Predicting the progression-free survival of gastrointestinal stromal tumors after imatinib therapy through multi-sequence magnetic resonance imaging

Purpose Identify radiomics features associated with progression-free survival (PFS) and develop a predictive model for accurate PFS prediction in liver metastatic gastrointestinal stromal tumor patients (GIST). Methods This multi-center retrospective study involved a comprehensive review of clinical and imaging data pertaining to 211 patients with gastrointestinal stromal tumors (GIST) from Center A and B. A total of 147 patients with hepatic metastatic GIST were included, with 102 cases as the training set and 45 cases as the external validation set. Radiomics features were extracted from non-enhanced MR images, specifically T2WI, DWI, and ADC, and relevant features were selected through LASSO-Cox regression. A radiomics nomogram model was then constructed using multivariable Cox regression analysis to effectively predict PFS. The models performance were evaluated with the concordance index (C-index). Results The median age of the patients was 53 years, with 82 males and 65 females. A total of 21 radiomics features were selected to generate the radiomics signature. Radiomics signature slightly outperformed the clinical model but without significant difference ( P > 0.05). Integrated radiomics signature with clinical features to build a nomogram, which exhibited high predictive performance in both training (C-index 0.757, 95% CI 0.692–0.822) and validation cohorts (C-index 0.718, 95% CI 0.618–0.818). Nomogram significantly outperformed the clinical model ( P = 0.002 for training cohort, P