Yi Yan, Xu Cheng, Wu Wei, Ge Ying-Qian, Xu Ke-Ting, Yu Xian-Bo, Wang Yi-Ning
Department of Radiology,PUMC Hospital,CAMS and PUMC,Beijing 100730,China.
Department of Cardiology,PUMC Hospital,CAMS and PUMC,Beijing 100730,China.
Zhongguo Yi Xue Ke Xue Yuan Xue Bao. 2025 Aug;47(4):542-549. doi: 10.3881/j.issn.1000-503X.16412.
Objective To develop a diagnostic model combining the CT angiography(CCTA)-derived myocardial radiomics signatures with the CT-derived fractional flow reserve(CT-FFR)based on coronary CCTA and investigate the diagnostic accuracy of the hybrid model for hemodynamically significant coronary artery disease(CAD).Methods The patients presenting stable angina pectoris,diagnosed with CAD,and clinically referred for CCTA examination and invasive coronary angiography were prospectively recruited.Radiomics features of the left ventricular myocardium were extracted from the three main perfusion territories demarcated according to the coronary blood supply.The extracted features were first selected by the minimum redundancy maximum relevance feature ranking method.A least absolute shrinkage and selection operator Logistic regression algorithm with leave-one-out cross-validation was then employed to construct a radiomics model.The CT-FFR value was generated for each blood vessel.The area under the receiver operating characteristics curve(AUC_ROC),sensitivity,and specificity were adopted to evaluate the performance of each model against the reference standard invasive coronary angiography/FFR.Results A total of 70 patients[42 men and 28 women;(61±10) years old] were included in this study and complemented CCTA examination,with 175 vessels and the corresponding myocardial territories undergoing invasive coronary angiography/FFR.A total of 1 656 specific radiomics parameters were extracted,from which 14 features were selected to establish the radiomics model.The AUC_ROC,sensitivity,and specificity were 0.797(95%=0.732-0.861),77.1%,and 73.7%for the radiomics model,0.892(95%=0.841-0.943),81.4%,and 88.8%for the CT-FFR model,and 0.928(95%=0.890-0.965),83.3%,and 88.4%for the hybrid model,respectively.The hybrid model outperformed the radiomics model and CT-FFR alone(=0.040).Conclusions The radiomics signatures of the vessel-related myocardium from CCTA could provide incremental value to the diagnostic performance of CT-FFR and improve vessel-specific ischemia detection.The hybrid model combining CT-FFR with radiomics signatures is potentially feasible for improving the diagnostic accuracy for hemodynamically significant CAD.
目的 基于冠状动脉CT血管造影（CCTA）开发一种将CCTA衍生的心肌放射组学特征与CT衍生的血流储备分数（CT-FFR）相结合的诊断模型，并研究该混合模型对血流动力学显著冠状动脉疾病（CAD）的诊断准确性。方法 前瞻性招募表现为稳定型心绞痛、诊断为CAD且临床转诊进行CCTA检查和有创冠状动脉造影的患者。根据冠状动脉供血情况，从划定的三个主要灌注区域提取左心室心肌的放射组学特征。首先通过最小冗余最大相关特征排序方法对提取的特征进行选择。然后采用带留一法交叉验证的最小绝对收缩和选择算子逻辑回归算法构建放射组学模型。为每支血管生成CT-FFR值。采用受试者工作特征曲线下面积（AUC_ROC）、敏感性和特异性来评估每个模型相对于参考标准有创冠状动脉造影/FFR的性能。结果 本研究共纳入70例患者[42例男性和28例女性；（61±10）岁]，均完成了CCTA检查，其中175支血管及其相应的心肌区域接受了有创冠状动脉造影/FFR检查。共提取了1656个特定的放射组学参数，从中选择了14个特征建立放射组学模型。放射组学模型的AUC_ROC、敏感性和特异性分别为0.797（95%=0.732-0.861）、77.1%和73.7%，CT-FFR模型分别为0.892（95%=0.841-0.943）、81.4%和88.8%，混合模型分别为0.928（95%=0.890-0.965）、83.3%和88.4%。混合模型优于单独的放射组学模型和CT-FFR（P=0.040）。结论 CCTA中与血管相关心肌的放射组学特征可为CT-FFR的诊断性能提供增量价值，并改善血管特异性缺血检测。将CT-FFR与放射组学特征相结合的混合模型在提高血流动力学显著CAD的诊断准确性方面可能是可行的。
