The differentiation of pancreatic neuroendocrine carcinoma from pancreatic ductal adenocarcinoma: the values of CT imaging features and texture analysis

Table 2 Diagnostic performance of CT features and texture features for differentiating PNEC from PDAC

	Variables	AUC	Sensitivity (95% CI)	Specificity (95% CI)	Cutoff point
CT features	AER	0.99	1.0 (0.77–1.0)	0.93 (0.66–1.00)	0.56
	PER Size Margins Parenchymal atrophy	0.98 0.67 0.66 0.70	0.93 (0.66–1.0) 0.47 (0.28–0.69) 0.75 (0.55–0.89) 0.68 (0.48–0.84)	1.00 (0.77–1.00) 1.00 (0.72–1.00) 0.57 (0.29–0.82) 0.71 (0.42–0.92)	0.63 2.73
Texture features at portal phase	F3 uniformity	0.72	0.79 (0.54–0.94)	0.65 (0.41–0.85)	0.34
	F3 entropy	0.71	0.74 (0.49–0.91)	0.70 (0.46–0.88)	1.89

f1-f3 denote sigma values of 0.5, 1.5 and 2.5, respectively. CI confidence interval; AER enhancement ratio at arterial phase; PER enhancement ratio at portal phase; AUC area under the curve

ISSN: 1470-7330