Table 1.

Selected features from machine learning algorithms.

	Feature Number	Features
Logistic regression	20	First order: 10th percentile, 90th percentile, entropy, maximum, median, minimum, skewness GLCM: cluster tendency, correlation, inverse difference normalized, inverse variance, sum entropy GLRLM: gray level non uniformity, long-run low gray level emphasis, run entropy, run variance GLSZM: gray level non uniformity normalized, large area high gray level emphasis, size zone non uniformity normalized, small area emphasis, zone entropy
Support vector machine	20	First order: 10th percentile, 90th percentile, entropy, maximum, median, robust mean absolute deviation, skewness GLCM: cluster shade, correlation, inverse difference normalized, informational measure of correlation 1, informational measure of correlation 2, joint entropy, maximum probability, sum entropy GLRLM: high gray level run emphasis GLSZM: high gray level zone emphasis, large area high gray level emphasis, size zone non uniformity normalized, zone entropy
Random forest	19	First order: mean, median, root mean squared, skewness GLCM: autocorrelation, cluster prominence, cluster shade, difference variance, joint average, joint energy, maximum probability, sum average GLRLM: gray level variance, high gray level run emphasis, long-run high gray level emphasis, short–run high gray level emphasis GLSZM: large area high gray level emphasis, small area high gray level emphasis, zone percentage
Extreme gradient boost	18	First order: mean, median, range, root mean squared, skewness, uniformity GLCM: cluster shade, contrast, inverse difference normalized, informational measure of correlation 2, maximum probability GLRLM: gray level non uniformity normalize, gray level variance, high gray level run emphasis, run length non uniformity normalized, short run emphasis GLSZM: gray level variance, zone percentage

GLCM, gray level co-occurrence matrix; GLRLM, gray level run length matrix; GLSZM, gray level size zone matrix.