1Department of Neurosurgery, Vanderbilt University Medical Center.
3Vanderbilt University School of Medicine.
Neurosurg Focus. 2018 Nov 1;45(5):E4. doi: 10.3171/2018.8.FOCUS18191.
OBJECTIVEPrognostication and surgical planning for WHO grade I versus grade II meningioma requires thoughtful decision-making based on radiographic evidence, among other factors. Although conventional statistical models such as logistic regression are useful, machine learning (ML) algorithms are often more predictive, have higher discriminative ability, and can learn from new data. The authors used conventional statistical models and an array of ML algorithms to predict atypical meningioma based on radiologist-interpreted preoperative MRI findings. The goal of this study was to compare the performance of ML algorithms to standard statistical methods when predicting meningioma grade.METHODSThe cohort included patients aged 18-65 years with WHO grade I (n = 94) and II (n = 34) meningioma in whom preoperative MRI was obtained between 1998 and 2010. A board-certified neuroradiologist, blinded to histological grade, interpreted all MR images for tumor volume, degree of peritumoral edema, presence of necrosis, tumor location, presence of a draining vein, and patient sex. The authors trained and validated several binary classifiers: k-nearest neighbors models, support vector machines, naïve Bayes classifiers, and artificial neural networks as well as logistic regression models to predict tumor grade. The area under the curve-receiver operating characteristic curve was used for comparison across and within model classes. All analyses were performed in MATLAB using a MacBook Pro.RESULTSThe authors included 6 preoperative imaging and demographic variables: tumor volume, degree of peritumoral edema, presence of necrosis, tumor location, patient sex, and presence of a draining vein to construct the models. The artificial neural networks outperformed all other ML models across the true-positive versus false-positive (receiver operating characteristic) space (area under curve = 0.8895).CONCLUSIONSML algorithms are powerful computational tools that can predict meningioma grade with great accuracy.
对于 WHO 分级 I 级和 II 级脑膜瘤，需要基于影像学证据等因素进行深思熟虑的决策。虽然传统的统计模型（如逻辑回归）很有用，但机器学习（ML）算法通常更具预测性、具有更高的判别能力，并且可以从新数据中学习。作者使用传统的统计模型和一系列 ML 算法，基于放射科医生解释的术前 MRI 结果预测非典型脑膜瘤。本研究的目的是比较 ML 算法和标准统计方法在预测脑膜瘤分级方面的性能。
该队列包括 1998 年至 2010 年间接受术前 MRI 检查的 18-65 岁 WHO 分级 I（n=94）和 II（n=34）级脑膜瘤患者。一名经过董事会认证的神经放射科医生，对肿瘤体积、瘤周水肿程度、坏死存在、肿瘤位置、引流静脉存在以及患者性别等 MRI 图像进行解读，同时对组织学分级不知情。作者训练和验证了几种二分类器：k-最近邻模型、支持向量机、朴素贝叶斯分类器和人工神经网络以及逻辑回归模型，以预测肿瘤分级。曲线下面积-接收者操作特征曲线用于模型内和模型间的比较。所有分析均在 MATLAB 中使用 MacBook Pro 进行。
作者纳入了 6 个术前影像学和人口统计学变量：肿瘤体积、瘤周水肿程度、坏死存在、肿瘤位置、患者性别和引流静脉，用于构建模型。人工神经网络在真阳性与假阳性（接收者操作特征）空间（曲线下面积=0.8895）上优于所有其他 ML 模型。
ML 算法是强大的计算工具，可以非常准确地预测脑膜瘤分级。
