Table 1. Available options for each step in the radiomics pipeline: Data normalization, dimension reduction, feature selection, and classifier.

All methods implemented based on scikit-learn [12].

Steps	Candidate
Data	Min-max Normalization
Normalization	Z-score Normalization
	Mean Normalization
Dimension	Pearson Correlation Coefficient (PCC)
Reduction	Principle Component Analysis (PCA)
Feature Selection	Analysis of Variance (ANOVA)
	Recursive Feature Elimination (RFE)
	Relief
Classifier	Linear Regression
	Least Absolute Shrinkage and Selection Operator (LASSO)
	Support Vector Machine (SVM)
	Linear Discriminant Analysis (LDA)
	Decision Tree
	Random Forest
	Adaboost
	Gaussian Process
	Naïve Bayes
	Multilayer Perceptron