文献速递神经外周血管头颈US

基于术前超声图像的深度学习影像组学预测颈动脉支架置入患者同侧缺血性卒中:多中心研究

Deep Learning Radiomics Based on Preoperational Ultrasound Images for Predicting Ipsilateral Ischemic Stroke in Patients with Carotid Artery Stenting: A Multicenter Study.
PubMed 文献 · Acad Radiol · 2025-12-26

本研究纳入三个中心2018至2024年802例颈动脉支架置入患者,从术前斑块超声图像提取影像组学与深度学习特征,结合临床特征构建列线图预测长期同侧缺血性卒中。中位随访62个月,213例(26.6%)发生同侧卒中,模型在训练集、内部验证集和外部验证集的C指数分别为0.800、0.751和0.708,均显著优于常规超声模型(p<0.05)。

要点

  • 基于术前超声斑块图像构建的深度学习影像组学列线图可预测颈动脉支架置入后长期同侧缺血性卒中风险。
  • 模型外部验证C指数为0.708(95% CI:0.634-0.782),在全部数据集上显著优于常规超声模型(p<0.05)。
  • 列线图划分的高风险组同侧卒中概率显著高于低风险组(p<0.05)。

核心结论

  • 基于术前超声的深度学习影像组学模型可预测颈动脉支架置入患者长期同侧卒中风险,可能有助于风险分层并指导治疗决策与随访管理。

研究设计与样本

  • 多中心研究,纳入三个中心2018至2024年802例接受颈动脉支架置入的患者,从术前斑块超声图像提取影像组学与深度学习特征,采用Cox回归和随机生存森林构建联合模型并以列线图呈现,以C指数和Kaplan-Meier分析评估性能。

诊断标准与关键数值

  • 训练集C指数0.800(95% CI:0.759-0.841),内部验证集0.751(95% CI:0.677-0.828),外部验证集0.708(95% CI:0.634-0.782)。
  • 模型在全部数据集上显著优于常规超声模型(p<0.05)。
  • 中位随访62个月,213例(26.6%)发生同侧卒中。

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

OBJECTIVES: This study aimed to develop and validate an integrated model incorporating clinical, radiomic, and deep learning features to predict long-term ipsilateral ischemic stroke after carotid artery stenting (CAS).

METHODS: We analyzed 802 patients who underwent CAS at three centers between 2018 and 2024. Clinical and ultrasound data were collected, and radiomic and deep learning features were extracted from preoperative plaque images. A combined model was built using Cox regression and random survival forest models, and then presented as a nomogram. Model performance was assessed using the C-index and Kaplan-Meier analysis.

RESULTS: Over a median follow-up of 62 months, 213 patients (26.6%) experienced ipsilateral stroke. We integrated the significant clinical, radiomics, and deep learning features (p<0.05) into a nomogram. The model demonstrated strong discriminative ability for stroke, with C-indices of 0.800 (95% CI: 0.759-0.841) in the training set, 0.751 (95% CI: 0.677-0.828) in the internal validation set, and 0.708 (95% CI: 0.634-0.782) in the external validation set. It significantly outperformed the conventional ultrasound model across all datasets (p<0.05). Moreover, Kaplan-Meier analysis confirmed that patients stratified into the high-risk group based on the nomogram had a substantially higher probability of ipsilateral stroke compared to the low-risk group (p<0.05).

CONCLUSION: A deep learning radiomics model based on preoperative ultrasound can predict long-time risk of ipsilateral stroke for patients with CAS, which may help in risk stratification and guide treatment decision-making and follow-up management.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Jie Z, Xiaodan L, Mingjie G, et al. Deep Learning Radiomics Based on Preoperational Ultrasound Images for Predicting Ipsilateral Ischemic Stroke in Patients with Carotid Artery Stenting: A Multicenter Study. Acad Radiol. 2025. PMID: 41455622. doi:10.1016/j.acra.2025.12.006

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。