Gao Yu, Li Zi-Ang, Xie Bei-Chen, Wang Wen-Peng, Sun Yan-Cong, Wei Zheng-Qi, Zhai Xiao-Yang, Zhao Qiu-Yi, Han Lin, Du Xin, Wang Jie, Zhang Ping, Yan Rui-Fang, Li Yong-Dong, Cui Hong-Kai
Department of Radiology Center, The First Affiliated Hospital of Xinxiang Medical University, Xinxiang, China.
The Second School of Clinical Medicine, Zhengzhou University, Zhengzhou, China.
Quant Imaging Med Surg. 2025 Apr 1;15(4):2929-2943. doi: 10.21037/qims-24-1723. Epub 2025 Mar 28.
High-resolution magnetic resonance vessel wall imaging (HR-VWI) offers enhanced visualization of vascular structures, thereby facilitating the deep learning (DL) network's acquisition of more extensive and detailed image information. This study aimed to develop a high-precision integrated model leveraging DL with an attention mechanism based on HR-VWI for predicting recurrent stroke in patients with symptomatic intracranial atherosclerotic stenosis (sICAS).
A retrospective study was conducted involving 363 sICAS patients who underwent HR-VWI, with data divided into a training set (n=254) from Center 1 (The First Affiliated Hospital of Xinxiang Medical University) and a test set (n=109) from Center 2 (The Sixth People's Hospital of Shanghai Jiao Tong University). Two convolutional neural network (CNN) models, ResNet50 and DenseNet169, were employed as feature extractors to capture image information from culprit plaques in HR-VWI. Integrating the Transformer attention mechanism, an advanced ensemble model, Trans-CNN, was constructed to predict stroke recurrence in sICAS patients. Model performance was evaluated using receiver operating characteristic (ROC) curves, with DeLong's test for comparing models. Additionally, decision curve analysis (DCA) and calibration curves were utilized to assess the model's practical and clinical value.
Trans-CNN demonstrated superior predictive performance, outperforming other models in both the training and test sets. Specifically, in the training set, Trans-CNN achieved an area under the curve (AUC) of 0.951 [95% confidence interval (CI): 0.923-0.974], accuracy of 0.880 (95% CI: 0.797-0.937), sensitivity of 0.900 (95% CI: 0.836-1.000), and specificity of 0.882 (95% CI: 0.757-0.948). Similarly, in the test set, it achieved an AUC of 0.912 (95% CI: 0.839-0.969), accuracy of 0.858 (95% CI: 0.743-0.936), sensitivity of 0.880 (95% CI: 0.693-1.000), and specificity of 0.810 (95% CI: 0.690-0.976). The AUC improvement of Trans-CNN over all other models was statistically significant (DeLong's test, P<0.05). Calibration curve analysis revealed good agreement between predicted probabilities and observed outcomes in both sets. DCA further underscored the potential value of Trans-CNN in guiding clinical decision-making.
The integrated model combining DL with an attention mechanism based on HR-VWI exhibits excellent performance in assessing the risk of stroke recurrence in sICAS patients. This advancement holds significant potential in assisting clinicians in diagnosis and developing individualized treatment strategies.
高分辨率磁共振血管壁成像（HR-VWI）能增强血管结构的可视化，从而有助于深度学习（DL）网络获取更广泛、详细的图像信息。本研究旨在开发一种基于HR-VWI的、利用带有注意力机制的DL的高精度集成模型，用于预测症状性颅内动脉粥样硬化狭窄（sICAS）患者的复发性卒中。
进行了一项回顾性研究，纳入363例行HR-VWI的sICAS患者，数据分为来自中心1（新乡医学院第一附属医院）的训练集（n = 254）和来自中心2（上海交通大学附属第六人民医院）的测试集（n = 109）。采用两种卷积神经网络（CNN）模型ResNet50和DenseNet169作为特征提取器，从HR-VWI中的责任斑块中捕获图像信息。整合Transformer注意力机制，构建了一种先进的集成模型Trans-CNN，用于预测sICAS患者的卒中复发。使用受试者工作特征（ROC）曲线评估模型性能，采用DeLong检验比较模型。此外，利用决策曲线分析（DCA）和校准曲线评估模型的实际和临床价值。
Trans-CNN表现出卓越的预测性能，在训练集和测试集中均优于其他模型。具体而言，在训练集中，Trans-CNN的曲线下面积（AUC）为0.951 [95%置信区间（CI）：0.923 - 0.974]，准确率为0.880（95% CI：0.797 - 0.937），灵敏度为0.900（95% CI：0.836 - 1.000），特异性为0.882（95% CI：0.757 - 0.948）。同样，在测试集中，其AUC为0.912（95% CI：0.839 - 0.969），准确率为0.858（95% CI：0.743 - 0.936），灵敏度为0.880（95% CI：0.693 - 1.000），特异性为0.810（95% CI：0.690 - 0.976）。Trans-CNN相对于所有其他模型的AUC改善具有统计学意义（DeLong检验，P < 0.05）。校准曲线分析显示两组中预测概率与观察结果之间具有良好的一致性。DCA进一步强调了Trans-CNN在指导临床决策方面的潜在价值。
基于HR-VWI将DL与注意力机制相结合的集成模型在评估sICAS患者卒中复发风险方面表现出卓越性能。这一进展在协助临床医生进行诊断和制定个体化治疗策略方面具有巨大潜力。
