多视图深度生存联合模型预测症状性颅内动脉粥样硬化性狭窄患者卒中复发
该研究回顾性纳入2家医疗机构363例症状性颅内动脉粥样硬化性狭窄患者,基于T1加权增强序列构建多视图深度生存联合模型预测卒中复发风险。联合模型内部验证集C指数为0.872(95%CI:0.785-0.958),外部测试集为0.803(95%CI:0.711-0.895),优于临床模型、影像组学模型和单独深度学习模型,1、2、3年复发预测AUC分别为0.841、0.870、0.802。
要点
- 联合模型外部测试集C指数0.803(95%CI:0.711-0.895),优于临床、影像组学和单独深度学习模型。
- 模型对1、2、3年复发的AUC分别为0.841、0.870、0.802。
- 校准曲线和决策曲线分析支持该模型的临床实用性。
核心结论
- 联合模型整合自动多视图深度特征学习和基于DeepSurv的生存分析,为症状性颅内动脉粥样硬化性狭窄患者的复发风险分层提供稳健且客观的工具,表现优于传统方法,在指导个体化二级预防策略方面具有显著潜力。
研究设计与样本
- 回顾性研究,2020年6月至2024年12月从2家医疗机构收集363例症状性颅内动脉粥样硬化性狭窄患者的HR-VWI图像,其中复发79例(21.76%)、未复发284例(78.24%);队列分为训练/验证集(n=290)和测试集(n=73);使用T1加权增强序列构建多视图深度生存联合模型,采用Vision Transformer和影像组学分析MR图像,并用DeepSurv扩展传统Cox比例风险模型的建模能力;模型性能采用时间依赖性ROC曲线和C指数评估,并用决策曲线分析和校准曲线验证。
诊断标准与关键数值
- 联合模型内部验证集C指数0.872(95%CI:0.785-0.958),外部测试集C指数0.803(95%CI:0.711-0.895);1年复发AUC 0.841、2年复发AUC 0.870、3年复发AUC 0.802。
临床应用与阅片要点
- 作者认为该联合模型为症状性颅内动脉粥样硬化性狭窄患者的复发风险分层提供了稳健且客观的工具,表现优于传统方法,在指导个体化二级预防策略方面具有显著潜力。
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: Symptomatic intracranial atherosclerotic stenosis (sICAS) is associated with a high risk of stroke recurrence. Current risk stratification approaches based on high-resolution vessel wall imaging (HR-VWI) remain dependent on subjective human assessment, which limits their precision.
METHODS: From June 2020 to December 2024, HR-VWI images were retrospectively collected from 363 patients with sICAS across 2 medical institutions. Among the 363 patients, there were 79 cases of stroke recurrence (21.76%) and 284 cases without recurrence (78.24%). The cohort was divided into a Training/Validation set (n=290) and a Test set (n=73). Using the T1-weighted contrast-enhanced sequence, we developed a Multi-View Deep Survival Combined Model. This model employs a Vision Transformer and radiomics to analyze MR images and uses DeepSurv to extend the modeling capacity of the traditional Cox proportional hazards model. It enables the prediction of stroke recurrence risk related to intracranial culprit plaques. Model performance was evaluated using time-dependent receiver operating characteristic curves and the C-index. Additionally, decision curve analysis and calibration curves were used to comprehensively validate the model's practical value and clinical application prospects.
RESULTS: The Combined Model exhibited superior predictive performance, achieving a C-index of 0.872 (95% CI: 0.785-0.958) in the internal validation set and 0.803 (95% CI: 0.711-0.895) in the external test set. This performance significantly outperformed that of clinical models, radiomics models, and standalone deep learning models. The model also demonstrated excellent time-dependent predictive accuracy for 1, 2, and 3-year recurrence (area under the curve: 0.841, 0.870, and 0.802, respectively). Calibration and decision curve analysis confirmed the model's clinical utility.
CONCLUSION: By integrating automated multi-view deep feature learning and DeepSurv-based survival analysis, the Combined Model provides a robust and objective tool for stratifying recurrence risk in patients with sICAS. It outperforms conventional methods and holds significant potential for guiding personalized secondary prevention strategies.
引用
- Li Z, Huang T, Zhang L, et al. A Multi-view Deep Survival Combined Model for Predicting Stroke Recurrence in Symptomatic Intracranial Atherosclerosis. Acad Radiol. 2025. PMID: 41242896. doi:10.1016/j.acra.2025.10.052
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。