基于CCTA的冠周脂肪影像组学特征对支架内再狭窄的诊断效能
本研究纳入165例患者共214条血管(79条存在支架内再狭窄),从支架周围冠周脂肪分割中提取1688个影像组学特征,按7:3随机分为训练组和验证组,采用五种机器学习算法构建影像组学模型及联合临床特征的整合模型。验证组中影像组学模型和整合模型的AUC分别为0.69和0.79;支架直径≤3 mm亚组中基于15个特征的影像组学模型和整合模型AUC分别为0.82和0.85。结论认为CCTA冠周脂肪影像组学特征有望无额外费用或辐射地识别支架内再狭窄。
要点
- CCTA冠周脂肪影像组学可辅助识别支架内再狭窄,整合模型验证组AUC为0.79。
- 支架直径≤3 mm亚组诊断效能更优,整合模型验证组AUC达0.85。
- 该方法无需额外扫描,不增加费用和辐射,可作为CCTA后处理分析。
核心结论
- 基于CCTA的冠周脂肪影像组学特征有潜力识别冠状动脉支架内再狭窄,且不增加额外费用或辐射暴露。
研究设计与样本
- 单中心回顾性研究,纳入165例患者共214条 eligible 血管,其中79条存在支架内再狭窄。
- 从每条血管支架周围冠周脂肪分割中提取1688个影像组学特征,按7:3随机分为训练组和验证组。
- 采用Pearson相关、F检验和LASSO进行特征筛选,使用逻辑回归、支持向量机、随机森林、随机梯度下降和XGBoost五种机器学习算法构建模型。
- 参考标准为支架内再狭窄,评估临床特征、支架特征、支架周围脂肪衰减指数和PCAT体积。
诊断标准与关键数值
- 验证组中影像组学模型(基于9个特征)AUC为0.69,整合模型(联合临床特征和Radscore)AUC为0.79。
- 支架直径≤3 mm亚组中,基于15个特征的影像组学模型验证组AUC为0.82,整合模型AUC为0.85。
临床应用与阅片要点
- 在CCTA报告支架内再狭窄风险时,可关注支架周围冠周脂肪的影像组学特征,尤其对支架直径≤3 mm的病例。
- 整合临床特征与影像组学评分可提高诊断效能,阅片时可结合两者综合判断。
- 该方法无需额外扫描或辐射,可作为CCTA后处理分析的一部分,辅助识别高再狭窄风险患者。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: Coronary inflammation can alter the perivascular fat phenotype. Hence, we aimed to assess the diagnostic performance of radiomics features of pericoronary adipose tissue (PCAT) in coronary computed tomography angiography (CCTA) for in-stent restenosis (ISR) after percutaneous coronary intervention.
MATERIALS AND METHODS: In this study, 165 patients with 214 eligible vessels were included, and ISR was found in 79 vessels. After evaluating clinical and stent characteristics, peri-stent fat attenuation index, and PCAT volume, 1688 radiomics features were extracted from each peri-stent PCAT segmentation. The eligible vessels were randomly categorized into training and validation groups in a ratio of 7:3. After performing feature selection using Pearson's correlation, F test, and least absolute shrinkage and selection operator analysis, radiomics models and integrated models that combined selected clinical features and Radscore were established using five different machine learning algorithms (logistic regression, support vector machine, random forest, stochastic gradient descent, and XGBoost). Subgroup analysis was performed using the same method for patients with stent diameters of ≤ 3 mm.
RESULTS: Nine significant radiomics features were selected, and the areas under the curves (AUCs) for the radiomics model and the integrated model were 0.69 and 0.79, respectively, for the validation group. The AUCs of the subgroup radiomics model based on 15 selected radiomics features and the subgroup integrated model were 0.82 and 0.85, respectively, for the validation group, which showed better diagnostic performance.
CONCLUSION: CCTA-based radiomics signature of PCAT has the potential to identify coronary artery ISR without additional costs or radiation exposure.
引用
- Cui, Liang, Hua, et al. Diagnostic Performance of Machine Learning-Derived Radiomics Signature of Pericoronary Adipose Tissue in Coronary Computed Tomography Angiography for Coronary Artery In-Stent Restenosis. Acad Radiol. 2023. PMID: 37268514. doi:10.1016/j.acra.2023.04.006
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。