Jabal Mohamed Sobhi, Mohammed Marwa A, Nesvick Cody L, Kobeissi Hassan, Graffeo Christopher S, Pollock Bruce E, Brinjikji Waleed
From the Department of Radiology (M.S.J., M.A.M., H.K., W.B.), Mayo Clinic, Rochester, Minnesota
Department of Computer and Information Science (M.S.J.), University of Pennsylvania, Philadelphia, Pennsylvania.
AJNR Am J Neuroradiol. 2024 Oct 3;45(10):1521-1527. doi: 10.3174/ajnr.A8351.
Stereotactic radiosurgery is a key treatment modality for cerebral AVMs, particularly for small lesions and those located in eloquent brain regions. Predicting obliteration remains challenging due to evolving treatment paradigms and complex AVM presentations. With digital subtraction angiography (DSA) being the gold standard for outcome evaluation, radiomic approaches offer potential for more objective and detailed analysis. We aimed to develop machine learning modeling using DSA quantitative features for post-SRS obliteration prediction.
A prospective registry of patients with cerebral AVMs was screened to include patients with digital prestereotactic radiosurgery DSA. Anterior-posterior and lateral views were retrieved and manually segmented. Quantitative features were computed from the lesion ROI. Following feature selection, machine learning models were developed to predict unsuccessful 2-year total obliteration using processed radiomics features in comparison with clinical and radiosurgical features. When we evaluated through area under the receiver operating characteristic curve (AUROC), accuracy, area under the precision-recall curve F1, recall, and precision, the best performing model predictions on the test set were interpreted using the Shapley additive explanations approach.
DSA images of 100 included patients were retrieved and analyzed. The best-performing clinical radiosurgical model was a gradient boosting classifier with an AUROC of 68% and a recall of 67%. When we used radiomics variables as input, the AdaBoost classifier had the best evaluation metrics with an AUROC of 79% and a recall of 75%. The most important clinico-radiosurgical features, ranked by model contribution, were lesion volume, patient age, treatment dose rate, the presence of seizure at presentation, and prior resection. The most important ranked radiomics features were the following: gray-level size zone matrix, gray-level nonuniformity, kurtosis, sphericity, skewness, and gray-level dependence matrix dependence nonuniformity.
The combination of radiomics with machine learning is a promising approach for predicting cerebral AVM obliteration status following stereotactic radiosurgery. DSA could enhance prognostication of stereotactic radiosurgery-treated AVMs due to its high spatial resolution. Model interpretation is essential for building transparent models and establishing clinically valid radiomic signatures.
立体定向放射外科是治疗脑动静脉畸形（AVM）的关键方法，尤其适用于小病灶以及位于脑功能区的病灶。由于治疗模式不断演变以及AVM表现复杂，预测其闭塞情况仍然具有挑战性。数字减影血管造影（DSA）是评估治疗结果的金标准，而放射组学方法为更客观、详细的分析提供了可能。我们旨在利用DSA定量特征开发机器学习模型，以预测立体定向放射外科治疗后AVM的闭塞情况。
对脑AVM患者的前瞻性登记资料进行筛选，纳入在立体定向放射外科治疗前有数字减影血管造影（DSA）检查的患者。获取前后位和侧位图像并进行手动分割。从病灶感兴趣区（ROI）计算定量特征。在进行特征选择后，开发机器学习模型，使用处理后的放射组学特征，并与临床和放射外科特征进行比较，以预测2年内未能完全闭塞的情况。当我们通过受试者工作特征曲线下面积（AUROC）、准确率以及精确召回率曲线下面积F1、召回率和精确率进行评估时，使用Shapley加性解释方法对测试集中表现最佳的模型预测结果进行解读。
检索并分析了100例纳入患者的DSA图像。表现最佳的临床放射外科模型是梯度提升分类器，其AUROC为68%，召回率为67%。当使用放射组学变量作为输入时，AdaBoost分类器的评估指标最佳，AUROC为79%，召回率为75%。按模型贡献排名，最重要的临床放射外科特征为病灶体积、患者年龄、治疗剂量率、就诊时是否有癫痫发作以及既往是否接受过切除术。排名最重要的放射组学特征如下：灰度大小区域矩阵、灰度不均匀性、峰度、球形度、偏度以及灰度依赖矩阵依赖不均匀性。
放射组学与机器学习相结合是预测立体定向放射外科治疗后脑AVM闭塞状态的一种有前景的方法。由于DSA具有高空间分辨率，它可以提高对立体定向放射外科治疗的AVM的预后评估。模型解释对于构建透明模型和建立临床有效的放射组学特征至关重要。
