Texture-based classification of different single liver lesion based on SPAIR T2W MRI images

BMC Medical Imaging

Table 2 Sensitivity and specificity for ability of textural to differentiate between HH and HM

Feature	Parameters	P	S.E.	AUC	95% CI	Sensitivity	Specificity
GLCM	Energy_mean	0.014	0.090	0.734	56.65%-82.45%	0.706	0.905
GLCM	Homogeneity_mean	0.012	0.075	0.782	64.23%-88.32%	0.619	0.941
GLRLM	SRE_0/45	0.016	0.062	0.825	61.45%-84.72%	0.933	0.667
		0.021	0.057	0.812	62.12%-86.32%	0.824	0.867
	SRHGE_0/45/90	0.012	0.068	0.801	61.45%-84.72%	0.762	0.867
		0.024	0.059	0.822	62.25%-87.33%	0.813	0.762
		0.016	0.102	0.792	58.63%-84.36%	0.922
ISZM	Small zone emphasis	0.009	0.074	0.851	73.23%-88.23%	0.932	0.762
ISZM	High-intensity small-Zone emphais	0.007	0.067	0.832	71.23%-85.35%	0.810	0.733

Abbreviations: AUC area under the curve, CI confidence interval, SRE Short Run Emphasis, SRHGE Short Run High Gray-Level Emphasis. SRE_0/45/90/135 and SRHGE_0/45/90/135 depicted the parameters of SRE and SRHGE in four directions, for SRE_0/45, two directions (0 degree and 45 degree) were calculated for SRE

ISSN: 1471-2342