Survival prediction using CT-based radiomic features in patients of pancreatic cancer treated with chemotherapy followed by SBRT.

Purpose: Owing to the heterogeneous nature of pancreatic cancer, clinical prediction models are not sufficient for prognostication. Radiomics is quantitative noninvasive assessment performed from imaging which by means of mathematical models can decode tumor phenotype and further predict disease and treatment outcomes. This pilot study aims to investigate the association of CT-based radiomic features with overall survival (OS) in pancreatic cancer patients treated with stereotactic body radiation therapy (SBRT).

Materials and methods: This study was conducted in patients of borderline resectable and locally advanced pancreatic cancer at our institute from January 2021 to December 2022. Ten patients underwent neoadjuvant chemotherapy, followed by SBRT with doses ranging from 33 Gy to 42 Gy administered in 5-6 fractions. Subsequent treatment included additional chemotherapy and evaluation for potential surgery. Radiomic features were extracted from planning CT images, and statistical analysis was performed using R software.

Results: Out of 10 patients receiving neoadjuvant chemotherapy followed by SBRT, three underwent surgery. The duration of median follow-up was 15 months, and the median OS was 25 months. A total of 851 radiomic features including 107 original images features and 93 × 8 wavelet-based features were extracted. Using Lasso Cox regression, four wavelet-based features were found to influence the overall survival.

Conclusions: The present study demonstrates that CT-based radiomic features can be a promising tool in predicting survival and in addition to clinical parameters can provide detailed prognostic information that can facilitate personalized patient care. However, clinical implications of this radiomic analysis need a larger number of patients to validate the results.