文献速递外周血管心血管介入CT

基于CT血管成像的深度学习影像组学预测急性非复杂性Stanford B型主动脉夹层初次腔内修复术后不良事件

Deep learning-based radiomics of computed tomography angiography to predict adverse events after initial endovascular repair for acute uncomplicated Stanford type B aortic dissection.
PubMed 文献 · Eur J Radiol · 2024-04-15

回顾性纳入2015年1月至2022年12月369例因急性非复杂性Stanford B型主动脉夹层接受初次胸主动脉腔内修复术的患者,从CTA提取三维深度学习卷积神经网络影像组学特征构建Rad-Score,并与白蛋白、C反应蛋白等临床因素联合建立XGBoost模型。联合模型在训练队列AUC为1.000(95%CI 1.000-1.000),内部验证队列AUC为0.990(95%CI 0.966-1.000),另一医院独立验证队列AUC为0.985(95%CI 0.965-1.000),准确率0.92、精确率0.92、敏感度0.94、特异度0.91。作者认为该联合模型有望预测术后不良事件。

要点

  • 联合模型在另一医院独立验证队列预测术后不良事件的AUC为0.985(95%CI 0.965-1.000)。
  • 联合模型独立验证队列准确率0.92、精确率0.92、敏感度0.94、特异度0.91。
  • Rad-Score联合白蛋白和C反应蛋白使预测效能中等程度提升。

核心结论

  • 基于CTA的深度学习影像组学联合临床指标构建的模型,作者认为有望预判急性非复杂性Stanford B型主动脉夹层初次TEVAR术后不良事件。
  • 作者称该联合模型在随访期间提供预后前瞻的临床效用已得到证实。

研究设计与样本

  • 回顾性评估2015年1月至2022年12月接受TEVAR治疗的急性非复杂性Stanford B型主动脉夹层患者369例。
  • 采用三维深度卷积神经网络从CTA图像自动提取影像组学特征,经方差分析和LASSO算法筛选构建Rad-Score。
  • Rad-Score与临床参数通过极端梯度提升(XGBoost)分析建模,并以校准曲线评估模型校准。
  • 验证包括内部验证队列及来自另一医院的独立验证队列。

诊断标准与关键数值

  • 联合模型训练队列AUC为1.000(95%CI 1.000-1.000)。
  • 联合模型内部验证队列AUC为0.990(95%CI 0.966-1.000)。
  • 联合模型另一医院独立验证队列AUC为0.985(95%CI 0.965-1.000),准确率0.92、精确率0.92、敏感度0.94、特异度0.91。

临床应用与阅片要点

  • 作者认为该联合模型可在随访期间提供预后前瞻,用于预判急性非复杂性Stanford B型主动脉夹层初次TEVAR术后不良事件。

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

PURPOSE: This study aimed to construct a predictive model integrating deep learning-derived radiomic features from computed tomography angiography (CTA) and clinical biomarkers to forecast postoperative adverse events (AEs) in patients with acute uncomplicated Stanford type B aortic dissection (uTBAD) undergoing initial thoracic endovascular aortic repair (TEVAR).

METHODS: We retrospectively evaluated 369 patients treated with TEVAR for acute uTBAD from January 2015 to December 2022. A three-dimensional (3D) deep convolutional neural network (CNN) automated radiomic feature extraction from CTA images. Feature selection, using Analysis of Variance (ANOVA) and the Least Absolute Shrinkage and Selection Operator (LASSO) algorithms, refined a radiomic score (Rad-Score). This score, alongside clinical parameters, was modelled via Extreme Gradient Boosting (XGBoost) analysis. Model calibration was assessed by calibration curves.

RESULTS: The integration of the Rad-Score with clinical factors including albumin and C-reactive protein levels moderately enhanced predictive efficiency, exhibiting an area under the curve (AUC) of 1.000 (95%CI, 1.000-1.000) in the training cohort and 0.990 (95%CI, 0.966-1.000) in the internal validation cohort. In an independent validation cohort from another hospital, the combined model yielded an AUC of 0.985 (95%CI, 0.965-1.000), with an accuracy, precision, sensitivity, and specificity of 0.92, 0.92, 0.94, and 0.91, respectively.

CONCLUSIONS: The synergistic application of deep learning-based radiomics from CTA and clinical indicators holds promise for anticipating AEs post-initial thoracic endovascular aortic repair in patients with acute uTBAD. The clinical utility of the constructed combined model, offering prognostic foresight during follow-up, has been substantiated.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Lu X, Gong W, Yang W, et al. Deep learning-based radiomics of computed tomography angiography to predict adverse events after initial endovascular repair for acute uncomplicated Stanford type B aortic dissection. Eur J Radiol. 2024. PMID: 38648727. doi:10.1016/j.ejrad.2024.111468

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。