. 2020 Mar 6;10:4250. doi: 10.1038/s41598-020-61178-w

Table 2.

Selected radiomic features in the multiparametric MRI imaging and in each MRI.

Result category	CET1	FLAIR	ADC	CBV
Individual features	Sum entropy (mean) LLH GLCM dist = 3 (P = 0.0003)	Mean absolute deviation LHH first order (P = 0.0023) High gray-level run emphasis (std)(P = 0.0003)	Skewness HHH first order (P = 0.0008)	Entropy (std) HHL GLCM dist = 1 (P = 0.0014) Long run high gray-level emphasis (mean) HHH GLRLM (P = 0.0003)

Result category

CET1

FLAIR

ADC

CBV

Individual features

Sum entropy (mean) LLH GLCM dist = 3

(P = 0.0003)

Mean absolute deviation LHH first order (P = 0.0023)

High gray-level run emphasis (std)(P = 0.0003)

Skewness HHH first order (P = 0.0008)

Entropy (std) HHL GLCM dist = 1 (P = 0.0014)

Long run high gray-level emphasis (mean) HHH GLRLM (P = 0.0003)

P-value for each radiomic feature associated with outcome was calculated using univariate Cox proportional hazards regression.

Abbreviations: CET1 = contrast-enhanced T1-weighted imaging, FLAIR = fluid-attenuated inversion recovery, ADC = apparent diffusion coefficient, CBV = cerebral blood volume. H = high-pass filter, L = low-pass filter, GLCM = gray-level co-occurrence matrix, GLRLM = gray-level run-length matrix.