AI-assisted histomorphological stratification of endometrial cancer: real-world validation of foundation models for molecular subtyping
Open Access
- 6 June 2026
- journal article
- research article
- Published by Springer Nature in npj Precision Oncology
- Vol. 10 (1) , 205
Abstract
Endometrial cancer (EC) is classified into four molecular subtypes with distinct prognosis and treatment implications. Despite this well-established molecular classification, morpho-molecular correlations remain understudied. Artificial intelligence (AI) enables biomarker prediction from H&E-stained whole-slide images (WSIs). However, real-world validation for EC molecular subtyping is lacking. In this study, we evaluated image-based molecular subtyping in a real-world cohort derived from routine diagnostic cases with heterogeneous image quality. We benchmarked the feature extraction with the CTransPath and UNI foundation models, demonstrating robust results across different scanner hardware and quantified performance variation by additional stain normalization. UNI-based features achieved a mean AUROC of 0.646 for POLE mut ( n = 16), 0.700 for MMRd_MSI ( n = 79), 0.684 for NSMP ( n = 176), and 0.844 for p53abn ( n = 18) on external real-world data. We provided human interpretations of subtype-specific morphological features. Our findings may thus lay the foundations of a more reliable framework for personalized treatment stratification based on morphologically informed molecular subtyping.Keywords
Funding Information
- Deutsche Krebshilfe (No: 70116663)
- Interdisciplinary Center for Clinical Research (IZKF) at the University Hospital of the University of Erlangen-Nuremberg (Junior Project J101)
- Young Scientist Fellowship by the Bavarian Center for Cancer Research
This publication has 59 references indexed in Scilit:
- Built to Last? Reproducibility and Reusability of Deep Learning Algorithms in Computational PathologyLaboratory Investigation, 2023
- Transformer-based biomarker prediction from colorectal cancer histology: A large-scale multicentric studyCancer Cell, 2023
- Transformer-based unsupervised contrastive learning for histopathological image classificationMedical Image Analysis, 2022
- Deep learning for diagnosis and survival prediction in soft tissue sarcomaAnnals of Oncology, 2021
- Clinical features of ProMisE groups identify different phenotypes of patients with endometrial cancerArchives of Gynecology and Obstetrics, 2021
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationInternational Journal of Computer Vision, 2019
- Evaluation of endometrial carcinoma prognostic immunohistochemistry markers in the context of molecular classificationThe Journal of Pathology: Clinical Research, 2017
- Confirmation of ProMisE: A simple, genomics‐based clinical classifier for endometrial cancerCancer, 2017
- Association of Polymerase e–Mutated and Microsatellite-Instable Endometrial Cancers With Neoantigen Load, Number of Tumor-Infiltrating Lymphocytes, and Expression of PD-1 and PD-L1JAMA Oncology, 2015
- Two pathogenetic types of endometrial carcinomaGynecologic Oncology, 1983