. Author manuscript; available in PMC: 2010 Jun 1.

Published in final edited form as: Pattern Recognit. 2009 Jun 1;42(6):1162–1171. doi: 10.1016/j.patcog.2008.08.011

Table 1.

Association between different extracted features and treatment failures in a cohort of 14 cervix patients measured by Spearman's rank correlation (rs) and the area under the ROC curve (AUC).

Variable		Spearman (rs)	AUC
Tumor volume		-0.1074	0.5714
SUV Measurements	Maximum	-0.0886	0.4592
	Minimum	-0.0710	0.4592
	Mean	-0.0886	0.4592
	Standard deviation	-0.1240	0.5306
IVH Intensity-volume metrics	I₁₀	-0.1240	0.5306
	I₉₀	-0.0886	0.4592
	I_10-90	-0.1595	0.5306
	V₁₀	-0.3012	0.6122
	V₉₀	0.2304	0.6122
	V_10-90	-0.3721	0.6531
Texture-based features	Energy	-0.4276	0.7245
	Contrast	0.1949	0.6020
	Local homogeneity	-0.3012	0.6224
	Entropy	0.2304	0.6531
Shape-based features	Eccentricity	0.1949	0.6429
	Euler Number	-0.2747	0.6327
	Solidity	0.1949	0.7245
	Extent	0.2658	0.5612