Prediction of tumour grade and survival outcome using pre-treatment PET- and MRI-derived imaging features in patients with resectable pancreatic ductal adenocarcinoma

Objectives To perform a correlation analysis between histopathology and imaging in patients with previously untreated pancreatic ductal adenocarcinoma (PDAC) and to determine the prognostic values of clinical, histological, and imaging parameters regarding overall survival (OS), disease-specific survival (DSS), and progression-free survival (PFS). Methods This single-centre study prospectively included 61 patients (32 males; median age, 68.0 years [IQR, 63.0-75.0 years]) with histologically confirmed PDAC and following surgical resection who preoperatively underwent(18)F-FDG PET/CT and DW-MRI. On whole lesions, we measured, using a 42% SUV(max)threshold volume of interest (VOI), the following quantitative parameters: mean and maximum standardised uptake values (SUV(mean)and SUVmax), total lesion glycolysis (TLG), metabolic tumour volume (MTV), mean and minimum apparent diffusion coefficient (ADC(mean)and ADC(min)), diffusion total volume (DTV), and MTV/ADC(min)ratio. Spearman's correlation analysis was performed to assess relationships between these markers and histopathological findings from surgical specimens (stage; grade; resection quality; and vascular, perineural, and lymphatic invasion). Kaplan-Meier and Cox hazard ratio methods were used to evaluate the impacts of imaging parameters on OS (n = 41), DSS (n = 36), and PFS (n = 41). Results Inverse correlations between ADC(min)and SUVmax(rho = - 0.34;p = 0.0071), and between SUV(mean)and ADC(mean)(rho = - 0.29;p = 0.026) were identified. ADC(min)was inversely correlated with tumour grade (rho = - 0.40;p = 0.0015). MTV was an independent predictive factor for OS and DSS, while DTV was an independent predictive factor for PFS. Conclusion In previously untreated PDAC, ADC and SUV values are correlated. Combining PET-MRI metrics may help predict PDAC grade and patients' survival.