Luo Xiaoyuan, Wang Jienan, Liang Xinmei, Yan Lei, Chen XinHua, He Jian, Luo Jing, Zhao Bing, He Guangchen, Wang Manning, Zhu Yueqi
Digital Medical Research Center and also with the Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University, Shanghai, China.
Department of Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, China.
J Neurointerv Surg. 2023 Apr;15(4):380-386. doi: 10.1136/neurintsurg-2022-018655. Epub 2022 Apr 8.
Accurate prediction of cerebral aneurysm (CA) rupture is of great significance. We intended to evaluate the accuracy of the point cloud neural network (PC-NN) in predicting CA rupture using MR angiography (MRA) and CT angiography (CTA) data.
418 CAs in 411 consecutive patients confirmed by CTA (n=180) or MRA (n=238) in a single hospital were retrospectively analyzed. A PC-NN aneurysm model with/without parent artery involvement was used for CA rupture prediction and compared with ridge regression, support vector machine (SVM) and neural network (NN) models based on radiomics features. Furthermore, the performance of the trained PC-NN and radiomics-based models was prospectively evaluated in 258 CAs of 254 patients from five external centers.
In the internal test data, the area under the curve (AUC) of the PC-NN model trained with parent artery (AUC=0.913) was significantly higher than that of the PC-NN model trained without parent artery (AUC=0.851; p=0.041) and of the ridge regression (AUC=0.803; p=0.019), SVM (AUC=0.788; p=0.013) and NN (AUC=0.805; p=0.023) radiomics-based models. Additionally, the PC-NN model trained with MRA source data achieved a higher prediction accuracy (AUC=0.936) than that trained with CTA source data (AUC=0.824; p=0.043). In external data of prospective cohort patients, the AUC of PC-NN was 0.835, significantly higher than ridge regression (0.692; p<0.001), SVM (0.701; p<0.001) and NN (0.681; p<0.001) models.
PC-NNs can achieve more accurate CA rupture prediction than traditional radiomics-based models. Furthermore, the performance of the PC-NN model trained with MRA data was superior to that trained with CTA data.
准确预测脑动脉瘤（CA）破裂具有重要意义。我们旨在评估点云神经网络（PC-NN）利用磁共振血管造影（MRA）和计算机断层血管造影（CTA）数据预测CA破裂的准确性。
回顾性分析了一家医院中411例连续患者的418个经CTA（n = 180）或MRA（n = 238）确诊的CA。使用包含/不包含母动脉受累情况的PC-NN动脉瘤模型进行CA破裂预测，并与基于影像组学特征的岭回归、支持向量机（SVM）和神经网络（NN）模型进行比较。此外，在来自五个外部中心的254例患者的258个CA中对训练好的PC-NN和基于影像组学的模型的性能进行了前瞻性评估。
在内部测试数据中，使用母动脉训练的PC-NN模型的曲线下面积（AUC）（AUC = 0.913）显著高于未使用母动脉训练的PC-NN模型（AUC = 0.851；p = 0.041）以及岭回归（AUC = 0.803；p = 0.019）、SVM（AUC = 0.788；p = 0.013）和NN（AUC = 0.805；p = 0.023）基于影像组学的模型。此外，使用MRA源数据训练的PC-NN模型比使用CTA源数据训练的模型具有更高的预测准确性（AUC = 0.936）（AUC = 0.824；p = 0.043）。在前瞻性队列患者的外部数据中，PC-NN的AUC为0.835，显著高于岭回归（0.692；p < 0.001）、SVM（0.701；p < 0.001）和NN（0.681；p < 0.001）模型。
与传统的基于影像组学的模型相比，PC-NN能够实现更准确的CA破裂预测。此外，使用MRA数据训练的PC-NN模型的性能优于使用CTA数据训练的模型。
