CT‐Based Radiomics for Preoperative Prediction of Surgical Margins in Pancreatic Head Cancer: A Tool for Selecting Patients for Neoadjuvant Chemotherapy

BACKGROUND: Microscopic margin involvement (≤ 1 mm) strongly predicts poor prognosis in pancreatic ductal adenocarcinoma (PDAC). Adjuvant chemotherapy (ACT) after upfront resection fails to fully mitigate this risk. It remains uncertain whether neoadjuvant chemotherapy (NACT) can neutralize the adverse prognostic impact of impending ≤ 1 mm margins. METHODS: Prognostic significance of ≤ 1 mm margins was assessed in an upfront-resection cohort (n = 228) using multivariable Cox regression. A separate cohort (n = 110; 52 NACT, 58 upfront surgery) compared overall survival (OS) by margin status. A CT-based radiomics model using a Laplacian-Dirichlet operator was developed to predict ≤ 1 mm margins and externally validated (n = 230). RESULTS: ≤ 1 mm margins independently predicted worse OS vs. > 1 mm (15.0 vs. 24.0 months, p = 0.005). ACT numerically extended OS for ≤ 1 mm patients (16.0 vs. 15.0 months, p = 0.271) but did not close the survival gap. Notably, ≤ 1 mm patients receiving NACT achieved median OS of 29.4 months-comparable to > 1 mm upfront patients (31.6 months)-and significantly better than ≤ 1 mm upfront patients (19.6 months, p = 0.045). The model predicted ≤ 1 mm margins with AUCs of 0.772 (95% CI: 0.705-0.838) and 0.723 (95% CI: 0.657-0.789) in internal and external validation. CONCLUSION: NACT-not ACT-selectively rescues high-risk patients destined for ≤ 1 mm margins. Our radiomics model enables preoperative identification, supporting personalized neoadjuvant therapy.