Radiomics in photon-counting dedicated breast CT: potential of texture analysis for breast density classification

European Radiology Experimental

Table 2 Texture feature descriptives and p values for post hoc Bonferroni correction for each feature

Feature	Mean	Standard deviation	95% confidence interval		p value after
Feature	Mean	Standard deviation	Lower	Upper	Bonferroni correction
Variance	187.03	74.15	185.57	188.48	< 0.001
Skewness	0.22	1.0	0.20	0.24	< 0.001
Kurtosis	0.34	1.76	0.31	0.38	< 0.001
Entropy	14.76	10.93	14.55	14.97	< 0.001
Contrast	0.93	0.05	0.93	0.93	< 0.001
Correlation	0.01	0.01	0.06	0.06	0.002
Energy	0.42	0.08	0.41	0.42	< 0.001
Homogeneity	16,193	0.30	5.44	5.45	0.01
SRE	0.89	0.05	0.89	0.89	1.0 *
LRE	1.77	1.66	1.74	1.81	0.1 **
GLN	468.09	176.12	464.64	471.54	< 0.001
RLN	9,432.94	4,143.13	9,351.72	9,514.16	< 0.001
RP	0.85	0.62	0.85	0.85	0.9 *
LGRE	0	0	0		0.4 **
HGRE	1,156.60	34.88	1,155.92	1,157.29	1.0
SRLGE	0	0	0		0.006
SRHGE	1,026.89	52.03	1,025.87	1,027.90	1.0 *
LRLGE	0.03	0.12	0.02	0.03	0.6
LRHGE	2,087.82	1,428.11	2,059.82	2,115.81	0.4

GLN Grey-level nonuniformity, HGRE High grey-level run emphasis, LGRE Low grey-level run emphasis, LRE Long-run emphasis, LRHGE Long-run high-grey-level emphasis, LRLGE Long-run low-grey-level emphasis, RLN Run-length nonuniformity, RP Run-percentage, SRE Short-run emphasis, SRHGE Short-run high-grey-level emphasis, SRLGE Short-run low-grey-level emphasis
*Only valid for level c compared to level d, all other p values being < 0.001
**Only valid for level a compared to level b, all other p values being < 0.001