Fig. 4: Performance metrics of PAN-VIQ for vascular invasion classification across internal and external validation cohorts. | npj Digital Medicine

Fig. 4: Performance metrics of PAN-VIQ for vascular invasion classification across internal and external validation cohorts.

From: A clinically validated 3D deep learning approach for quantifying vascular invasion in pancreatic cancer

Fig. 4

This figure presents the classification performance of PAN-VIQ for five peripancreatic vessels, including the celiac artery (CA), common hepatic artery (CHA), superior mesenteric artery (SMA), superior mesenteric vein (SMV), and portal vein (PV), using radar plots to visualize five key evaluation metrics: accuracy, precision, recall, F1 score, and specificity. Panel A displays the results from the internal validation cohort comprising 2130 patients. Panel B illustrates performance across three independent external datasets with sample sizes of 169, respectively.

Back to article page