Adding Delayed Phase Images to Dual-Phase Contrast-Enhanced CT Increases Sensitivity for Small Pancreatic Ductal Adenocarcinoma.

Background: Contrast-enhanced CT performed for pancreatic ductal adenocarcinoma (PDAC) detection traditionally uses a dual-phase (pancreatic and portal venous) protocol. However, PDAC may exhibit isoattenuation in these phases, hindering detection. Objective: To assess the impact on diagnostic performance in detection of small PDAC of adding a delayed phase to dual-phase contrast-enhanced CT. Methods: A database of 571 patients who underwent triple-phase (pancreatic, portal venous, and delayed) contrast-enhanced MDCT between January 2017 and March 2020 for suspected pancreatic tumor was retrospectively reviewed. A total of 97 patients had pathologically confirmed small PDAC (mean size, 22 mm; range, 7-30 mm). Twenty control patients had no pancreatic tumor suspected on CT nor on an initial MRI and follow-up CT or MRI after ≥12 months. Three radiologists independently reviewed dual-phase (pancreatic and portal venous) and triple-phase (pancreatic, portal venous, and delayed) images. Two additional radiologists assessed tumors' visual attenuation on each phase, reaching consensus for differences. Performance of dual- and triple-phase images were compared using ROC analysis, McNemar test, and Fisher's exact test. Results: AUC was higher (P<.05) for triple-phase than dual-phase images for all observers (observer 1, 0.97 vs 0.94; observer 2, 0.97 vs 0.94; observer 3, 0.97 vs 0.95). Sensitivity was higher (P<.001) for triple-phase than dual-phase images for all observers [observer 1, 74.2% (72/97) vs 59.8% (58/97); observer 2, 88.7% (86/97) vs 71.7% (69/97); observer 3, 86.6% (84/97) vs 72.2% (70/97)]. Specificity, PPV, and NPV did not differ between image sets for any reader (P≥.05). Seventeen tumors showed pancreatic phase visual isoattenuation, of which nine showed isoattenuation and eight hyperattenuation in the delayed phase. Sixteen of these were not detected by any observer on dual-phase images; of these, six were detected by at least two observers, and five by one observer, on triple-phase images. Visual attenuation showed excellent interreader agreement (κ=0.89-0.96). Conclusion: Addition of delayed phase to pancreatic and portal venous phase CT increases sensitivity for small PDAC without loss of specificity, partly related to delayed phase hyperattenuation of some small PDACs showing pancreatic phase isoattenuation. Clinical Impact: Addition of delayed phase may facilitate earlier PDAC detection and thus improved prognosis.