Yang Hyeondong, Cho Kwang-Chun, Kim Jung-Jae, Kim Jae Ho, Kim Yong Bae, Oh Je Hoon
Department of Mechanical Engineering and BK21 FOUR ERICA-ACE Center, Hanyang University, Ansan, Gyeonggi-do, Korea.
Department of Neurosurgery, College of Medicine, Yonsei University, Yongin Severance Hospital, Yongin, Korea.
J Neurointerv Surg. 2023 Feb;15(2):200-204. doi: 10.1136/neurintsurg-2021-018551. Epub 2022 Feb 9.
Cerebral aneurysms should be treated before rupture because ruptured aneurysms result in serious disability. Therefore, accurate prediction of rupture risk is important and has been estimated using various hemodynamic factors.
To suggest a new way to predict rupture risk in cerebral aneurysms using a novel deep learning model based on hemodynamic parameters for better decision-making about treatment.
A novel convolutional neural network (CNN) model was used for rupture risk prediction retrospectively of 123 aneurysm cases. To include the effect of hemodynamic parameters into the CNN, the hemodynamic parameters were first calculated using computational fluid dynamics and fluid-structure interaction. Then, they were converted into images for training the CNN using a novel approach. In addition, new data augmentation methods were devised to obtain sufficient training data. A total of 53,136 images generated by data augmentation were used to train and test the CNN.
The CNNs trained with wall shear stress (WSS), strain, and combination images had area under the receiver operating characteristics curve values of 0.716, 0.741, and 0.883, respectively. Based on the cut-off values, the CNN trained with WSS (sensitivity: 0.5, specificity: 0.79) or strain (sensitivity: 0.74, specificity: 0.71) images alone was not highly predictive. However, the CNN trained with combination images of WSS and strain showed a sensitivity and specificity of 0.81 and 0.82, respectively.
CNN-based deep learning algorithm using hemodynamic factors, including WSS and strain, could be an effective tool for predicting rupture risk in cerebral aneurysms with good predictive accuracy.
脑动脉瘤应在破裂前进行治疗，因为破裂的动脉瘤会导致严重残疾。因此，准确预测破裂风险很重要，并且已经使用各种血流动力学因素进行了评估。
提出一种使用基于血流动力学参数的新型深度学习模型来预测脑动脉瘤破裂风险的新方法，以便更好地进行治疗决策。
使用一种新型卷积神经网络（CNN）模型对123例动脉瘤病例进行回顾性破裂风险预测。为了将血流动力学参数的影响纳入CNN，首先使用计算流体动力学和流固相互作用计算血流动力学参数。然后，使用一种新方法将它们转换为图像以训练CNN。此外，还设计了新的数据增强方法以获得足够的训练数据。总共53136张通过数据增强生成的图像用于训练和测试CNN。
用壁面剪应力（WSS）、应变和组合图像训练的CNN在受试者工作特征曲线下的面积值分别为0.716、0.741和0.883。基于临界值，单独用WSS（敏感性：0.5，特异性：0.79）或应变（敏感性：0.74，特异性：0.71）图像训练的CNN预测性不高。然而，用WSS和应变的组合图像训练的CNN的敏感性和特异性分别为0.81和0.82。
基于CNN的深度学习算法使用包括WSS和应变在内的血流动力学因素，可能是预测脑动脉瘤破裂风险的有效工具，具有良好的预测准确性。
