Systematic Analysis of Accuracy in Predicting Complete Oncological Resection in Pancreatic Cancer Patients-Proposal of a New Simplified Borderline Resectability Definition

Background: Borderline resectability in pancreatic cancer (PDAC) is currently debated. Methods: Patients undergoing pancreatic resections for PDAC were identified from a prospectively maintained database. As new borderline criteria, the presence of any superior mesenterico-portal vein alteration (SMPV) and perivascular stranding of the superior mesenteric artery (SMA) was evaluated in preoperative imaging. The accuracy of established radiological borderline criteria as compared to the new borderline criteria in predicting R status (sensitivity/negative predictive value) and overall survival was assessed. Results: 118 patients undergoing pancreatic resections for PDAC from 2013 to 2018 were identified. Forty-three (36.4%) had radiological perivascular SMA stranding and 55 (46.6%) had SMPV alterations. Interrater reliability was 90% for SMA stranding and 87% for SMPV alterations. The new borderline definition including SMPV alterations and perivascular SMA stranding was the best predictor of conventional R status (p = 0.040, sensitivity 53%, negative predictive value 81%) and Leeds/Wittekind circumferential margin status (p = 0.050, sensitivity 73%, negative predictive value 79%) as compared to established borderline resectability definition criteria. Perivascular SMA stranding qualified as an independent negative prognostic parameter (HR 3.066, 95% CI 1.078-5.716, p = 0.036). Conclusion: The radiological evaluation of any SMPV alteration and perivascular SMA stranding predicts R status and overall survival in PDAC patients, and may serve to identify potential candidates for neoadjuvant therapy.