Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
Department of Neurosurgery, Guangzhou General Hospital of Guangzhou Military Command, Guangzhou, China.
Cancer Med. 2018 Dec;7(12):5999-6009. doi: 10.1002/cam4.1863. Epub 2018 Nov 13.
Isocitrate dehydrogenase 1 (IDH1) has been proven as a prognostic and predictive marker in glioblastoma (GBM) patients. The purpose was to preoperatively predict IDH mutation status in GBM using multiregional radiomics features from multiparametric magnetic resonance imaging (MRI).
In this retrospective multicenter study, 225 patients were included. A total of 1614 multiregional features were extracted from enhancement area, non-enhancement area, necrosis, edema, tumor core, and whole tumor in multiparametric MRI. Three multiregional radiomics models were built from tumor core, whole tumor, and all regions using an all-relevant feature selection and a random forest classification for predicting IDH1. Four single-region models and a model combining all-region features with clinical factors (age, sex, and Karnofsky performance status) were also built. All models were built from a training cohort (118 patients) and tested on an independent validation cohort (107 patients).
Among the four single-region radiomics models, the edema model achieved the best accuracy of 96% and the best F1-score of 0.75 while the non-enhancement model achieved the best area under the receiver operating characteristic curve (AUC) of 0.88 in the validation cohort. The overall performance of the tumor-core model (accuracy 0.96, AUC 0.86 and F1-score 0.75) and the whole-tumor model (accuracy 0.96, AUC 0.88 and F1-score 0.75) was slightly better than the single-regional models. The 8-feature all-region radiomics model achieved an improved overall performance of an accuracy 96%, an AUC 0.90, and an F1-score 0.78. Among all models, the model combining all-region imaging features with age achieved the best performance of an accuracy 97%, an AUC 0.96, and an F1-score 0.84.
The radiomics model built with multiregional features from multiparametric MRI has the potential to preoperatively detect the IDH1 mutation status in GBM patients. The multiregional model built with all-region features performed better than the single-region models, while combining age with all-region features achieved the best performance.
异柠檬酸脱氢酶 1（IDH1）已被证明是胶质母细胞瘤（GBM）患者的预后和预测标志物。本研究旨在使用多参数磁共振成像（MRI）的多区域放射组学特征术前预测 GBM 中的 IDH 突变状态。
在这项回顾性多中心研究中，共纳入 225 例患者。从增强区、非增强区、坏死、水肿、肿瘤核心和整个肿瘤中提取了 1614 个多区域特征。使用全相关特征选择和随机森林分类，从肿瘤核心、整个肿瘤和所有区域构建了 3 个多区域放射组学模型，以预测 IDH1。还构建了 4 个单区域模型和一个结合所有区域特征与临床因素（年龄、性别和卡诺夫斯基表现状态）的模型。所有模型均基于训练队列（118 例患者）构建，并在独立验证队列（107 例患者）上进行测试。
在 4 个单区域放射组学模型中，水肿模型在验证队列中的准确率最高（96%），F1 评分最高（0.75），而非增强模型的受试者工作特征曲线（ROC）下面积（AUC）最高（0.88）。肿瘤核心模型（准确率 0.96、AUC 0.86 和 F1 评分 0.75）和整个肿瘤模型（准确率 0.96、AUC 0.88 和 F1 评分 0.75）的整体性能略优于单区域模型。包含所有区域的 8 个特征放射组学模型的整体性能有所提高，准确率为 96%、AUC 为 0.90、F1 评分为 0.78。在所有模型中，结合所有区域成像特征和年龄的模型表现最佳，准确率为 97%、AUC 为 0.96、F1 评分为 0.84。
使用多参数 MRI 的多区域特征构建的放射组学模型具有预测 GBM 患者 IDH1 突变状态的潜力。基于所有区域特征构建的多区域模型比单区域模型表现更好，而结合年龄和所有区域特征则可获得最佳性能。
