Anatomy-informed CT Spatial Phenotype Associated with Extrapancreatic Perineural Invasion in Resected Pancreatic Ductal Adenocarcinoma

Purpose To develop and evaluate an interpretable CT spatial phenotype associated with extrapancreatic perineural invasion (EPNI) in resected pancreatic ductal adenocarcinoma. Materials and Methods This multicenter study included training, internal testing, neoadjuvant testing, retrospective external testing, prospective external testing, and The Cancer Imaging Archive (TCIA) sets. The Preoperative Risk of Perineural High-risk Extension in Tumors (PROPHET) model and threshold were locked before testing. Performance was assessed with area under the receiver operating characteristic curve (AUC) and threshold metrics. Six radiologists compared unaided and assisted readings. A stratified Cox model related PROPHET risk to survival, adjusting for age, sex, tumor size, carbohydrate antigen 19-9, nodal category, and differentiation. Results Among 1854 patients (median age, 63 years; 1131 male), AUCs were 0.92 (95% CI, 0.86–0.96) in prospective external testing, 0.85 (95% CI, 0.75–0.93) in retrospective external testing, 0.90 (95% CI, 0.83–0.95) after neoadjuvant therapy, 0.99 (95% CI, 0.98–> 0.99) in internal testing, and 0.80 (95% CI, 0.68–0.93) in TCIA. TCIA sensitivity and specificity were 24/30 (80%) and 2/19 (11%). Assistance increased mean sensitivity to 93% from 82% and reduced reading time to 3.02 from 3.64 minutes per patient (both Holm-adjusted P < .001). Higher PROPHET risk was associated with shorter survival (adjusted hazard ratio, 1.95; 95% CI, 1.53–2.47; nominal P < .001). Conclusion PROPHET provides a CT-visible tumor-vessel spatial phenotype associated with pathologically confirmed EPNI.