Endometrial cancer risk stratification using MRI radiomics: corroborating with choline metabolism

Abstract Background and purpose Radiomics offers little explainability. This study aims to develop a radiomics model (Rad-Score) using diffusion-weighted imaging (DWI) to predict high-risk patients for nodal metastasis or recurrence in endometrial cancer (EC) and corroborate with choline metabolism. Materials and methods From August 2015 to July 2018, 356 EC patients were enrolled. Rad-Score was developed using LASSO regression in a training cohort ( n = 287) and validated in an independent test cohort ( n = 69). MR spectroscopy (MRS) was also used in 230 patients. Nuclear MRS measured choline metabolites in 70 tissue samples. The performance was compared against European Society for Medical Oncology (ESMO) risk groups. A P < .05 denoted statistical significance. Results Rad-Score achieved 71.1% accuracy in the training and 71.0% in the testing cohorts. Incorporating clinical parameters of age, tumor type, size, and grade, Rad-Signature reached accuracies of 73.2% in training and 75.4% in testing cohorts, closely matching the performance to the post-operatively based ESMO's 70.7% and 78.3%. Rad-Score was significantly associated with increased total choline levels on MRS ( P = .034) and tissue levels ( P = .019). Conclusions Development of a preoperative radiomics risk score, comparable to ESMO clinical standard and associated with altered choline metabolism, shows translational relevance for radiomics in high-risk EC patients. Trial registration This study was registered in ClinicalTrials.gov on 2015–08-01 with Identifier NCT02528864.