Zhan Weisheng, Li Yixin, Luo Hui, He Jiang, Long Jiao, Xu Yang, Yang Ying
Cardiovascular Medicine Department, Affiliated Hospital of North Sichuan Medical College, Nanchong, China.
Digestive System Department, Affiliated Hospital of North Sichuan Medical College, Nanchong, China.
Front Cardiovasc Med. 2024 Dec 12;11:1462566. doi: 10.3389/fcvm.2024.1462566. eCollection 2024.
To explore whether radiomics analysis of pericoronary adipose tissue (PCAT) captured by coronary computed tomography angiography (CCTA) could discriminate unstable angina (UA) from stable angina (SA).
In this single-center retrospective case-control study, coronary CT images and clinical data from 240 angina patients were collected and analyzed. Patients with unstable angina ( = 120) were well-matched with those having stable angina ( = 120). All patients were randomly divided into training (70%) and testing (30%) datasets. Automatic segmentation was performed on the pericoronary adipose tissue surrounding the proximal segments of the left anterior descending artery (LAD), left circumflex coronary artery (LCX), and right coronary artery (RCA). Corresponding radiomic features were extracted and selected, and the fat attenuation index (FAI) for these three vessels was quantified. Machine learning techniques were employed to construct the FAI and radiomic models. Multivariate logistic regression analysis was used to identify the most relevant clinical features, which were then combined with radiomic features to create clinical and integrated models. The performance of different models was compared in terms of area under the curve (AUC), calibration, clinical utility, and sensitivity.
In both training and validation cohorts, the integrated model (AUC = 0.87, 0.74) demonstrated superior discriminatory ability compared to the FAI model (AUC = 0.68, 0.51), clinical feature model (AUC = 0.84, 0.67), and radiomic model (AUC = 0.85, 0.73). The nomogram derived from the combined radiomic and clinical features exhibited excellent performance in diagnosing and predicting unstable angina. Calibration curves showed good fit for all four machine learning models. Decision curve analysis indicated that the integrated model provided better clinical benefit than the other three models.
CCTA-based radiomics signature of PCAT is better than the FAI model in identifying unstable angina and stable angina. The integrated model constructed by combining radiomics and clinical features could further improve the diagnosis and differentiation ability of unstable angina.
探讨冠状动脉计算机断层扫描血管造影（CCTA）所捕获的冠状动脉周围脂肪组织（PCAT）的放射组学分析能否区分不稳定型心绞痛（UA）和稳定型心绞痛（SA）。
在这项单中心回顾性病例对照研究中，收集并分析了240例心绞痛患者的冠状动脉CT图像和临床数据。不稳定型心绞痛患者（n = 120）与稳定型心绞痛患者（n = 120）进行了良好匹配。所有患者被随机分为训练集（70%）和测试集（30%）。对左前降支（LAD）、左旋支冠状动脉（LCX）和右冠状动脉（RCA）近端段周围的冠状动脉周围脂肪组织进行自动分割。提取并选择相应的放射组学特征，并对这三支血管的脂肪衰减指数（FAI）进行量化。采用机器学习技术构建FAI和放射组学模型。多变量逻辑回归分析用于识别最相关的临床特征，然后将其与放射组学特征相结合，创建临床模型和综合模型。比较不同模型在曲线下面积（AUC）、校准、临床实用性和敏感性方面的性能。
在训练队列和验证队列中，综合模型（AUC = 0.87，0.74）与FAI模型（AUC = 0.68，0.51）、临床特征模型（AUC = 0.84，0.67）和放射组学模型（AUC = 0.85，0.73）相比，具有更好的区分能力。由放射组学和临床特征组合得出的列线图在诊断和预测不稳定型心绞痛方面表现出色。校准曲线显示所有四种机器学习模型拟合良好。决策曲线分析表明，综合模型比其他三种模型提供了更好的临床效益。
基于CCTA的PCAT放射组学特征在识别不稳定型心绞痛和稳定型心绞痛方面优于FAI模型。将放射组学和临床特征相结合构建的综合模型可进一步提高不稳定型心绞痛的诊断和鉴别能力。
