Validation of an Artificial Intelligence Model for Breast Cancer Molecular Subtyping Using Hematoxylin and Eosin-Stained Whole-Slide Images in a Population-Based Cohort
Cancers · 05.10.2025 · 17 (19) · 3234
DOI: 10.3390/cancers17193234 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cancers, online erschienen am 05.10.2025. Verfasst von Umay Kiraz und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, Stavanger University Hospital, 4011 Stavanger, Norway. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Horizon 2020 European Union research and innovation program under the Marie Sklodowska Curie (CLARIFY Project), Ayuda a Primeros Proyectos de Investigación (PAID-06-23), Vicerrectorado de Investigación of the Universitat Politècnica de València, Ayuda a Primeros Proyectos de Investigación.
Abstract (Originalsprache)
Background/Objectives: Breast cancer (BC) is the most commonly diagnosed cancer in women and the leading cause of cancer-related deaths globally. Molecular subtyping is crucial for prognosis and treatment planning, with immunohistochemistry (IHC) being the most commonly used method. However, IHC has limitations, including observer variability, a lack of standardization, and a lack of reproducibility. Gene expression profiling is considered the ground truth for molecular subtyping; unfortunately, this is expensive and inaccessible to many institutions. This study investigates the potential of an artificial intelligence (AI) model to predict BC molecular subtypes directly from hematoxylin and eosin (H&E)-stained whole-slide images (WSIs).
Methods
A pretrained deep learning framework based on multiple-instance learning (MIL) was validated on the Stavanger Breast Cancer (SBC) dataset, consisting of 538 BC cases. Three classification tasks were assessed, including two-class [triple negative BC (TNBC) vs. non-TNBC], three-class (luminal vs. HER2-positive vs. TNBC), and four-class (luminal A vs. luminal B vs. HER2-positive vs. TNBC) groups. Performance metrics were used for the evaluation of the AI model.
Results
The AI model demonstrated strong performance in distinguishing TNBC from non-TNBC (AUC = 0.823, accuracy = 0.833, F1-score = 0.824). However, performance declined with an increasing number of classes.
Conclusions
The study highlights the potential of AI in BC molecular subtyping from H&E WSIs, offering an easily applicable and standardized method to IHC. Future improvements should focus on optimizing multi-class classification and validating AI-based methods against gene expression analyses for enhanced clinical applicability.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Pathology, Stavanger University Hospital, 4011 Stavanger, Norway.
- Department of Chemistry, Bioscience and Environmental Engineering, University of Stavanger, 4021 Stavanger, Norway.
- Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano, HUMAN-Tech, Universitat Politècnica de València, 46022 Valencia, Spain.
- Institute for Biomedicine and Glycomics, Griffith University, Southport, QLD 4215, Australia.
ORCID-Profile: Umay Kiraz, Claudio Fernandez-Martin, Sandra Morales-Martinez, Emiel A M Janssen
Förderung
- Horizon 2020 European Union research and innovation program under the Marie Sklodowska Curie (CLARIFY Project)
- Ayuda a Primeros Proyectos de Investigación (PAID-06-23), Vicerrectorado de Investigación of the Universitat Politècnica de València
- Ayuda a Primeros Proyectos de Investigación
- Vicerrectorado de Investigación of the Universitat Politècnica de València
Zitieren
APA
Kiraz, U., Fernandez-Martin, C., Rewcastle, E., Gudlaugsson, E. G., Skaland, I., Naranjo, V., Morales-Martinez, S., & Janssen, E. A. M. (2025). Validation of an Artificial Intelligence Model for Breast Cancer Molecular Subtyping Using Hematoxylin and Eosin-Stained Whole-Slide Images in a Population-Based Cohort. Cancers, 17(19), 3234. https://doi.org/10.3390/cancers17193234
Vancouver
Kiraz U, Fernandez-Martin C, Rewcastle E, Gudlaugsson EG, Skaland I, Naranjo V, et al. Validation of an Artificial Intelligence Model for Breast Cancer Molecular Subtyping Using Hematoxylin and Eosin-Stained Whole-Slide Images in a Population-Based Cohort. Cancers. 2025;17(19):3234. doi:10.3390/cancers17193234
BibTeX
@article{Kiraz2025,
author = {Kiraz, Umay and Fernandez-Martin, Claudio and Rewcastle, Emma and Gudlaugsson, Einar G and Skaland, Ivar and Naranjo, Valery and Morales-Martinez, Sandra and Janssen, Emiel A M},
title = {Validation of an Artificial Intelligence Model for Breast Cancer Molecular Subtyping Using Hematoxylin and Eosin-Stained Whole-Slide Images in a Population-Based Cohort},
journal = {Cancers},
year = {2025},
volume = {17},
number = {19},
pages = {3234},
doi = {10.3390/cancers17193234}
}
EUVIMED