Risk Stratification and Overall Survival Prediction in Advanced Gastric Cancer Patients Based on Whole-Volume MRI Radiomics.

Abstract

The prognosis of advanced gastric cancer (AGC) patients has attracted much attention, but there is a lack of evaluation method. MRI-based radiomics has the potential to evaluate AGC patients' prognosis. To identify and validate the risk stratification and overall survival (OS) in AGC patients using MRI-based radiomics. Retrospective. A total of 233 patients (168 males, 63.6 ± 11.1 years; 65 females, 59.7 ± 11.8 years) confirmed AGC were collected. The data were randomly divided into a training (164) and validation set (69). A 3.0 T, axial T2-weighted, diffusion-weighted imaging, and contrast-enhanced T1-weighted (CE-T1WI). Radiologist 1 segmented 233 patients and radiologist 2 segmented randomly 50 patients on CE-T1WI. The risk score (RS) was summed by each sample based on the radiomics features and correlation coefficients. Patients were followed up for 7-67months (median 41; 138 dead and 95 alive). The intraclass correlation coefficient (ICC) and Kappa value were calculated. Differences in survival analysis were assessed by Kaplan-Meier curves and log-rank test. Cox-regression analysis was performed to identify the radiomics features and clinical indicators associated with OS. The calibration curves were built to assess the model. A two-tailed P value < 0.05 was considered statistically significant. Integrated with age, lymphovascular invasion (LVI) and RS, a survival combined model was built. The area under the curve (AUC) for predicting 3-year and 5-year OS was 0.765 and 0.788 in the training set, 0.757 and 0.729 in the validation set. There was no significant difference between the radiomics model and survival combined model for 3-year (0.690 vs. 0.757, P=0.425) and 5-year OS (0.687 vs. 729, P=0.412) in the validation set. The calibration curves showed a high degree of fit for the survival combined model. This study established a survival combined model that might help AGC patients in future clinical decision-making. 33 TECHNICAL EFFICACY: Stage 5.