No abstract

No abstract

No abstract

No abstract

No abstract

No abstract

No abstract

Purpose: To assess the value of 18F-Fluorodeoxyglucose (18F-FDG) PET Radiomic Features (RF) in predicting Distant Relapse Free Survival (DRFS) in patients with Locally Advanced Pancreatic Cancer (LAPC) treated with radio-chemotherapy. Materials & Methods: One-hundred-ninety-eight RF were extracted using an IBSI (Image Biomarker Standardization Initiative) consistent software from pre-radiotherapy images of 176 LAPC patients, treated with moderate hypo-fractionation (44.25Gy, 2.95Gy/fr). Tumors were segmented by applying a previously validated semi-automatic method. One-hundred-twenty-six RF were excluded due to poor reproducibility and/or repeatability and/or inter-scanner variability. The original cohort was randomly split in a training (n=116) and a validation (n=60) group. Multi-variable Cox regression was applied on the training group, including only independent RF in the model. The resulting radiomic index was tested in the validation cohort. The impact of selected clinical variables was also investigated. Results: The resulting Cox model included two RF of first order: Center of Mass Shift (COMshift) and 10 th Intensity percentile (P10) (p=0.0005, HR=2.72, 95%CI=1.54-4.80), showing worse outcome for patients with lower COMshift and higher P10. Once stratified by quartile values (< lowest quartile vs > highest quartile vs the remaining), the index properly stratified patients according to their DRFS (p=0.0024, log-rank test). Performances were confirmed in the validation cohort (p=0.03, HR=2.53, 95%CI=0.96-6.65). The addition of clinical factors did not significantly improve models' performances. Conclusions: A radiomic-based index including only two robust PET-RF predicted DRFS of LAPC patients after radio-chemotherapy. Current results could find relevant applications in treatment personalization of LAPC. A multi-institution independent validation has currently been planned.