Skip to main content
Fig. 5 | Cancer Imaging

Fig. 5

From: Dual-energy computed tomography in a multiparametric regression model for diagnosing lymph node metastases in pancreatic ductal adenocarcinoma

Fig. 5

Receiver operating characteristic curve of the quantitative dual-energy computed tomography parameters model. The best threshold value for the predictive probability of binary logistic regression models of multiple parameters in differentiating between benign and metastatic lymph nodes was 0.66 cm. Area under the curve (AUC) was 0.991 (95% confidence interval, 0.975–0.997). The parameter model showed good discrimination

Back to article page