The study aimed to investigate the potential of tumor-stroma ratio (TSR) on digitalized whole-mount histopathology to predict prognosis in patients with pancreatic ductal adenocarcinoma (PDAC). The effectiveness were evaluated through internal validation. Data were retrospectively collected from consecutive patients who underwent primary pancreatic resection from December 2016 to August 2017 (developing cohort) and from September 2017 to April 2018 (validation cohort). Digitalized whole-mount slide images were used to evaluate TSR by both pathologists and a computerized model based on Conditional Generative Adversarial Model (cGAN), respectively. TSR>1 and ≤ 1 denoted low and high stromal component. Logistic regression analysis revealed intratumoral necrosis and R1 independently associated with low stromal component in the developing cohort. Cox regression analysis revealed tumor-node-metastasis (TNM) stage [II vs. I: hazard ratio (HR), 2.584; 95% CI, 1.386-4.819; P = 0.003; III vs. I: HR, 4.384; 95% CI, 2.285-8.411; P < 0.001], stromal component (low vs. high: HR, 1.876; 95% CI, 1.227-2.870; P = 0.004), tumor grade (G3 vs. G1/2: HR, 2.124; 95% CI, 1.419-3.179; P < 0.001), and perineural invasion (with vs. without: HR, 2.147; 95% CI, 1.187-3.883; P = 0.011) were independent prognostic factors in the developing cohort. Stromal component categories could classify patients into subgroups within TNM stages I, II, and III based on over survival. All results were validated in the validation cohort. The weighted kappa value for categorical assessments between pathologists' evaluation and computer-aided evaluation was 0.804 (95% CI, 0.573-0.951). TSR represents a simple and reliable metric for combining the prognostic value of TNM stage in patients with PDAC.
Keywords: pancreatic ductal adenocarcinoma; patient stratification; prognosis; tumor–stroma ratio; whole-mount histological slides.
Copyright © 2020 Li, Wang, Jiang, Li, Shi, Gao, Ni, Zhang, Guo, Xu and Jin.