# Temporal Validation of an FDG-PET-Radiomic Model for Distant-Relapse-Free-Survival After Radio-Chemotherapy for Pancreatic Adenocarcinoma

## TL;DR

This study improves a model using PET imaging features to predict survival outcomes in pancreatic cancer patients after treatment.

## Contribution

The study temporally validates and refines a radiomic model for predicting distant relapse-free survival in pancreatic cancer patients.

## Key findings

- A radiomic model using FDG-PET features showed moderate accuracy in predicting patient outcomes.
- Simplifying the model improved performance slightly, while adding a complementary feature further enhanced accuracy.
- The model demonstrated potential for patient risk stratification despite moderate predictive accuracy.

## Abstract

Pancreatic cancer is a highly aggressive disease with a poor prognosis, even when detected in its early stages. This study temporally validated and improved a model using radiomic features derived from [18F]FDG-PET imaging to predict distant relapse-free survival in patients with locally advanced pancreatic cancer. Data from 215 patients treated with chemoradiotherapy were analyzed. The original model, which included two radiomic features and a cancer stage, showed moderate accuracy in predicting patient outcomes. Simplifying the model to a single radiomic feature improved performance slightly, while adding another complementary feature further enhanced accuracy. Although all versions of the model showed moderate ability to differentiate risk levels, these radiomic features demonstrate potential for patient stratification. Further validation is ongoing with independent cohorts from external centers, ensuring robustness beyond the analyzed patient group.

Background/Objectives: Pancreatic cancer is a very aggressive disease with a poor prognosis, even when diagnosed at an early stage. This study aimed to validate and refine a radiomic-based [18F]FDG-PET model to predict distant relapse-free survival (DRFS) in patients with unresectable locally advanced pancreatic cancer (LAPC). Methods: A Cox regression model incorporating two radiomic features (RFs) and cancer stage (III vs. IV) was temporally validated using a larger cohort (215 patients treated between 2005–2022). Patients received concurrent chemoradiotherapy with capecitabine and hypo-fractionated Intensity Modulated Radiotherapy (IMRT). Data were split into training (145 patients, 2005–2017) and validation (70 patients, 2017–2022) groups. Seventy-eight RFs were extracted, harmonized, and analyzed using machine learning to develop refined models. Results: The model incorporating Statistical-Percentile10, Morphological-ComShift, and stage demonstrated moderate predictive accuracy (training: C-index = 0.632; validation: C-index = 0.590). When simplified to include only Statistical-Percentile10, performance improved slightly in the validation group (C-index = 0.601). Adding GLSZM3D-grayLevelVariance to Statistical-Percentile10, while excluding Morphological-ComShift, further enhanced accuracy (training: C-index = 0.654; validation: C-index = 0.623). Despite these refinements, all versions showed similar moderate ability to stratify patients into risk classes. Conclusions: [18F]FDG-PET radiomic features are robust predictors of DRFS after chemoradiotherapy in LAPC. Despite moderate performance, these models hold promise for patient risk stratification. Further validation with external cohorts is ongoing.