文献速递神经外周血管MR

基于高分辨率磁共振血管壁成像的深度学习模型预测症状性颅内动脉粥样硬化性狭窄患者预后:一项多中心研究

Predicting the prognosis of symptomatic intracranial atherosclerotic stenosis (sICAS) patients using deep learning models: a multicenter study based on high-resolution magnetic resonance vessel wall imaging.
PubMed 文献 · Clin Radiol · 2025-09-18

本研究回顾性收集两个医疗中心363例症状性颅内动脉粥样硬化性狭窄患者的HR-VWI数据,以中心1(254例)为训练队列、中心2(109例)为外部验证队列,比较三种深度学习模型(ResNet50、DenseNet169、ViT)在2D与3D图像上的预测性能,并构建影像组学机器学习模型。结果显示3D-ResNet50与3D-DenseNet169的AUC均为0.780,显著优于2D模型及影像组学模型,校准曲线与决策曲线分析进一步支持3D模型的临床价值。

要点

  • 3D-ResNet50与3D-DenseNet169预测卒中复发的AUC均为0.780,优于2D模型与影像组学模型。
  • 2D-ResNet50的AUC为0.574,2D-DenseNet169为0.660,影像组学模型为0.698。
  • 校准曲线与决策曲线分析提示3D深度学习模型具有临床价值。

核心结论

  • 基于HR-VWI的3D深度学习模型在预测sICAS复发风险方面优于2D模型和影像组学模型,有助于临床决策和高危患者识别。

研究设计与样本

  • 回顾性多中心研究,共纳入两个医疗中心363例sICAS患者,中心1(n=254)为训练队列,中心2(n=109)为外部验证队列;采用HR-VWI提取责任斑块2D与3D图像特征,构建ResNet50、DenseNet169、ViT三种深度学习模型及基于手动提取特征的影像组学机器学习模型,使用LASSO进行特征选择、朴素贝叶斯分类器预测卒中复发风险,以AUC、校准曲线和决策曲线分析评价模型性能。

诊断标准与关键数值

  • 3D-ResNet50预测卒中复发的AUC=0.780(95%CI:0.638-0.92),3D-DenseNet169的AUC=0.780(95%CI:0.641-0.919);2D-ResNet50的AUC=0.574(95%CI:0.416-0.719),2D-DenseNet169的AUC=0.660(95%CI:0.533-0.788),影像组学模型AUC=0.698(95%CI:0.579-0.810);DeLong检验证实3D模型与2D模型及影像组学模型间差异有统计学意义。

临床应用与阅片要点

  • 作者认为基于HR-VWI的3D深度学习模型可辅助临床决策和高危患者识别。

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

AIM: Symptomatic intracranial atherosclerotic stenosis (sICAS) is a leading cause of stroke recurrence. This study aimed to develop a deep learning model based on high-resolution vessel wall imaging (HR-VWI) to improve recurrence prediction, identify high-risk patients, and guide clinical intervention.

MATERIALS AND METHODS: We retrospectively collected HR-VWI data from 363 patients with sICAS across two medical centres. Centre 1 (n = 254) served as the training cohort, and centre 2 (n = 109) served as the external validation cohort. Three deep learning models-ResNet50, DenseNet169, and Vision Transformer (ViT)-were used to extract features from both 2D and 3D images of culprit plaques. In addition, radiomics-based machine learning models were constructed using manually extracted features. The Least Absolute Shrinkage and Selection Operator (LASSO) algorithm was applied for feature selection, and a Naive Bayes classifier was used to predict the risk of stroke recurrence. Model performance was evaluated using the area under the curve (AUC), calibration curves, and decision curve analysis (DCA).

RESULTS: The 3D-ResNet50 (AUC = 0.780, 95% confidence interval [CI]: 0.638-0.92) and 3D-DenseNet169 (AUC = 0.780, 95% CI: 0.641-0.919) models significantly outperformed 2D models: 2D-ResNet50 (AUC = 0.574, 95% CI: 0.416-0.719), 2D-DenseNet169 (AUC = 0.660, 95% CI: 0.533-0.788), and radiomics (AUC = 0.698, 95% CI: 0.579-0.810). Delong's test confirmed the significance of these differences. Calibration and DCA curves further underscored the 3D models' clinical value.

CONCLUSION: The 3D deep learning model based on HR-VWI offers superior prediction of sICAS recurrence risk compared to 2D models and radiomics, aiding clinical decision-making and high-risk patient identification.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Li Z, Gao Y, Zhang K, et al. Predicting the prognosis of symptomatic intracranial atherosclerotic stenosis (sICAS) patients using deep learning models: a multicenter study based on high-resolution magnetic resonance vessel wall imaging. Clin Radiol. 2025. PMID: 41086706. doi:10.1016/j.crad.2025.107092

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。