Tong Jing, Zhang Libo, Bei Guiguang, Liu Wenyuan, Zou Mingyu, Li Yuze, Li Xiaogang, Sun Yu, Wang Xinrui, Zhu Jingya, Wang Zhenguo, Yang Benqiang
Department of Radiology, General Hospital of Northern Theater Command, 83 Wenhua Road, Shenyang, Liaoning Province, 110016, China.
Key Laboratory of Cardiovascular Imaging and Research of Liaoning Province, Shenyang, China.
BMC Med Imaging. 2025 Jul 1;25(1):258. doi: 10.1186/s12880-025-01792-0.
At present, the diagnosis of coronary slow flow (CSF) relies on coronary angiography, and non-invasive imaging examinations for the diagnosis of CSF have not been fully studied. This study aimed to explore the value of diagnosing CSF based on epicardial adipose tissue (EAT) radiomics in chest computed tomography (CT).
This retrospective study included 211 patients who underwent coronary angiography showing coronary artery stenosis < 40% from January 2020 to December 2021 and underwent chest CT within 2 weeks before angiography. According to the thrombolysis in myocardial infarction flow grade, the patients were divided into CSF group (n = 103) and normal coronary flow group (n = 108). Establish an automatic method for segmenting EAT on chest CT images. Patients were randomly divided into a training set (n = 148) and a validation set (n = 63) at a ratio of 7:3, and then radiomics features were extracted. Features selected using the maximum relevance minimum redundancy and the least absolute shrinkage and selection operator were adopted to construct an EAT radiomics model. The diagnostic efficacy of the model for CSF was evaluated using the area under the receiver operating characteristic curve. The consistency between the model and the actual results was evaluated using calibration curves, and the clinical application value of the model was evaluated using decision curve analysis.
16 radiomics features were retained to establish an EAT radiomics model for diagnosing CSF. The model had an AUC of 0.81, sensitivity of 0.72, specificity of 0.79, and accuracy of 0.76 for diagnosing CSF in the training set, and an AUC of 0.77, sensitivity of 0.82, specificity of 0.71, and accuracy of 0.77 in the validation set. The calibration curves showed good consistency between the model and the actual results, while the decision analysis curves showed good overall net benefits of the model within most reasonable threshold probability ranges.
The EAT radiomics model based on chest CT had good diagnostic efficacy for CSF and may become a potential non-invasive tool for diagnosing CSF.
目前，冠状动脉慢血流（CSF）的诊断依赖于冠状动脉造影，而用于CSF诊断的非侵入性成像检查尚未得到充分研究。本研究旨在探讨基于胸部计算机断层扫描（CT）中的心外膜脂肪组织（EAT）影像组学诊断CSF的价值。
这项回顾性研究纳入了2020年1月至2021年12月期间接受冠状动脉造影显示冠状动脉狭窄<40%且在造影前2周内接受胸部CT检查的211例患者。根据心肌梗死溶栓血流分级，将患者分为CSF组（n = 103）和正常冠状动脉血流组（n = 108）。建立胸部CT图像上EAT的自动分割方法。患者按7:3的比例随机分为训练集（n = 148）和验证集（n = 63），然后提取影像组学特征。采用最大相关最小冗余法和最小绝对收缩和选择算子选择的特征构建EAT影像组学模型。使用受试者操作特征曲线下面积评估模型对CSF的诊断效能。使用校准曲线评估模型与实际结果之间的一致性，并使用决策曲线分析评估模型的临床应用价值。
保留16个影像组学特征以建立用于诊断CSF的EAT影像组学模型。该模型在训练集中诊断CSF的AUC为0.81，灵敏度为0.72，特异性为0.79，准确率为0.76；在验证集中AUC为0.77，灵敏度为0.82，特异性为0.71，准确率为0.77。校准曲线显示模型与实际结果之间具有良好的一致性，而决策分析曲线显示在大多数合理的阈值概率范围内模型具有良好的总体净效益。
基于胸部CT的EAT影像组学模型对CSF具有良好的诊断效能，可能成为诊断CSF的潜在非侵入性工具。
