A triple-classification for differentiating renal oncocytoma from renal cell carcinoma subtypes and CK7 expression evaluation: a radiomics analysis

Table 3 The diagnostic performance of the radiomic models in the testing set (n = 57)

Classifier evaluation	CMP			NP			Combination
Classifier evaluation	RO	chRCC	ccRCC	RO	chRCC	ccRCC	RO	chRCC	ccRCC
Average AUC	0.949	0.953	0.929	0.888	0.845	0.901	0.939	0.906	0.959
95% CI	0.878, 0.996	0.891, 0.998	0.859, 0.998	0.764, 0.997	0.730, 0.960	0.811, 0.991	0.855, 0.997	0.810, 0.998	0.911, 0.996
Balanced Accuracy	0.877	0.943	0.886	0.864	0.870	0.862	0.914	0.902	0.926
Sensitivity	0.854	0.950	0.905	0.927	0.900	0.857	0.927	0.900	0.952
Specificity	0.900	0.935	0.867	0.800	0.839	0.867	0.900	0.903	0.900

AUC, the area under the curve. CI, confidence interval. CMP, corticomedullary phase. NP, nephrographic phase

ISSN: 1471-2490