Table 2.

Eight different radiomics feature categories along with a short explanation of each category is shown in this table.

Category	Number of radiomics features	Radiomics features
IBHF	9 features	Nine features are extracted from histogram of the pixel intensity values: 1-Mean, 2-Standard Deviation, 3-Skewness, 4-Kurtosis, 5-Entropy, 6-Central Moment of 3rd order, 7- Central Moment of 4th Order, 8- Central Moment of 5th Order, 9- Central Moment of 6th Order.
GLRL	7 features	Seven Gray Level Run Length texture descriptors were constructed based on the following emphasizes: Short Run Emphasis (SRE), Long Run Emphasis (LRE), Gray Level Non-Uniformity (GLN), Run Percentage (RP), Run Length Non-Uniformity (RLN), Low Gray Level Run Emphasis (LGRE), and High Gray Level Run Emphasis (HGRE).
LAWS	18 features	Nine textural maps were constructed by filtering the image data using the following convolution kernels: L5 = [1 4 6 4 1], E5 = [−1 −2 0 2 1], S5 = [−1 0 2 0 −1], R5 = [1 −4 6 −4 1] and then, 18 LAWS textural features were computed by applying and combining the energy and entropy operators on these maps as following: L5E5/E5L5, L5R5/R5L5, E5S5/S5E5, S5S5, R5R5, L5S5/S5L5, E5E5, E5R5/R5E5, and S5R5/R5S5.
DOST	18 features	The two-dimensional matrix of DOST coefficients was divided into nine equal segments and the energy and entropy of each segment was averaged over the tumor volume and eighteen features (nine energy along with nine entropy) were generated and used as the DOST radiomics features.
LBP	6 features	Local Binary Pattern algorithm with a radial filter (eight-neighborhood) was used to generate a two-dimensional LBP map and Entropy, Entropy, Mean, Standard Deviation, Skewness, and Kurtosis of the LBP maps were used as the six LBPF radiomics features.
2DWT	48 features	Two-dimensional Wavelet Transform with six decomposition levels for four different information attributes (Multi-resolution image, vertical, horizontal, and diagonal) was used to generate 24 maps of 2DWT information. Energy and entropy of the information maps were calculated and used as the 48 2DWT radiomics features.
2DGF	40 features	Two-dimensional Gabor (2DG) filter with five different scales for four different orientations generated 20 maps. Energy and entropy of the maps was averaged over the tumor volume and used as the 2DGT radiomics features.
GLCM	22 features	Gray-Level-Co-occurrence Matrix (GLCM) was generated and the following 22 features were measured from the GLCM using an 8-bit depth quantization: 1-Autocorrelation, 2-Contrast, 3-Correlation (2), 4-Correlation (1), 5-Cluster Prominence, 6-Cluster Shade, 7-Dissimilarity, 8-Energy, 9-Entropy, 10-Homogeneity (1), 11-Homogeneity (2), 12-Maximum probability, 13-Sum of squares(Variance), 14-Sum average, 15-Sum variance, 16-Sum entropy, 17-Difference variance, 18-Difference entropy, 19-Information measure of correlation (1), 20-Information measure of correlation (2), 21-Inverse difference normalized, and 22-Inverse difference moment normalized.