Related Experiment Video
Updated: Aug 17, 2026

Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers
Published on: December 5, 2017
Real-World Benchmarking and Validation of Foundation Model Transformers for Endometrial Cancer Subtyping from
Vincent M Wagner1, Casey M Cosgrove2, Stephanie J Chen3
1University of Iowa, Department of Obstetrics and Gynecology, Division of Gynecologic Oncology, Iowa City, IA.
Purpose:
To evaluate whether open-source histopathology foundation model pipelines, paired with attention-based multiple instance learning (MIL), can accurately classify molecular subtypes of endometrial cancer (EC) from whole-slide images (WSIs) and maintain performance in a real-world, independent cohort.
Methods:
We assembled a public discovery cohort of 815 patients (1,195 WSIs) from The Cancer Genome Atlas and Clinical Proteomic Tumor Analysis Consortium, and an independent external cohort of 720 patients (1,357 WSIs) with molecular subtyping determined by mismatch repair immunohistochemistry plus TP53 and POLE sequencing. Four ImageNet-pretrained convolutional neural networks (CNNs) and six open-source foundation encoders using two MIL aggregation strategies (TransMIL and CLAM) were benchmarked within the STAMP pipeline. Models were trained with five-fold cross-validation and evaluated on an independent cohort. Macro-area under the receiver operating characteristic curve (AUC) was the primary outcome.
Results:
In cross-validation, foundation models outperformed CNNs (macro-AUC 0.799-0.860 vs 0.715-0.829). The best configuration (Virchow2 with CLAM) achieved macro-AUC 0.860 (95%CI, 0.839-0.880), macro-F1 score 0.607, and balanced accuracy 0.647. External validation showed substantial degradation for CNNs, while foundation models retained higher discrimination (macro-AUC 0.667-0.780). UNI2 with CLAM had the highest external macro-AUC (0.780), and Virchow2 with CLAM had the best balanced accuracy (0.525). Subtype-level AUCs for UNI2 with CLAM were highest for p53abn (0.851).
Conclusions:
Open-source foundation model pipelines with attention-based MIL can deliver accurate and generalizable molecular subtyping of EC directly from WSIs. These models outperform CNNs in real-world validation, supporting their potential as scalable, cost-effective tools to guide precision oncology and triage confirmatory molecular testing.
More Related Videos
Related Concept Videos
Mouse Models of Cancer Study
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
Mouse Models of Cancer Study
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...

