文献速递神经介入CTDSA

基于ASPECTS框架的CT影像组学模型开发与验证用于预测恶性脑水肿

Development and validation of a radiomics model based on the ASPECTS framework using CT imaging for predicting malignant cerebral edema.
PubMed 文献 · Eur J Radiol · 2025-09-04

这项多中心回顾性研究纳入5个卒中中心708例急性缺血性卒中患者,基于ASPECTS区域提取影像组学特征构建融合临床、影像和影像组学特征的模型预测恶性脑水肿。融合模型在训练集、内部验证集和外部验证集的AUC分别为0.91、0.78和0.88,均优于临床模型和影像特征模型,SHAP分析显示ASPECTS、NIHSS评分和侧支循环评分是主要预测因子。

要点

  • 融合模型在外部验证集AUC为0.88,优于临床模型的0.71和CT_Features模型的0.70。
  • SHAP分析显示ASPECTS、NIHSS评分和侧支循环评分是前三位预测因子。
  • 模型基于常规NCCT和CTA的ASPECTS框架提取特征,无需手动分割梗死灶。

核心结论

  • 整合临床、影像和基于ASPECTS框架提取的影像组学特征的融合模型对早期恶性脑水肿预测表现出优越且可泛化的预测性能,可整合入临床工作流程实现快速一致的MCE风险评估。

研究设计与样本

  • 多中心回顾性研究纳入5个卒中中心708例急性缺血性卒中患者,均接受NCCT和CTA检查,基于ASPECTS区域提取影像组学特征,采用机器学习构建临床模型、影像特征模型和融合模型,以AUC、准确率、校准曲线和决策曲线分析评估性能。

诊断标准与关键数值

  • 训练集融合模型AUC=0.91(95%CI: 0.88-0.95),优于临床模型AUC=0.72(95%CI: 0.66-0.78,p<0.001)和CTA_Features模型AUC=0.83(95%CI: 0.79-0.88,p<0.001);内部验证集融合模型AUC=0.78(95%CI: 0.70-0.87),优于临床模型AUC=0.68(95%CI: 0.59-0.77,p=0.030);外部验证集融合模型AUC=0.88(95%CI: 0.82-0.94),优于临床模型AUC=0.71(95%CI: 0.59-0.83,p=0.010)和CT_Features模型AUC=0.70(95%CI: 0.56-0.85,p=0.012);融合模型特异度82.5%,准确率78.3%。

临床应用与阅片要点

  • 该模型基于常规基线NCCT和CTA及入院即可获得的变量,通过ASPECTS框架避免手动分割,作者认为可整合入临床工作流程以实现快速一致的MCE风险估计。

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: Accurate delineation of the infarct region on acute-phase Computed Tomography (CT) remains challenging, and radiomics applications in stroke are limited. We aimed to develop and validate a multimodal prediction model for malignant cerebral edema (MCE) using clinical and radiomic features extracted based on the Alberta Stroke Program Early Computed Tomography Score (ASPECTS) framework, eliminating the need for manual infarct segmentation.

METHOD: This multicenter retrospective study included patients with acute ischemic stroke (AIS) from five stroke centers who underwent Non-Contrast Computed Tomography (NCCT) and computed tomography angiography (CTA). Radiomic features were extracted from ASPECTS regions. Clinical, imaging-alone, and fused models were developed using machine learning. Model performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC) analysis, accuracy, calibration curves, and decision curve analysis (DCA). Shapley Additive exPlanations (SHAP) was used to interpret feature contributions.

RESULTS: A total of 708 patients were included (median age: 67 years; interquartile range (IQR): 60-76; 448 men, 63.3 %). In the training cohort, the fused model (AUC = 0.91, 95 %CI: 0.88-0.95) outperformed the clinical (AUC = 0.72, 95 %CI: 0.66-0.78, p < 0.001) and CTA_Features (AUC = 0.83, 95 %CI: 0.79-0.88, p < 0.001) models. In the internal validation cohort, the fused model (AUC = 0.78, 95 %CI: 0.70-0.87) outperformed the clinical model (AUC = 0.68, 95 %CI: 0.59-0.77, p = 0.030). In the external validation, the fused model (AUC = 0.88, 95 %CI: 0.82-0.94) outperformed the clinical (AUC = 0.71, 95 %CI: 0.59-0.83, p = 0.010) and CT_Features (AUC = 0.70, 95 %CI: 0.56-0.85, p = 0.012) models. SHAP analysis identified ASPECTS, National Institutes of Health Stroke Scale (NIHSS) score, and collateral score (CS) as top predictors. The fused model demonstrated the highest specificity (82.5 %) and accuracy (78.3 %).

CONCLUSIONS: The fused model integrating clinical, radiological, and radiomic features extracted using the ASPECTS framework, demonstrated superior and generalizable predictive performance for early MCE prediction. As it uses routinely acquired baseline NCCT and CTA with readily available admission variables and avoids manual segmentation through an ASPECTS-based framework, it can be integrated into clinical workflows to enable rapid and consistent MCE risk estimation.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Huang L, Xu X, Tian B, et al. Development and validation of a radiomics model based on the ASPECTS framework using CT imaging for predicting malignant cerebral edema. Eur J Radiol. 2025. PMID: 40957118. doi:10.1016/j.ejrad.2025.112410

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。