Abstract：
To propose a machine learning (ML) model predicting the favorable outcome of stereotactic radiosurgery (SRS) for residual brain arteriovenous malformation (bAVM) after partial embolization.
One hundred and thirty bAVM patients who underwent partial embolization followed by SRS were reviewed retrospectively. Patients were split at random split into training datasets (n = 100) and testing datasets (n = 30). Radiomics and dosimetric features were extracted from pre-SRS treatment images. Feature selection was performed to select appropriate radiomics and dosimetric features. Three ML algorithms were applied to construct models using selected features respectively. A total of 9 models were trained to predict favorable outcomes (obliteration without complication) of bAVMs. The efficacy of these models was evaluated on the testing dataset using mean accuracy (ACC) and area under the receiver operating characteristic curve (AUC).
The obliteration rate of this cohort was 70.77% (92 of 130) with a mean follow-up of 43.8 months (range, 12-108 months). Favorable outcomes were achieved in 89 patients (68.46%). Four radiomics features and 7 dosimetric features were selected for ML model construction. The dosimetric support vector machines (SVM) model showed the best performance on the training dataset, with an ACC of 0.74 and AUC of 0.78. The dosimetric SVM model also showed the best performance on the testing dataset, with an ACC of 0.83 and AUC of 0.77.
Dosimetric features are good predictors of prognosis for patients with partially embolized bAVM followed by SRS therapy. The use of ML models is an innovative method for predicting favorable outcomes of partially embolized bAVM followed by SRS therapy.
One hundred and thirty bAVM patients who underwent partial embolization followed by SRS were reviewed retrospectively. Patients were split at random split into training datasets (n = 100) and testing datasets (n = 30). Radiomics and dosimetric features were extracted from pre-SRS treatment images. Feature selection was performed to select appropriate radiomics and dosimetric features. Three ML algorithms were applied to construct models using selected features respectively. A total of 9 models were trained to predict favorable outcomes (obliteration without complication) of bAVMs. The efficacy of these models was evaluated on the testing dataset using mean accuracy (ACC) and area under the receiver operating characteristic curve (AUC).
The obliteration rate of this cohort was 70.77% (92 of 130) with a mean follow-up of 43.8 months (range, 12-108 months). Favorable outcomes were achieved in 89 patients (68.46%). Four radiomics features and 7 dosimetric features were selected for ML model construction. The dosimetric support vector machines (SVM) model showed the best performance on the training dataset, with an ACC of 0.74 and AUC of 0.78. The dosimetric SVM model also showed the best performance on the testing dataset, with an ACC of 0.83 and AUC of 0.77.
Dosimetric features are good predictors of prognosis for patients with partially embolized bAVM followed by SRS therapy. The use of ML models is an innovative method for predicting favorable outcomes of partially embolized bAVM followed by SRS therapy.
摘要：
提出一种机器学习（ML）模型，预测立体定向放射外科（SRS）对部分栓塞后残留的脑动静脉畸形（bAVM）的有利结果。
回顾性分析了130例接受部分栓塞后接受SRS治疗的bAVM患者。患者随机分成训练数据集(n=100)和测试数据集(n=30)。从SRS治疗前的图像中提取影像组学和剂量学特征。进行特征选择以选择适当的放射组学和剂量学特征。应用三种ML算法分别使用选定的特征构建模型。总共训练了9个模型来预测bAVM的有利结果（无并发症的消除）。使用平均准确度（ACC）和受试者工作特征曲线下面积（AUC）在测试数据集上评估这些模型的功效。
该队列的闭塞率为70.77％（130个中的92个），平均随访时间为43.8个月（范围，12-108个月）。89例患者（68.46%）取得了良好的预后。选择4个影像组学特征和7个剂量学特征用于ML模型构建。剂量支持向量机（SVM）模型在训练数据集上表现最佳，ACC为0.74，AUC为0.78。剂量SVM模型在测试数据集上也表现出最佳性能，ACC为0.83，AUC为0.77。
剂量学特征是部分栓塞bAVM后接受SRS治疗的患者预后的良好预测因子。ML模型的使用是预测SRS治疗后部分栓塞bAVM的有利结果的创新方法。
回顾性分析了130例接受部分栓塞后接受SRS治疗的bAVM患者。患者随机分成训练数据集(n=100)和测试数据集(n=30)。从SRS治疗前的图像中提取影像组学和剂量学特征。进行特征选择以选择适当的放射组学和剂量学特征。应用三种ML算法分别使用选定的特征构建模型。总共训练了9个模型来预测bAVM的有利结果（无并发症的消除）。使用平均准确度（ACC）和受试者工作特征曲线下面积（AUC）在测试数据集上评估这些模型的功效。
该队列的闭塞率为70.77％（130个中的92个），平均随访时间为43.8个月（范围，12-108个月）。89例患者（68.46%）取得了良好的预后。选择4个影像组学特征和7个剂量学特征用于ML模型构建。剂量支持向量机（SVM）模型在训练数据集上表现最佳，ACC为0.74，AUC为0.78。剂量SVM模型在测试数据集上也表现出最佳性能，ACC为0.83，AUC为0.77。
剂量学特征是部分栓塞bAVM后接受SRS治疗的患者预后的良好预测因子。ML模型的使用是预测SRS治疗后部分栓塞bAVM的有利结果的创新方法。
