基于交叉注意力视觉Transformer模型与多模态MRI预测NIHSS评分及急性缺血性卒中严重程度
本研究回顾性纳入1227例急性缺血性卒中患者,按NIHSS评分分为轻度(NIHSS<5)和中重度(NIHSS≥5)两组,构建8种基线模型进行比较,包括临床模型、基于DWI或多序列的影像组学模型以及采用不同融合策略的深度学习模型。以DWI为主序列并交叉融合其他MRI序列的深度学习模型(模型8)表现最佳,测试队列AUC为0.914、ACC为0.830、特异度0.818、敏感度0.853,外部验证中心2和中心3的AUC分别达0.910和0.912。
要点
- 以DWI为主序列交叉融合其他MRI序列的ViT深度学习模型对AIS严重程度分类表现最佳。
- 模型8测试队列AUC 0.914、ACC 0.830、特异度0.818、敏感度0.853。
- Grad-CAM显示梗死核心是预测的最关键区域,各序列特征注意力一致。
核心结论
- 基于ViT的交叉模态融合深度学习模型为AIS严重程度分类提供无创高效工具,在亚组中表现稳健且具有可解释性,有望用于临床个性化管理与决策。
研究设计与样本
- 回顾性队列研究,纳入1227例AIS患者,按NIHSS评分分为轻度(NIHSS<5)和中重度(NIHSS≥5)两组,构建8种基线模型进行比较,包括临床模型、基于DWI或多序列的影像组学模型以及采用早期融合、后期融合、完全交叉融合和以DWI为中心的交叉融合等不同融合策略的深度学习模型,所有深度学习模型均基于Vision Transformer框架,外部验证在中心2和中心3进行。
关键影像表现/征象
- Grad-CAM可视化显示梗死核心是预测的最关键区域,DWI、T1WI、T2WI和FLAIR序列间特征注意力一致。
诊断标准与关键数值
- 模型8在测试队列中AUC为0.914、ACC为0.830、特异度0.818、敏感度0.853。
- 模型8在中心2外部验证AUC为0.910,在中心3外部验证AUC为0.912。
- 亚组分析显示模型8在多数亚组中稳健,预测差异无统计学意义(p > 0.05),AUC值持续超过0.900;BMI组观察到显著预测差异(p < 0.001)。
临床应用与阅片要点
- 作者认为基于ViT的交叉模态融合深度学习模型是有前景的工具,可用于临床实践中的个性化管理与决策。
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
RATIONALE AND OBJECTIVES: This study aimed to develop and evaluate models for classifying the severity of neurological impairment in acute ischemic stroke (AIS) patients using multimodal MRI data.
METHODS: A retrospective cohort of 1227 AIS patients was collected and categorized into mild (NIHSS<5) and moderate-to-severe (NIHSS≥5) stroke groups based on NIHSS scores. Eight baseline models were constructed for performance comparison, including a clinical model, radiomics models using DWI or multiple MRI sequences, and deep learning (DL) models with varying fusion strategies (early fusion, later fusion, full cross-fusion, and DWI-centered cross-fusion). All DL models were based on the Vision Transformer (ViT) framework. Model performance was evaluated using metrics such as AUC and ACC, and robustness was assessed through subgroup analyses and visualization using Grad-CAM.
RESULTS: Among the eight models, the DL model using DWI as the primary sequence with cross-fusion of other MRI sequences (Model 8) achieved the best performance. In the test cohort, Model 8 demonstrated an AUC of 0.914, ACC of 0.830, and high specificity (0.818) and sensitivity (0.853). Subgroup analysis shows that model 8 is robust in most subgroups with no significant prediction difference (p > 0.05), and the AUC value consistently exceeds 0.900. A significant predictive difference was observed in the BMI group (p < 0.001). The results of external validation showed that the AUC values of the model 8 in center 2 and center 3 reached 0.910 and 0.912, respectively. Visualization using Grad-CAM emphasized the infarct core as the most critical region contributing to predictions, with consistent feature attention across DWI, T1WI, T2WI, and FLAIR sequences, further validating the interpretability of the model.
CONCLUSION: A ViT-based DL model with cross-modal fusion strategies provides a non-invasive and efficient tool for classifying AIS severity. Its robust performance across subgroups and interpretability make it a promising tool for personalized management and decision-making in clinical practice.
引用
- Tuxunjiang P, Huang C, Zhou Z, et al. Prediction of NIHSS Scores and Acute Ischemic Stroke Severity Using a Cross-attention Vision Transformer Model with Multimodal MRI. Acad Radiol. 2025. PMID: 40517096. doi:10.1016/j.acra.2025.05.031
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。