Radiomics-Based Prognostic Model for Progesterone Resistance in Endometrial Cancer

Current study results on personalized medicine in the treatment of endometrial cancer have been published, providing a promising tool for predicting progesterone resistance in fertility-preserving patients. Researchers at Peking University People's Hospital constructed a radiomics model to predict progesterone-resistant subgroups, achieving high predictive accuracy with an area under the ROC curve (AUC) of 0.841. The model identified key biological pathways and cellular structures, offering insights into extracellular matrix remodeling and collagen type III content.

Key Takeaways:

• Researchers developed a radiomics model to predict progesterone resistance in endometrial cancer patients undergoing fertility preservation.
• The model achieved high predictive accuracy with an AUC of 0.841 in the training cohort and 0.873 and 0.852 in the validation and whole cohorts, respectively.
• Key biological pathways identified include cellular response to external stimulus, collagen metabolic processes, and extracellular matrix (ECM) remodeling.
• The model highlights the influence of ECM remodeling on treatment outcomes and provides a promising non-invasive tool for predicting progesterone resistance.
• Progestin-resistant subgroups were characterized by higher collagen type III content and alterations in ECM stiffness, reflected in altered tumor microenvironment dynamics.
• Fibroblast-epithelial interactions, cytoskeletal organization, and collagen binding were validated by atomic force microscope (AFM) and microfluid equipment.
• The research provides insights into personalized therapeutic strategies for fertility-preserving patients.

Statistics:

• The radiomics model achieved an AUC of 0.841 in the training cohort.
• The model's predictive accuracy was validated in the validation cohort (AUC = 0.873) and the whole cohort (AUC = 0.852).
• Collagen type III content was significantly higher in progestin-resistant subgroup (PS).
• Altered tumor microenvironment dynamics were reflected in EC stiffness and ECM remodeling.

Sources:

• Radiomics-based prognostic model for progesterone resistance in endometrial cancer: insights into extracellular matrix and collagen type III. International Journal of Surgery, 2025.
• Jingyuan Wang, et al. Investigators at Peking University People's Hospital Release New Data on Personalized Medicine (Radiomics-based prognostic model for progesterone resistance in endometrial cancer: insights into extracellular matrix and collagen type III). OBGYN & Reproduction Week. October 27, 2025; p 337.