Table_3_Predicting Adverse Radiation Effects in Brain Tumors After Stereotactic Radiotherapy With Deep Learning and Handcrafted Radiomics.docx

IntroductionThere is a cumulative risk of 20–40% of developing brain metastases (BM) in solid cancers. Stereotactic radiotherapy (SRT) enables the application of high focal doses of radiation to a volume and is often used for BM treatment. However, SRT can cause adverse radiation effects (ARE), such as radiation necrosis, which sometimes cause irreversible damage to the brain. It is therefore of clinical interest to identify patients at a high risk of developing ARE. We hypothesized that models trained with radiomics features, deep learning (DL) features, and patient characteristics or their combination can predict ARE risk in patients with BM before SRT. MethodsGadolinium-enhanced T1-weighted MRIs and characteristics from patients treated with SRT for BM were collected for a training and testing cohort (N = 1,404) and a validation cohort (N = 237) from a separate institute. From each lesion in the training set, radiomics features were extracted and used to train an extreme gradient boosting (XGBoost) model. A DL model was trained on the same cohort to make a separate prediction and to extract the last layer of features. Different models using XGBoost were built using only radiomics features, DL features, and patient characteristics or a combination of them. Evaluation was performed using the area under the curve (AUC) of the receiver operating characteristic curve on the external dataset. Predictions for individual lesions and per patient developing ARE were investigated. ResultsThe best-performing XGBoost model on a lesion level was trained on a combination of radiomics features and DL features (AUC of 0.71 and recall of 0.80). On a patient level, a combination of radiomics features, DL features, and patient characteristics obtained the best performance (AUC of 0.72 and recall of 0.84). The DL model achieved an AUC of 0.64 and recall of 0.85 per lesion and an AUC of 0.70 and recall of 0.60 per patient. ConclusionMachine learning models built on radiomics features and DL features extracted from BM combined with patient characteristics show potential to predict ARE at the patient and lesion levels. These models could be used in clinical decision making, informing patients on their risk of ARE and allowing physicians to opt for different therapies.引言：实体瘤患者发生脑转移瘤（brain metastases, BM）的累积风险为20%~40%。立体定向放射治疗（Stereotactic radiotherapy, SRT）可对靶区实施高聚焦剂量照射，是脑转移瘤的常用治疗手段。然而，SRT可能引发放射性不良反应（adverse radiation effects, ARE），例如放射性坏死，有时会对脑组织造成不可逆损伤。因此，识别出发生放射性不良反应风险较高的患者具有重要临床价值。我们假设，基于放射组学特征、深度学习（deep learning, DL）特征、患者临床特征或三者组合训练的模型，可在SRT治疗前预测脑转移瘤患者的ARE发生风险。 方法：本研究从两家医疗中心收集了接受SRT治疗的脑转移瘤患者的钆增强T1加权磁共振成像及临床特征，其中训练与测试队列共1404例，来自另一家机构的外部验证队列共237例。从训练集的每一处病灶中提取放射组学特征，并用于训练极限梯度提升（extreme gradient boosting, XGBoost）模型。同时在同一队列中训练深度学习模型，以实现独立预测并提取模型最后一层的特征。我们分别构建了四类XGBoost模型：仅使用放射组学特征、仅使用深度学习特征、仅使用患者临床特征，以及三者联合的模型。模型性能评估采用外部验证数据集上的受试者工作特征曲线下面积（area under the curve, AUC）。此外，本研究还分析了单病灶及单患者层面的ARE发生风险预测情况。 结果：在病灶层面，性能最优的XGBoost模型结合了放射组学特征与深度学习特征，其曲线下面积为0.71，召回率为0.80。在患者层面，联合放射组学特征、深度学习特征与患者临床特征的模型性能最佳，曲线下面积为0.72，召回率为0.84。单独的深度学习模型在病灶层面的曲线下面积为0.64，召回率为0.85；在患者层面的曲线下面积为0.70，召回率为0.60。 结论：基于脑转移瘤的放射组学特征、深度学习特征联合患者临床特征构建的机器学习模型，在病灶与患者层面均具备预测ARE发生风险的潜力。此类模型可应用于临床决策，为患者告知其ARE发生风险，并辅助医师选择更适宜的治疗方案。