Table 3 Overview of all classifiers used during training
From: Evaluation of the dependence of radiomic features on the machine learning model
Classifier | Hyperparameters |
|---|---|
Linear discriminant analysis (LDA) | – |
Linear SVM | Regularization parameter C in 2**{− 6, − 4, − 2, 0, 2, 4, 6} |
Logistic regression | Regularization parameter, C in 2**{− 6, − 4, − 2, 0, 2, 4, 6} |
Naive Bayes | – |
Neural network (three layers) | Neurons in layer 1, 2, 3 in {4, 16, 64} |
Random forest | Number of trees in 50, 250, 500 |
Radial basis function-SVM (RBF-SVM) | Regularization parameter, C in 2**{− 6, − 4, − 2, 0, 2, 4, 6}, Kernel parameter γ = auto |
XGBoost | Learning rate in 0.001, 0.1, 0.3, 0.9, number of estimators in 50, 250, 500 |