Training and validation of a robust PET radiomic-based index to predict distant-relapse-free-survival after radio-chemotherapy for locally advanced pancreatic cancer. (December 2020)

• Record Type: Journal Article
• Authors: Mori, Martina; Passoni, Paolo; Incerti, Elena; Bettinardi, Valentino; Broggi, Sara; Reni, Michele; Whybra, Phil; Spezi, Emiliano; Vanoli, Elena G.; Gianolli, Luigi; Picchio, Maria; Di Muzio, Nadia G.; Fiorino, Claudio
• Is Part Of: Radiotherapy and oncology. Volume 153(2020)
• Page Start: 258
• Page End: 264
• Publication Date: 2020-12
• Subjects: Pancreatic cancer -- Radiotherapy -- Induction chemotherapy -- Radiomic -- Predictive models -- Distant relapses; Oncology -- Periodicals; Radiotherapy -- Periodicals; Tumors -- Periodicals; Medical Oncology -- Periodicals; Neoplasms -- radiotherapy -- Periodicals; Radiotherapy -- Periodicals; Radiothérapie -- Périodiques; Cancérologie -- Périodiques; Tumeurs -- Périodiques; Electronic journals; 616.9940642
• DOI: 10.1016/j.radonc.2020.07.003
• Languages: English
• ISSNs: 0167-8140

Abstract

Highlights: This single-center study involved 176 pancreatic pts treated with radiochemotherapy. IBSI-consistent radiomic features (RF) of tumors were extracted by pre-RT PET images. RF were pre-selected based on robustness; their power in predicting DRFS was tested. A Cox-model trained on 116 pts including two RF well classified pts against DRFS. The model was validated on the other 60 pts; clinical variables did not impact. 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 RFs were extracted using IBSI (Image Biomarker Standardization Initiative) consistent software from pre-radiotherapy images of 176 LAPC patients treated with moderate hypo-fractionation (44.25 Gy, 2.95 Gy/fr). Tumors were segmented by applying a previously validated semi-automatic method. One-hundred-twenty-six RFs were excluded due to poor reproducibility and/or repeatability and/or inter-scanner variability. The original cohort was randomly split into a training ( n = 116) and a validation ( n = 60) group. Multi-variable Cox regression was applied to the training group, including only independent RFs 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 first order RFs: Center of Mass Shift (COMshift) and 10th Intensity percentile (P10 ) ( p = 0.0005, HR = 2.72, 95%CI = 1.54–4.80), showing worse outcomes for patients with lower COMshift and higher P10 . Once stratified by quartile values (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 the models' performance. Conclusions: A radiomic-based index including only two robust PET-RFs predicted DRFS of LAPC patients after radio-chemotherapy. The current results could find relevant applications in the treatment personalization of LAPC. A multi-institution independent validation has been planned.