Sun Shuchen, Ren Leihao, Miao Zong, Hua Lingyang, Wang Daijun, Deng Jiaojiao, Chen Jiawei, Liu Ning, Gong Ye
Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China.
Institute of Neurosurgery, Fudan University, Shanghai, China.
Front Oncol. 2022 Sep 28;12:879528. doi: 10.3389/fonc.2022.879528. eCollection 2022.
This study aimed to investigate the feasibility of predicting mutation status based on the MR radiomic analysis in patients with intracranial meningioma.
This retrospective study included 105 patients with meningiomas, including 60 -mutant samples and 45 wild-type samples. Radiomic features were extracted from magnetic resonance imaging scans, including T1-weighted, T2-weighted, and contrast T1-weighted images. Student's t-test and LASSO regression were performed to select the radiomic features. All patients were randomly divided into training and validation cohorts in a 7:3 ratio. Five linear models (RF, SVM, LR, KNN, and xgboost) were trained to predict the mutational status. Receiver operating characteristic curve and precision-recall analyses were used to evaluate the model performance. Student's t-tests were then used to compare the posterior probabilities of NF2 mut/loss prediction for patients with different NF2 statuses.
Nine features had nonzero coefficients in the LASSO regression model. No significant differences was observed in the clinical features. Nine features showed significant differences in patients with different NF2 statuses. Among all machine learning algorithms, SVM showed the best performance. The area under curve and accuracy of the predictive model were 0.85; the F1-score of the precision-recall curve was 0.80. The model risk was assessed by plotting calibration curves. The p-value for the H-L goodness of fit test was 0.411 (p> 0.05), which indicated that the difference between the obtained model and the perfect model was statistically insignificant. The AUC of our model in external validation was 0.83.
A combination of radiomic analysis and machine learning showed potential clinical utility in the prediction of preoperative NF2 status. These findings could aid in developing customized neurosurgery plans and meningioma management strategies before postoperative pathology.
本研究旨在探讨基于磁共振成像（MRI）影像组学分析预测颅内脑膜瘤患者突变状态的可行性。
本回顾性研究纳入了105例脑膜瘤患者，其中包括60例突变样本和45例野生型样本。从磁共振成像扫描中提取影像组学特征，包括T1加权、T2加权和对比增强T1加权图像。采用学生t检验和LASSO回归进行影像组学特征选择。所有患者按7:3的比例随机分为训练组和验证组。训练5种线性模型（随机森林[RF]、支持向量机[SVM]、逻辑回归[LR]、K近邻算法[KNN]和极端梯度提升[xgboost]）以预测突变状态。采用受试者工作特征曲线和精确召回率分析评估模型性能。然后使用学生t检验比较不同NF2状态患者的NF2突变/缺失预测的后验概率。
LASSO回归模型中有9个特征的系数不为零。临床特征方面未观察到显著差异。9个特征在不同NF2状态的患者中显示出显著差异。在所有机器学习算法中，SVM表现最佳。预测模型的曲线下面积和准确率为0.85；精确召回率曲线的F1值为0.80。通过绘制校准曲线评估模型风险。H-L拟合优度检验的p值为0.411（p>0.05），这表明所获得的模型与理想模型之间的差异无统计学意义。我们模型在外部验证中的AUC为0.83。
影像组学分析与机器学习相结合在术前预测NF2状态方面显示出潜在的临床应用价值。这些发现有助于在术后病理检查之前制定定制化的神经外科手术方案和脑膜瘤管理策略。
