TU‐CD‐BRB‐10: 18F‐FDG PET Image‐Derived Tumor Features Highlight Altered Pathways Identified by Trancriptomic Analysis in Head and Neck Cancer

Purpose: Several quantitative features can be extracted from 18F‐FDG PET images, such as standardized uptake values (SUVs), metabolic tumor volume (MTV), shape characterization (SC) or intra‐tumor radiotracer heterogeneity quantification (HQ). Some of these features calculated from baseline 18F‐FDG PET images have shown a prognostic and predictive clinical value. It has been hypothesized that these features highlight underlying tumor patho‐physiological processes at smaller scales. The objective of this study was to investigate the ability of recovering alterations of signaling pathways from FDG PET image‐derived features. Methods: 52 patients were prospectively recruited from two medical centers (Brest and Poitiers). All patients underwent an FDG PET scan for staging and biopsies of both healthy and primary tumor tissues. Biopsies went through a transcriptomic analysis performed in four spates on 4×44k chips (Agilent™). Primary tumors were delineated in the PET images using the Fuzzy Locally Adaptive Bayesian algorithm and characterized using 10 features including SUVs, SC and HQ. A module network algorithm followed by functional annotation was exploited in order to link PET features with signaling pathways alterations. Results: Several PET‐derived features were found to discriminate differentially expressed genes between tumor and healthy tissue (fold‐change >2, p