Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95 Yongan Road, Beijing 100050, China; Department of Radiology, the Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, No. 127 Dongming Road, Zhengzhou, Henan 450008, China.
Department of Radiology, the Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, No. 127 Dongming Road, Zhengzhou, Henan 450008, China.
Magn Reson Imaging. 2023 Dec;104:72-79. doi: 10.1016/j.mri.2023.09.001. Epub 2023 Sep 30.
To establish and validate a radiomics nomogram for preoperative prediction of isocitrate dehydrogenase (IDH) mutation status of gliomas in a multicenter setting.
414 gliomas patients were collected (306 from local institution and 108 from TCGA). 851 radiomics features were extracted from contrast-enhanced T1-weighted (CE-T1W) and fluid attenuated inversion recovery (FLAIR) sequence, respectively. The features were refined using least absolute shrinkage and selection operator (LASSO) regression combing 10-fold cross-validation. The optimal radiomics features with age and sex were processed by multivariate logistic regression analysis to construct a prediction model, which was developed in the training dataset and assessed in the test and validation dataset. Receiver operating characteristic (ROC) curve, calibration curve and decision curve analysis were applied in the test and external validation datasets to evaluate the performance of the prediction model.
Ten robust radiomics features were selected from the 1702 features (four CE-T1W features and six FLAIR features). A nomogram was plotted to represent the prediction model. The accuracy and AUC of the radiomics nomogram achieved 86.96% and 0.891(0.809-0.947) in the test dataset and 84.26% and 0.881(0.805-0.936) in the external validation dataset (all p < 0.05). The positive predictive value (PPV) and negative predictive value (NPV) were 83.72% and 87.75% in the test dataset and 87.81% and 82.09% in the external validation dataset.
IDH genotypes of gliomas can be identified by preoperative multiparametric MRI radiomics nomogram and might be clinically meaningful for treatment strategy and prognosis stratification of gliomas.
建立并验证一个基于放射组学的nomogram 模型，用于在多中心环境下术前预测胶质瘤的异柠檬酸脱氢酶（IDH）突变状态。
共纳入 414 例胶质瘤患者（306 例来自本地机构，108 例来自 TCGA）。分别从对比增强 T1 加权（CE-T1W）和液体衰减反转恢复（FLAIR）序列中提取 851 个放射组学特征。使用最小绝对收缩和选择算子（LASSO）回归结合 10 折交叉验证对特征进行精炼。使用多元逻辑回归分析对最优放射组学特征（结合年龄和性别）进行处理，构建预测模型，在训练数据集和测试数据集进行开发，并在验证数据集进行评估。在测试和外部验证数据集上应用受试者工作特征（ROC）曲线、校准曲线和决策曲线分析来评估预测模型的性能。
从 1702 个特征中（CE-T1W 特征 4 个，FLAIR 特征 6 个）筛选出 10 个稳健的放射组学特征。绘制了一个 nomogram 来表示预测模型。在测试数据集和外部验证数据集中，放射组学 nomogram 的准确性和 AUC 分别达到 86.96%和 0.891（0.809-0.947）和 84.26%和 0.881（0.805-0.936）（均 P<0.05）。测试数据集和外部验证数据集中的阳性预测值（PPV）和阴性预测值（NPV）分别为 83.72%和 87.75%和 87.81%和 82.09%。
术前多参数 MRI 放射组学 nomogram 可识别胶质瘤的 IDH 基因型，可能对胶质瘤的治疗策略和预后分层具有临床意义。
