Endometrial cancer prognosis is crucial for correct diagnosis and customized treatment (EC).
Researchers employed radiogenomics to integrate preoperative magnetic resonance imaging (MRI, n = 487 patients) with histologic-, transcriptomic-, and molecular biomarkers (n = 550 patients) in a study of 866 EC patients, with the objective of detecting aggressive tumor features. Whole-volume tumor radiomic profiling of manually segmented tumors (n = 138 patients) revealed clusters indicating patients with high-risk histological characteristics and poor survival. The same radiometric prognostic groups were reproduced by a fully automated machine learning (ML)-based tumor segmentation algorithm (n = 336 patients).
An 11-gene high-risk signature was established from these radiomic risk-groups, and its predictive effect was replicated in orthologous validation cohorts (n = 554 patients) and associated with The Cancer Genome Atlas (TCGA) molecular class with poor survival (copy-number-high/p53-altered). The researchers concluded that MRI-based integrated radiogenomics profiling gives refined tumor characterization, which may assist in prognosis and guide future EC treatment methods.