基于冠状动脉周围脂肪组织影像组学预测急性冠脉综合征

Predicting acute coronary syndrome based on the radiomics of pericoronary adipose tissue

目的探究基于冠状动脉周围脂肪组织(PCAT)影像组学预测急性冠脉综合征(ACS)的临床价值。方法回顾性分析兰州大学第二医院2015年1月-2021年6月经临床诊断为ACS、慢性冠脉综合征(CCS)及无冠心病(CHD)的患者,将其随机分为训练队列和测试队列,并全自动提取患者左前降支、左回旋支及右冠状动脉近端的PCAT影像组学特征,使用最小绝对值收敛和选择算子回归筛选特征,基于最终筛选结果分别构建ACS的预测模型并使用受试者操作特性曲线评价预测模型。结果构建的所有模型在训练队列和测试队列的诊断性能都较高(曲线下面积均>0.85)。结论基于PCAT影像组学构建的预测模型可以有效预测临床上具有ACS风险的患者。

Objective To investigate the clinical value of predicting acute coronary syndrome(ACS)based on the radiomics of pericoronary adipose tissue(PCAT).Methods A retrospective analysis was made of patients clinically diagnosed with ACS,chronic coronary syndrome and without coronary heart disease between January 2015 and June 2021 in the Second Hospital of Lanzhou University.Patients were randomized into the training cohort and the testing cohort and the PCAT radiomic features of the proximal left anterior descending branch,left circumflex branch and right coronary artery were extracted fully automated.The features were screened using least absolute shrinkage and selection operator regression,and the prediction models for ACS were constructed based on the final screening results and were evaluated using receiver operating characteristic curves,respectively.Results All models constructed had a high diagnostic performance in both the training cohort and the testing cohorts(area under the curve values all>0.85).Conclusion The prediction model constructed based on PCAT radiomics can effectively predict patients with the risk of ACS in clinical practice.