A preoperative computed tomography radiomics model to predict disease-free survival in patients with pancreatic neuroendocrine tumors
Margaux Homps, Philippe Soyer, Romain Coriat, Solène Dermine, Anna Pellat, David Fuks, Ugo Marchèse, Benoît Terris, Lionel Groussin, Anthony Dohan, Maxime Barat
Abstract
IMPORTANCE: Imaging has demonstrated capabilities in the diagnosis of pancreatic neuroendocrine tumors (pNETs), but its utility for prognostic prediction has not been elucidated yet. OBJECTIVE: The aim of this study was to build a radiomics model using preoperative computed tomography (CT) data that may help predict recurrence-free survival (RFS) or OS in patients with pNET. DESIGN: We performed a retrospective observational study in a cohort of French patients with pNETs. PARTICIPANTS: Patients with surgically resected pNET and available CT examinations were included. INTERVENTIONS: Radiomics features of preoperative CT data were extracted using 3D-Slicer® software with manual segmentation. Discriminant features were selected with penalized regression using least absolute shrinkage and selection operator method with training on the tumor Ki67 rate (≤2 or >2). Selected features were used to build a radiomics index ranging from 0 to 1. OUTCOME AND MEASURE: A receiving operator curve was built to select an optimal cutoff value of the radiomics index to predict patient RFS and OS. Recurrence-free survival and OS were assessed using Kaplan-Meier analysis. RESULTS: Thirty-seven patients (median age, 61 years; 20 men) with 37 pNETs (grade 1, 21/37 [57%]; grade 2, 12/37 [32%]; grade 3, 4/37 [11%]) were included. Patients with a radiomics index >0.4 had a shorter median RFS (36 months; range: 1-133) than those with a radiomics index ≤0.4 (84 months; range: 9-148; P = .013). No associations were found between the radiomics index and OS (P = .86).