An interpretable multimodal morphomolecular model refines progression-risk stratification in early-stage endometrioid endometrial carcinoma
7 affiliations
- 1Ningbo Institute of Innovation for Combined Medicine and Engineering, The Affiliated Lihuili Hospital of Ningbo University , ,
- 2Section of Quality Management, Science and Education, Jiaocheng District Center for Disease Control and Prevention , ,
- 3School of Electronic Science and Technology, Xiamen University , , ,
- 4Department of Obstetrics and Gynecology, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University , ,
- 5College of Life Sciences, Heilongjiang University , , ,
- 6West China Second University Hospital, Sichuan University , ,
- 7School of Laboratory Medicine and Life Sciences, Wenzhou Medical University , ,
Abstract
Background: Risk stratification remains incomplete for patients with FIGO stage I–II endometrioid endometrial carcinoma (EEC) despite clinicopathological assessment and molecular subtyping. Interpretable integration of diagnostic tissue morphology with molecular programmes may provide complementary information for progression-risk assessment.
Methods: We developed a prototype-resolved interpretable survival model (PRISM), a multimodal framework integrating haematoxylin and eosin-stained whole-slide images with RNA-seq-derived pathway programmes for progression-free survival risk assessment. PRISM was developed in 287 eligible TCGA-UCEC patients with EEC, comprising a training cohort (n = 229) and a held-out internal validation cohort (n = 58). After model specification was fixed, PRISM was retrained on all 287 cases and evaluated without further tuning in an independent CPTAC-UCEC cohort of 63 patients with EEC. Prototype–pathway alignment provided tissue- and pathway-level interpretation of model predictions.
Results: Among 350 patients with EEC and matched multimodal data, PRISM achieved C-indices of 0.770, 0.751 and 0.745 in the TCGA training, internal validation and CPTAC external validation cohorts, respectively. In CPTAC-UCEC, the 36-month time-dependent AUC was 0.727, compared with 0.685 for the clinicopathological and molecular subtype baseline model. In a complementary fixed-horizon analysis, adding PRISM to the clinicopathological model increased the 36-month AUC in CPTAC-UCEC from 0.609 to 0.719. The PRISM risk score remained associated with progression-free survival after multivariable adjustment. Prototype-resolved analyses linked higher-risk predictions to localised histomorphological patterns and pathway programmes related to proliferation, cell-cycle activity, glycolysis, hypoxia, focal adhesion and epithelial–mesenchymal transition.
Conclusion: PRISM showed prognostic discrimination in an exploratory independent external evaluation and provided a biologically interpretable framework for integrating histopathology and transcriptomics to refine progression-risk assessment in early-stage EEC. Further validation in larger, prospective, multi-institutional cohorts is warranted to establish its generalisability and clinical utility.
Related
- Association of VCP/p97 Expression with Clinicopathological Features and Overall Survival in Endometrioid Endometrial Carcinoma
- Case Report: Primary endometrioid adenocarcinoma of the cervix and secondary cervical involvement by endometrial carcinoma: diagnostic pitfalls and an integrated approach based on two cases
- Recurrence patterns and adjuvant therapy in endometrioid early-stage endometrial cancer with a p53-abnormal pattern
- Metformin as an Adjunct to Fertility-Sparing Treatment in Atypical Endometrial Hyperplasia and Early-Stage Endometrioid Endometrial Cancer: Narrative Review.
- Advanced Age and Low Parity as Predictors of Non-Endometrioid Histopathological Subtypes in Endometrial Carcinoma: A Cross-Sectional Study in Indonesia.
BibTeX
@article{li2026interpretable,
title = {{An interpretable multimodal morphomolecular model refines progression-risk stratification in early-stage endometrioid endometrial carcinoma}},
author = {Jinxin Li and Qiong Tang and Jinyang Chen and Qiaoqiao Chen and Bochen Liu and Qingran Kong and Jingzhang Ji and Qi Zhao},
journal = {Frontiers in cell and developmental biology},
year = {2026},
month = oct,
doi = {10.3389/fcell.2026.1945984},
url = {https://europepmc.org/article/PMC/PMC13724606},
note = {CC BY},
}
RIS
TY - JOUR
TI - An interpretable multimodal morphomolecular model refines progression-risk stratification in early-stage endometrioid endometrial carcinoma
AU - Jinxin Li
AU - Qiong Tang
AU - Jinyang Chen
AU - Qiaoqiao Chen
AU - Bochen Liu
AU - Qingran Kong
AU - Jingzhang Ji
AU - Qi Zhao
PY - 2026
DA - 2026/10/19
JO - Frontiers in cell and developmental biology
DO - 10.3389/fcell.2026.1945984
UR - https://europepmc.org/article/PMC/PMC13724606
AB - Background: Risk stratification remains incomplete for patients with FIGO stage I–II endometrioid endometrial carcinoma (EEC) despite clinicopathological assessment and molecular subtyping. Interpretable integration of diagnostic tissue morphology with molecular programmes may provide complementary information for progression-risk assessment. Methods: We developed a prototype-resolved interpretable survival model (PRISM), a multimodal framework integrating haematoxylin and eosin-stained whole-slide images with RNA-seq-derived pathway programmes for progression-free survival risk assessment. PRISM was developed in 287 eligible TCGA-UCEC patients with EEC, comprising a training cohort (n = 229) and a held-out internal validation cohort (n = 58). After model specification was fixed, PRISM was retrained on all 287 cases and evaluated without further tuning in an independent CPTAC-UCEC cohort of 63 patients with EEC. Prototype–pathway alignment provided tissue- and pathway-level interpretation of model predictions. Results: Among 350 patients with EEC and matched multimodal data, PRISM achieved C-indices of 0.770, 0.751 and 0.745 in the TCGA training, internal validation and CPTAC external validation cohorts, respectively. In CPTAC-UCEC, the 36-month time-dependent AUC was 0.727, compared with 0.685 for the clinicopathological and molecular subtype baseline model. In a complementary fixed-horizon analysis, adding PRISM to the clinicopathological model increased the 36-month AUC in CPTAC-UCEC from 0.609 to 0.719. The PRISM risk score remained associated with progression-free survival after multivariable adjustment. Prototype-resolved analyses linked higher-risk predictions to localised histomorphological patterns and pathway programmes related to proliferation, cell-cycle activity, glycolysis, hypoxia, focal adhesion and epithelial–mesenchymal transition. Conclusion: PRISM showed prognostic discrimination in an exploratory independent external evaluation and provided a biologically interpretable framework for integrating histopathology and transcriptomics to refine progression-risk assessment in early-stage EEC. Further validation in larger, prospective, multi-institutional cohorts is warranted to establish its generalisability and clinical utility.
SN - 2296-634X
ER -