Setyawan Nurhuda H, Choridah Lina, Nugroho Hanung A, Malueka Rusdy G, Dwianingsih Ery K, Supriatna Yana, Supriyadi Bambang, Hartanto Rachmat A
Department of Radiology, Faculty of Medicine, Public Health, and Nursing, Dr. Sardjito General Hospital, Universitas Gadjah Mada, Yogyakarta, IDN.
Department of Electrical and Information Engineering, Faculty of Engineering, Universitas Gadjah Mada, Yogyakarta, IDN.
Cureus. 2024 Jul 4;16(7):e63873. doi: 10.7759/cureus.63873. eCollection 2024 Jul.
This study aimed to leverage Visually AcceSAble Rembrandt Images (VASARI) radiological features, extracted from magnetic resonance imaging (MRI) scans, and machine-learning techniques to predict glioma grade, isocitrate dehydrogenase (IDH) mutation status, and O6-methylguanine-DNA methyltransferase (MGMT) methylation.
A retrospective evaluation was undertaken, analyzing MRI and molecular data from 107 glioma patients treated at a tertiary hospital. Patients underwent MRI scans using established protocols and were evaluated based on VASARI criteria. Tissue samples were assessed for glioma grade and underwent molecular testing for IDH mutations and MGMT methylation. Four machine learning models, namely, Random Forest, Elastic-Net, multivariate adaptive regression spline (MARS), and eXtreme Gradient Boosting (XGBoost), were trained on 27 VASARI features using fivefold internal cross-validation. The models' predictive performances were assessed using the area under the curve (AUC), sensitivity, and specificity.
For glioma grade prediction, XGBoost exhibited the highest AUC (0.978), sensitivity (0.879), and specificity (0.964), with f6 (proportion of non-enhancing) and f12 (definition of enhancing margin) as the most important predictors. In predicting IDH mutation status, XGBoost achieved an AUC of 0.806, sensitivity of 0.364, and specificity of 0.880, with f1 (tumor location), f12, and f30 (perpendicular diameter to f29) as primary predictors. For MGMT methylation, XGBoost displayed an AUC of 0.580, sensitivity of 0.372, and specificity of 0.759, highlighting f29 (longest diameter) as the key predictor.
This study underscores the robust potential of combining VASARI radiological features with machine learning models in predicting glioma grade, IDH mutation status, and MGMT methylation. The best and most balanced performance was achieved using the XGBoost model. While the prediction of glioma grade showed promising results, the sensitivity in discerning IDH mutations and MGMT methylation still leaves room for improvement. Follow-up studies with larger datasets and more advanced artificial intelligence techniques can further refine our understanding and management of gliomas.
本研究旨在利用从磁共振成像（MRI）扫描中提取的可视化可访问伦勃朗图像（VASARI）放射学特征和机器学习技术，预测胶质瘤分级、异柠檬酸脱氢酶（IDH）突变状态和O6-甲基鸟嘌呤-DNA甲基转移酶（MGMT）甲基化情况。
进行了一项回顾性评估，分析了一家三级医院治疗的107例胶质瘤患者的MRI和分子数据。患者按照既定方案接受MRI扫描，并根据VASARI标准进行评估。对组织样本进行胶质瘤分级评估，并进行IDH突变和MGMT甲基化的分子检测。使用五重内部交叉验证，在27个VASARI特征上训练了四个机器学习模型，即随机森林、弹性网络、多元自适应回归样条（MARS）和极端梯度提升（XGBoost）。使用曲线下面积（AUC）、敏感性和特异性评估模型的预测性能。
对于胶质瘤分级预测，XGBoost表现出最高的AUC（0.978）、敏感性（0.879）和特异性（0.964），其中f6（非强化比例）和f12（强化边缘定义）是最重要的预测因子。在预测IDH突变状态时，XGBoost的AUC为0.806，敏感性为0.364，特异性为0.880，主要预测因子为f1（肿瘤位置）、f12和f30（与f29垂直的直径）。对于MGMT甲基化，XGBoost的AUC为0.580，敏感性为0.372，特异性为0.759，突出显示f29（最长直径）为关键预测因子。
本研究强调了将VASARI放射学特征与机器学习模型相结合在预测胶质瘤分级、IDH突变状态和MGMT甲基化方面的强大潜力。使用XGBoost模型取得了最佳且最平衡的性能。虽然胶质瘤分级预测显示出有希望的结果，但在识别IDH突变和MGMT甲基化方面的敏感性仍有改进空间。使用更大数据集和更先进人工智能技术的后续研究可以进一步完善我们对胶质瘤的理解和管理。
