基于放射组学驱动的机器学习从多平面CCTA图像自动进行CAD-RADS评分
本研究为回顾性单中心研究,纳入251例因临床评估冠心病而行CCTA的患者(2016-2018年),自动分割图像并提取放射组学特征,构建级联机器学习模型实现6类CAD-RADS评分及4类治疗导向分类。放射组学模型CAD-RADS评分AUC为0.88,联合模型AUC为0.90,临床模型AUC为0.66;治疗导向分类放射组学模型AUC为0.93,联合模型AUC为0.97,临床模型AUC为0.79。放射组学与联合模型在部分类别中显著优于临床模型(DeLong P<0.05)。
要点
- 放射组学联合临床模型对CAD-RADS评分AUC达0.90,治疗导向分类AUC达0.97
- 放射组学模型可解释性较高,有望作为冠状动脉狭窄评估的支持系统
- 临床模型在CAD-RADS 1类和2类及治疗导向2类中显著低于放射组学与联合模型
核心结论
- 本研究首次提出基于放射组学的CAD-RADS分类模型,具有较高可解释性,为冠状动脉狭窄评估提供有前景的支持系统。
研究设计与样本
- 回顾性单中心研究,纳入251例因临床评估冠心病于2016-2018年行CCTA的患者(男性70%,平均年龄60.5±12.7岁)。
- 图像自动分割并提取放射组学特征,同时收集临床特征。
- 数据集按90%-10%分为训练集和测试集,训练阶段在5折交叉验证内完成特征缩放与选择、数据平衡及模型训练。
- 采用级联流程分别完成6类CAD-RADS评分和4类治疗导向分类(0-1、2、3-4、5),每个分类任务构建临床、放射组学和联合模型。
诊断标准与关键数值
- CAD-RADS评分:放射组学模型AUC=0.88 [0.86-0.88],联合模型AUC=0.90 [0.88-0.90],临床模型AUC=0.66 [0.66-0.67]。
- 治疗导向分类:放射组学模型AUC=0.93 [0.91-0.93],联合模型AUC=0.97 [0.96-0.97],临床模型AUC=79 [0.78-0.79](原文此处写作79,按上下文应为0.79)。
- 放射组学和联合模型在CAD-RADS级联的1类和2类及治疗导向级联的2类中显著优于临床模型(DeLong P<0.05)。
临床应用与阅片要点
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
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
BACKGROUND: Coronary Artery Disease-Reporting and Data System (CAD-RADS), a standardized reporting system of stenosis severity from coronary computed tomography angiography (CCTA), is performed manually by expert radiologists, being time-consuming and prone to interobserver variability. While deep learning methods automating CAD-RADS scoring have been proposed, radiomics-based machine-learning approaches are lacking, despite their improved interpretability. This study aims to introduce a novel radiomics-based machine-learning approach for automating CAD-RADS scoring from CCTA images with multiplanar reconstruction.
METHODS: This retrospective monocentric study included 251 patients (male 70 %; mean age 60.5 ± 12.7) who underwent CCTA in 2016-2018 for clinical evaluation of CAD. Images were automatically segmented, and radiomic features were extracted. Clinical characteristics were collected. The image dataset was partitioned into training and test sets (90 %-10 %). The training phase encompassed feature scaling and selection, data balancing and model training within a 5-fold cross-validation. A cascade pipeline was implemented for both 6-class CAD-RADS scoring and 4-class therapy-oriented classification (0-1, 2, 3-4, 5), through consecutive sub-tasks. For each classification task the cascade pipeline was applied to develop clinical, radiomic, and combined models.
RESULTS: The radiomic, combined and clinical models yielded AUC = 0.88 [0.86-0.88], AUC = 0.90 [0.88-0.90], and AUC = 0.66 [0.66-0.67] for the CAD-RADS scoring, and AUC = 0.93 [0.91-0.93], AUC = 0.97 [0.96-0.97], and AUC = 79 [0.78-0.79] for the therapy-oriented classification. The radiomic and combined models significantly outperformed (DeLong p-value < 0.05) the clinical one in class 1 and 2 (CAD-RADS cascade) and class 2 (therapy-oriented cascade).
CONCLUSIONS: This study represents the first CAD-RADS classification radiomic model, guaranteeing higher explainability and providing a promising support system in coronary artery stenosis assessment.
引用
- Corti A, Ronchetti F, Lo Iacono F, et al. Automated CAD-RADS scoring from multiplanar CCTA images using radiomics-driven machine learning. Eur J Radiol. 2025. PMID: 40684709. doi:10.1016/j.ejrad.2025.112320
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。