■在成人弥漫性神经胶质瘤中,术前检测异柠檬酸脱氢酶(IDH)状态有助于临床医师制定手术策略和评估患者预后.这里,我们的目标是通过结合深度学习(DL)签名和常规放射组学(CR)特征作为模型预测因子,确定用于预测IDH基因分型的最佳机器学习模型.
■在这项研究中,从我们的医疗中心(n=268)和公共数据库(TCGA,n=218)。通过使用嵌套的10倍交叉验证,将所有纳入的患者随机分为训练集和验证集。从每位患者的四种MRI模式中总共提取了6,736个CR特征,即T1WI,T1CE,T2WI,和FLAIR。执行LASSO算法用于CR特征选择。在每种MRI模式中,我们应用了基于CNN+LSTM的神经网络来提取DL特征,并在具有sigmoid激活的完全连接层之后将这些特征集成到DL签名中。通过结合LASSO选择的CR特征和集成的DL签名作为模型预测因子,对八个经典的机器学习模型在IDH基因分型中的预测性能和稳定性进行了分析和比较。在验证集中,通过使用接收器工作特性的准确性和曲线下面积(AUC)来评估预测性能,同时使用AUC的相对标准偏差(RSDAUC)对模型稳定性进行分析。还单独进行DL特征和CR特征的亚组分析以探索它们的独立预测值。
■逻辑回归(LR)取得了良好的预测性能(AUC:0.920±0.043,精度:0.843±0.044),而具有线性核的支持向量机(l-SVM)显示出较低的预测性能(AUC:0.812±0.052,准确性:0.821±0.050)。关于稳定性,LR还显示了对数据扰动的高鲁棒性(RSDAUC:4.7%)。亚组分析表明,DL签名优于CR特征(DL,AUC:0.915±0.054,准确度:0.835±0.061,RSDAUC:5.9%;CR,AUC:0.830±0.066,准确度:0.771±0.051,RSDAUC:8.0%),而DL和DL+CR取得了相似的预测结果。
■在IDH基因分型中,LR是一种有前途的机器学习分类模型。与CR特征相比,DL特征表现出明显优异的预测值和辨别能力。
UNASSIGNED: In adult diffuse glioma, preoperative detection of isocitrate dehydrogenase (
IDH) status helps clinicians develop surgical strategies and evaluate patient prognosis. Here, we aim to identify an optimal machine-learning model for prediction of
IDH genotyping by combining deep-learning (DL) signatures and conventional radiomics (CR) features as model predictors.
UNASSIGNED: In this study, a total of 486 patients with adult diffuse gliomas were retrospectively collected from our medical center (n=268) and the public database (TCGA, n=218). All included patients were randomly divided into the training and validation sets by using nested 10-fold cross-validation. A total of 6,736 CR features were extracted from four MRI modalities in each patient, namely T1WI, T1CE, T2WI, and FLAIR. The LASSO algorithm was performed for CR feature selection. In each MRI modality, we applied a CNN+LSTM-based neural network to extract DL features and integrate these features into a DL signature after the fully connected layer with sigmoid activation. Eight classic machine-learning models were analyzed and compared in terms of their prediction performance and stability in
IDH genotyping by combining the LASSO-selected CR features and integrated DL signatures as model predictors. In the validation sets, the prediction performance was evaluated by using accuracy and the area under the curve (AUC) of the receiver operating characteristics, while the model stability was analyzed by using the relative standard deviation of the AUC (RSDAUC). Subgroup analyses of DL signatures and CR features were also individually conducted to explore their independent prediction values.
UNASSIGNED: Logistic regression (LR) achieved favorable prediction performance (AUC: 0.920 ± 0.043, accuracy: 0.843 ± 0.044), whereas support vector machine with the linear kernel (l-SVM) displayed low prediction performance (AUC: 0.812 ± 0.052, accuracy: 0.821 ± 0.050). With regard to stability, LR also showed high robustness against data perturbation (RSDAUC: 4.7%). Subgroup analyses showed that DL signatures outperformed CR features (DL, AUC: 0.915 ± 0.054, accuracy: 0.835 ± 0.061, RSDAUC: 5.9%; CR, AUC: 0.830 ± 0.066, accuracy: 0.771 ± 0.051, RSDAUC: 8.0%), while DL and DL+CR achieved similar prediction results.
UNASSIGNED: In
IDH genotyping, LR is a promising machine-learning classification model. Compared with CR features, DL signatures exhibit markedly superior prediction values and discriminative capability.