Citations 1
Spatial Configuration of Pancreatic Cancer Is Associated with Disease Recurrence after Neoadjuvant Therapy and Curative-Intent Resection
Cisneros, Luis , Toruner, Merih Deniz , Siddiqui, Zafar , Maraone, Andrea V. , Lin, Miranda , Xiao, Alexander , Thiels, Cornelius A. , Truty, Mark J. , George, Ben , Jazieh, Khalid , Scheel, Robert , Hartley, Christopher , Elhalaby, Rofyda , Dizona, Paul , Fernández-Zapico, Martín E. , Carr, Ryan M. , Cisneros, Luis H , Toruner, Merih D , Xiao, Alexander H , Thiels, Cornelius A , Scheel, Robb , McWilliams, Robert R , Maley, Carlo C. , Hartley, Christopher P , Elhalaby, Rofyda Essam , Dizona, Paul , Shi, Qian , Fernandez-Zapico, Martin E , Carr, Ryan M , Truty, Mark J , Garzaro, Andrea V. Maraone , Lin, Miranda , George, Ben , McWilliams, Robert R. , Shi, Qian
Clinical Cancer Research | July 15, 2026 | Volume: No volume available | Issue: No issue available | Pages: OF1-OF16
Abstract Purpose: Pancreatic ductal adenocarcinoma (PDAC) frequently recurs after neoadjuvant therapy (NT) and curative-intent resection. Although major pathologic response predicts favorable outcomes, most patients achieve only minor response with a heterogeneous recurrence risk. We asked whether the spatial organization of residual PDAC encodes clinically relevant biology beyond residual tumor burden. Experimental Design: In a retrospective cohort of 203 patients with resected PDAC treated with NT and restricted to minor pathologic response, routine hematoxylin and eosin (H&E) whole-slide images were segmented into cancer and stroma using an artificial intelligence–enabled pipeline. Spatial composition (patch density, edge density) and configuration (compactness/complexity, intermixing) were quantified and tested for associations with disease-free survival (DFS) using multivariable models adjusted for standard clinicopathologic factors. Results: Shorter DFS was associated with a fragmented, interface-rich tumor–stroma ecology featuring higher edge density and diversity and reduced homotypic aggregation, independent of clinicopathologic variables. Two spatial risk models were independently prognostic: (i) cancer mean shape index plus stromal shape index variability [adjusted hazard ratio (HR), 1.71; P = 0.003] and (ii) mean stromal patch area plus edge density (adjusted HR, 2.19; P = 0.002). Both models stratified outcomes in which pathologic response grading and residual cancer area did not. High-risk configurations were further associated with reduced intratumoral tumor-infiltrating lymphocyte (TIL) density and infiltration ratio, with relative TIL accumulation at the cancer periphery and within the stroma, consistent with an immune-excluded phenotype. Conclusions: Residual cancer–stroma topology quantified from standard H&E slides yields independent prognostic signals after NT in PDAC, provides a cellular immune correlate for spatial risk, and motivates prospective validation and spatially informed adjuvant strategies.