Benchmarking Open-Source Pathology Foundation Models for Breast Cancer Biomarker Prediction from H&E Whole-Slide Images
Cancers · 01.08.2026 · 18 (15) · 2475
DOI: 10.3390/cancers18152475 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cancers, online erschienen am 01.08.2026. Verfasst von Samir Atiya und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, University of Chicago Medical Center, Chicago, IL 60637, USA. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Breast cancer biomarker detection through immunohistochemistry (IHC) is essential for treatment planning but faces challenges including turnaround time, variability, and laboratory resource constraints. Large open-source vision-language foundation models offer a potential avenue for inferring biomarker status directly from hematoxylin-and-eosin (H&E)-stained whole-slide images (WSIs).
Methods
We evaluated two open-source pathology foundation models—TITAN (Transformer-based Pathology Image and Text Alignment Network, approximately 48.5 M parameters) and CHIEF (Clinical Histopathology Imaging Evaluation Foundation Model, approximately 1.2 M parameters)—for predicting estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status from H&E-stained breast cancer WSIs. WSI data were obtained from The Cancer Genome Atlas Breast Invasive Carcinoma collection (TCGA-BRCA) via the NCI Imaging Data Commons, with biomarker labels from the NCI Genomic Data Commons. In total, 937 cases (995 WSIs; 78.3% ER-positive) were evaluated for ER, 934 cases (992 WSIs; 68.4% PR-positive) for PR, and 646 cases (691 WSIs; 21.1% HER2-positive) for HER2. All evaluation was performed under a strict patient-level 50/25/25 split with 10 independent random partitions; metrics are reported as the mean across partitions with percentile-based 95% confidence intervals. Performance was assessed using area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), sensitivity, specificity, and positive predictive value (PPV).
Results
TITAN and CHIEF achieved comparable performance for ER (TITAN AUROC: 0.885 [95% CI: 0.848, 0.921], AUPRC: 0.954 [0.940, 0.964]; CHIEF AUROC: 0.877 [0.831, 0.914], AUPRC: 0.955 [0.938, 0.969]) and PR (TITAN AUROC: 0.799, AUPRC: 0.868; CHIEF AUROC: 0.791, AUPRC: 0.864). At the default 0.5 operating point, ER PPV was 0.90 and PR PPV was 0.79–0.81. For HER2, both models achieved AUROC values of 0.71–0.74 and AUPRC values of 0.41–0.45—well above the prevalence-based random baseline (approximately 0.211)—but default-threshold sensitivity was very low (approximately 0.07–0.08), reflecting class imbalance and the use of an uncalibrated default threshold rather than a categorical absence of morphologic signal.
Conclusions
Under retrospective evaluation, both models demonstrate strong discriminative performance for ER and moderate performance for PR; HER2 prediction at the default operating point is limited and motivates threshold-calibration and multimodal extensions before any clinical use. AUPRC summarizes precision−recall behavior across thresholds and is distinct from threshold-specific precision (PPV); the two should be reported together for clinical-utility assessment in pathology AI. The findings are hypothesis-generating and motivate prospective external validation across independent institutional cohorts before any clinical deployment is considered.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Pathology, University of Chicago Medical Center, Chicago, IL 60637, USA.
- Biological Science Division, University of Chicago, Chicago, IL 60637, USA.
- Trillium Health Partners, Mississauga, ON L5B 1B8, Canada.
- Data Science Institute, University of Chicago, Chicago, IL 60615, USA.
- Department of Pathology, Ohio State University, Colombus, OH 43210, USA.
- Department of Pathology, University of Nebraska Medical Center, Omaha, NE 68106, USA.
ORCID-Profile: Yifei Zhou, Ankush Patel, Junhan Zhao
Zitieren
APA
Atiya, S., Liang, J., Ofori-Atta, K., Peng, M., Wang, H., Zhou, Y., Patel, A., Edgertion, M., Zhao, J., & Pamuksuz, U. (2026). Benchmarking Open-Source Pathology Foundation Models for Breast Cancer Biomarker Prediction from H&E Whole-Slide Images. Cancers, 18(15), 2475. https://doi.org/10.3390/cancers18152475
Vancouver
Atiya S, Liang J, Ofori-Atta K, Peng M, Wang H, Zhou Y, et al. Benchmarking Open-Source Pathology Foundation Models for Breast Cancer Biomarker Prediction from H&E Whole-Slide Images. Cancers. 2026;18(15):2475. doi:10.3390/cancers18152475
BibTeX
@article{Atiya2026,
author = {Atiya, Samir and Liang, Jiayou and Ofori-Atta, Kwaku and Peng, Michelle and Wang, Huili and Zhou, Yifei and Patel, Ankush and Edgertion, Mary and Zhao, Junhan and Pamuksuz, Utku},
title = {Benchmarking Open-Source Pathology Foundation Models for Breast Cancer Biomarker Prediction from H&E Whole-Slide Images},
journal = {Cancers},
year = {2026},
volume = {18},
number = {15},
pages = {2475},
doi = {10.3390/cancers18152475}
}
EUVIMED