A novel machine learning-derived radiotranscriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiography
A novel machine learning-derived radiotranscriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiography
复制标题
DOI：
10.1093/eurheartj/ehz592
复制
发表时间：
2019-11-14
影响因子：
39.3
通讯作者：
Antoniades, Charalambos
中科院分区：
文献类型：
--
作者：
Oikonomou, Evangelos K.;Williams, Michelle C.;Antoniades, Charalambos
背景冠状动脉炎症会引起血管周围脂肪组织（PVAT）中水和脂质含量平衡的动态变化，正如标准冠状动脉CT血管造影（CCTA）中血管周围脂肪衰减指数（FAI）所捕获的那样。然而，炎症并不是参与动脉粥样硬化形成的唯一过程，我们假设不良纤维化和微血管 PVAT 重塑的额外放射组学特征可能会进一步改善心脏风险预测。方法和结果我们提出了一种新的人工智能驱动的方法，通过分析冠状动脉 PVAT 的放射组学特征来预测心脏风险，该方法在三项不同研究中获得的患者队列中开发和验证。在研究 1 中，从 167 名接受心脏手术的患者身上获取了脂肪组织活检样本，代表炎症、纤维化和血管的基因表达与从组织 CT 图像中提取的放射组学特征相关。脂肪组织小波变换平均衰减（由 FAI 捕获）是描述组织炎症（TNFA 表达）最敏感的放射组学特征，而放射组学纹理特征与脂肪组织纤维化（COL1A1 表达）和血管分布（CD31 表达）相关。在研究 2 中，我们分析了 101 名在接受 CCTA 后 5 年内经历过主要不良心脏事件 (MACE) 的患者的 1391 个冠状动脉 PVAT 放射组学特征，以及 101 名匹配对照，训练和验证机器学习（随机森林）算法（脂肪放射组学特征，FRP）以区分病例和对照（外部验证集中的 C 统计量 0.77 [95%CI：0.62-0.93]）。然后，在 SCOT-HEART 试验中，对 1575 名连续合格参与者进行了冠状动脉 FRP 特征测试，与传统风险分层相比，它显着改善了 MACE 预测，传统风险分层包括危险因素、冠状动脉钙评分、冠状动脉狭窄和 CCTA 上的高风险斑块特征（Delta[C-统计] = 0.126，P
Background Coronary inflammation induces dynamic changes in the balance between water and lipid content in perivascular adipose tissue (PVAT), as captured by perivascular Fat Attenuation Index (FAI) in standard coronary CT angiography (CCTA). However, inflammation is not the only process involved in atherogenesis and we hypothesized that additional radiomic signatures of adverse fibrotic and microvascular PVAT remodelling, may further improve cardiac risk prediction.Methods and results We present a new artificial intelligence-powered method to predict cardiac risk by analysing the radiomic profile of coronary PVAT, developed and validated in patient cohorts acquired in three different studies. In Study 1, adipose tissue biopsies were obtained from 167 patients undergoing cardiac surgery, and the expression of genes representing inflammation, fibrosis and vascularity was linked with the radiomic features extracted from tissue CT images. Adipose tissue wavelet-transformed mean attenuation (captured by FAI) was the most sensitive radiomic feature in describing tissue inflammation (TNFA expression), while features of radiomic texture were related to adipose tissue fibrosis (COL1A1 expression) and vascularity (CD31 expression). In Study 2, we analysed 1391 coronary PVAT radiomic features in 101 patients who experienced major adverse cardiac events (MACE) within 5years of having a CCTA and 101 matched controls, training and validating a machine learning (random forest) algorithm (fat radiomic profile, FRP) to discriminate cases from controls (C-statistic 0.77 [95%CI: 0.62-0.93] in the external validation set). The coronary FRP signature was then tested in 1575 consecutive eligible participants in the SCOT-HEART trial, where it significantly improved MACE prediction beyond traditional risk stratification that included risk factors, coronary calcium score, coronary stenosis, and high-risk plaque features on CCTA (Delta[C-statistic] = 0.126, P