 63 ± 10 years; 616 men] who underwent stress CMR for known or suspected coronary artery disease were randomly divided into derivation (n = 365) and validation (n = 365) cohorts. MACE was defined as non-fatal myocardial infarction and cardiac deaths. A deep learning algorithm was developed and trained to quantify EAT volume from CMR. EAT volume was adjusted for height (EAT volume index). A composite CMR-based risk score by Cox analysis of the risk of MACE was created.
RESULTS: In the derivation cohort, 32 patients (8.7 %) developed MACE during a follow-up of 2103 days. Left ventricular ejection fraction (LVEF) < 35 % (HR 4.407 [95 % CI 1.903-10.202]; p<0.001), stress perfusion defect (HR 3.550 [95 % CI 1.765-7.138]; p<0.001), late gadolinium enhancement (LGE) (HR 4.428 [95%CI 1.822-10.759]; p = 0.001) and EAT volume index (HR 1.082 [95 % CI 1.045-1.120]; p<0.001) were independent predictors of MACE. In a multivariate Cox regression analysis, adding EAT volume index to a composite risk score including LVEF, stress perfusion defect and LGE provided additional value in MACE prediction, with a net reclassification improvement of 0.683 (95%CI, 0.336-1.03; p<0.001). The combined evaluation of risk score and EAT volume index showed a higher Harrel C statistic as compared to risk score (0.85 vs. 0.76; p<0.001) and EAT volume index alone (0.85 vs.0.74; p<0.001). These findings were confirmed in the validation cohort.
CONCLUSIONS: In patients with clinically indicated stress CMR, fully automated EAT volume measured by deep learning can provide additional prognostic information on top of standard clinical and imaging parameters.
摘要：
目的：本研究调查了心外膜脂肪组织（EAT）体积对接受压力心脏磁共振（CMR）成像的患者主要不良心血管事件（MACE）的额外预后价值。
方法：730名连续患者[平均年龄：63±10岁；616名男性]因已知或疑似冠状动脉疾病而接受应激性CMR，随机分为推导组（n=365）和验证组（n=365）。MACE定义为非致死性心肌梗死和心脏死亡。开发并训练了一种深度学习算法，以量化CMR的EAT量。针对高度调整EAT体积(EAT体积指数)。通过Cox分析MACE的风险，创建了基于CMR的复合风险评分。
结果：在派生队列中，32例患者（8.7%）在2103天的随访期间发生MACE。左心室射血分数(LVEF)<35%(HR4.407[95%CI1.903-10.202];p<0.001),应力灌注缺损(HR3.550[95%CI1.765-7.138]；p<0.001)，钆晚期增强(LGE)(HR4.428[95CI1.822-10.759];p=0.001)和进食量指数(HR1.082[95%CI1.045-1.120];p<0.001)是MACE的独立预测因子。在多元Cox回归分析中，将EAT容量指数添加到包括LVEF在内的综合风险评分中，应力灌注缺陷和LGE在MACE预测中提供了额外的价值，净重新分类改善0.683（95CI，0.336-1.03；p<0.001）。与风险评分相比，风险评分和EAT体积指数的综合评估显示出较高的HarrelC统计量（0.85vs.0.76；p<0.001）和单独的EAT体积指数（0.85vs.0.74；p<0.001）。这些发现在验证队列中得到证实。
结论：在有临床指示应激CMR的患者中，通过深度学习测量的全自动EAT体积可以在标准临床和成像参数之上提供额外的预后信息。
方法：730名连续患者[平均年龄：63±10岁；616名男性]因已知或疑似冠状动脉疾病而接受应激性CMR，随机分为推导组（n=365）和验证组（n=365）。MACE定义为非致死性心肌梗死和心脏死亡。开发并训练了一种深度学习算法，以量化CMR的EAT量。针对高度调整EAT体积(EAT体积指数)。通过Cox分析MACE的风险，创建了基于CMR的复合风险评分。
结果：在派生队列中，32例患者（8.7%）在2103天的随访期间发生MACE。左心室射血分数(LVEF)<35%(HR4.407[95%CI1.903-10.202];p<0.001),应力灌注缺损(HR3.550[95%CI1.765-7.138]；p<0.001)，钆晚期增强(LGE)(HR4.428[95CI1.822-10.759];p=0.001)和进食量指数(HR1.082[95%CI1.045-1.120];p<0.001)是MACE的独立预测因子。在多元Cox回归分析中，将EAT容量指数添加到包括LVEF在内的综合风险评分中，应力灌注缺陷和LGE在MACE预测中提供了额外的价值，净重新分类改善0.683（95CI，0.336-1.03；p<0.001）。与风险评分相比，风险评分和EAT体积指数的综合评估显示出较高的HarrelC统计量（0.85vs.0.76；p<0.001）和单独的EAT体积指数（0.85vs.0.74；p<0.001）。这些发现在验证队列中得到证实。
结论：在有临床指示应激CMR的患者中，通过深度学习测量的全自动EAT体积可以在标准临床和成像参数之上提供额外的预后信息。
