AI and Cancer Research ── Endometrial ── 2026-11-13
Endometrial cancer: treatment, trials and AI
- Abstract
Preoperative identification of p53-abnormal (p53abn) endometrial cancer is important for molecular risk stratification, yet biopsy-based testing and p53 immunohistochemistry may be limited by sampling and interpretive variability. This study aimed to develop and externally validate a dynamic contrast-enhanced MRI (DCE-MRI) Fusion model integrating peritumoral radiomics, intratumoral habitat features, and clinical predictors for noninvasive prediction of p53abn endometrial cancer. This retrospective dual-center study included 498 patients with surgically confirmed endometrial cancer and sequencing-based molecular classification. Patients from Institution 1 were assigned to a training cohort ( n = 351) and an internal validation cohort ( n = 86), and patients from Institution 2 formed an external test cohort ( n = 61). Radiomic features were extracted from the whole tumor, 3-mm and 5-mm peritumoral regions, and three unsupervised intratumoral habitat subregions. After reproducibility assessment, statistical filtering, correlation analysis, and least absolute shrinkage and selection operator selection, single-domain models were developed. A Fusion model combined clinical predictors with the 5-mm peritumoral and habitat radiomics scores. Performance was assessed using discrimination, calibration, decision curve analysis, reclassification metrics, and Shapley additive explanations (SHAP) interpretation. The Habitat model showed the most stable single-domain performance, with AUCs of 0.831, 0.813, and 0.788 in the training, internal validation, and external test cohorts, respectively. The Fusion model achieved AUCs of 0.891, 0.885, and 0.863, with sensitivities of 0.882, 0.765, and 0.889 and negative predictive values of 0.974, 0.925, and 0.968, respectively. Brier scores were 0.078, 0.095, and 0.110. SHAP analysis identified the Habitat and 5-mm peritumoral radiomics scores as the dominant contributors to prediction. A DCE-MRI Fusion model integrating clinical, peritumoral, and habitat radiomics demonstrated good discrimination for preoperative p53abn prediction. The model may serve as a noninvasive adjunct to molecular testing for preoperative risk stratification.
Journal IF-equivalent: 3.8 (OpenAlex 2-year mean citedness, value as of 2026-11-03, retrieved 2026-11-05; not the official Clarivate IF)Reference: Dai H, Guo W, Liu Y, Yan B, Lyu B, Wang F, et al. DCE-MRI-derived peritumoral and habitat radiomics for preoperative prediction of p53-abnormal endometrial cancer: a dual-center retrospective study with external test. BMC Med Imaging. 2026 Nov 10 [Epub ahead of print]. doi:10.1186/s12880-026-03045-0.Checked: Abstract only