Table 3.

Applications of radiomics-based classification of malignant versus benign tumors

Image modality	Number of patients	Cancer	Target	Number of radiomics features	Commercial or open-source software	Method	References
MRI	130	HNSCC	Classify benign and malignant tumors, differentiate ENE	89/6	3D Slicer, Segmentation Wizard, Python	ML: Adam optimization algorithm SM: t-test DL: Multilayer perceptron neural network	[21]
CT	285	HCC and hepatic hemangioma	Classify benign and malignant tumors	13	Matlab	ML: LR, LASSO, SVM, Multiple-regression	[22]
MRI	69	Parotid lesions	Classify benign and malignant tumors	4	Matlab, S-IBEX	ML: SVM, NCA, CV SM: Chi-square test, Mann–Whitney test, Spearman correlation coefficient, Z-score	[23]

MRI magnetic resonance imaging, CT computed tomography, ML machine learning, SM statistical method, DL deep learning, HNSCC head and neck squamous cell carcinoma, HCC hepatocellular carcinoma, ENE extra-nodal extension, LR logistic regression, LASSO least absolute shrinkage and selection operator, SVM support vector machine, NCA neighborhood component analysis, CV cross validation