A preoperative CT radiomics model to predict disease-free survival in patients with pancreatic neuroendocrine tumors.

Abstract

Imaging has demonstrated capabilities in the diagnosis of pancreatic neuroendocrine tumors (pNETs) but its utility for prognostic prediction has not been elucidated yet. 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 overall survival (OS) in patients with pNET. Radiomics features of preoperative CT data obtained from patients with surgically resected pNET 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 tumor Ki67 rate (≤2 or >2). Selected features were used to build a radiomics index ranging from 0 to 1. A receiving operator curve was built to select optimal cut-off value of radiomics index to predict patient RFS and OS. RFS and OS were assessed using Kaplan-Meier analysis. Thirty-seven patients (median age, 61 years; 20 men) with 37 pNETs (Grade1, 21/37 [56%]; Grade 2, 11/37 [29%]; Grade 3, 4/37 [10%]) 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 = 0.013). No associations were found between radiomics index and OS (P = 0.86). The proposed radiomics index allows identifying patients with shorter RFS after pNET surgery. This result, however, requires prospective validation but may improve patient' care by intensifying imaging follow-up for those identified at high risk of recurrence.