文献速递神经技术与安全CT

基于Transformer的多模态融合模型预测自发性脑出血早期血肿扩大:一项多中心研究

Transformer-based multimodal fusion model predicts early hematoma expansion in spontaneous cerebral hemorrhage: A multicenter study.
PubMed 文献 · Eur J Radiol · 2025-10-11

该多中心研究纳入3家医院465例自发性脑出血患者,基于平扫CT提取2.5D图像与影像组学特征,结合临床因素构建Transformer多模态融合模型预测早期血肿扩大。Transformer模型AUC为0.894,优于2.5D深度学习模型(AUC=0.86)和影像组学模型(AUC=0.813),DeLong检验显示与影像组学和临床模型差异显著。

要点

  • Transformer多模态融合模型预测早期血肿扩大AUC达0.894,优于单一深度学习或影像组学模型。
  • 模型整合了临床因素、影像组学特征与深度学习特征,校准曲线显示融合模型预测价值最佳。
  • 决策曲线分析提示Transformer模型临床获益最大。

核心结论

  • 多模态Transformer模型在预测早期血肿扩大方面表现出色,验证了多模态模型预测早期血肿扩大的可行性。

研究设计与样本

  • 多中心研究,纳入3家医院465例自发性脑出血患者;医院1和2按8:2分为训练集315例和内部测试集80例,医院3为外部测试集70例;从平扫CT提取2.5D图像训练深度学习模型,从感兴趣区提取影像组学特征;将临床因素、影像组学特征和深度学习特征纳入SVM、LR、RF、AdaBoost四种机器学习模型,最终整合为Transformer模型;使用AUC评估性能,DeLong检验比较AUC,校准曲线评估一致性。

诊断标准与关键数值

  • Transformer模型预测早期血肿扩大AUC=0.894。
  • 2.5D深度学习模型AUC=0.86。
  • 影像组学模型AUC=0.813。
  • DeLong检验显示Transformer模型与影像组学模型和临床模型差异显著。

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: To develop a multimodal transformer model that integrates deep learning, radiomics, and clinical factors for the precise prediction of early hematoma expansion (EHE) in patients with spontaneous intracerebral hemorrhage (sICH).

METHODS: We included 465 patients from three hospitals, dividing patients from hospitals 1 and 2 into a training set (n = 315) and an internal testing set (n = 80) in an 8:2 ratio, while using hospital 3 as an external testing set (n = 70). We extracted 2.5D images from non-contrast computed tomography (NCCT) images for deep learning model training and extracted radiomics features from the Region of Interest (ROI). Clinical factors, radiomics features, and deep learning features were incorporated into four machine learning models: Support Vector Machine (SVM), Logistic Regression (LR), Random Forests (RF), and AdaBoost. Finally, we integrated the multimodal features into the transformer model. We evaluated the model's performance using the Area under the curve (AUC), compared model AUCs using the DeLong test, and assessed model consistency with calibration curves.

RESULTS: The transformer model achieved the best performance with an AUC of 0.894, outperforming the 2.5D deep learning model (AUC = 0.86) and the radiomics model (AUC = 0.813). The DeLong test revealed significant differences between the transformer model and the radiomics and clinical models. Decision Curve Analysis (DCA) indicated that the transformer model provided the greatest clinical benefit, and calibration curves showed that the fusion model achieved the best predictive value.

CONCLUSION: The multimodal transformer model demonstrated excellent performance in predicting EHE, validating the feasibility of multimodal models in predicting EHE.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang Y, Gao X, Zhou M, et al. Transformer-based multimodal fusion model predicts early hematoma expansion in spontaneous cerebral hemorrhage: A multicenter study. Eur J Radiol. 2025. PMID: 41135231. doi:10.1016/j.ejrad.2025.112465

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。