EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Agreement Across 10 Artificial Intelligence Models in Assessing Human Epidermal Growth Factor Receptor 2 (HER2) Expression in Breast Cancer Whole-Slide Images

Brittany McKelvey, Pedro A Torres-Saavedra, Jessica Li, Glenn Broeckx, Frederik Deman, Siraj Ali, Hillary S Andrews, Salim Arslan, Meir Azulay, Santhosh Balasubramanian, J C Barrett, Peter Caie und 29 weitere

Modern Pathology · 2026-02 · 39 (2) · 100944

DOI: 10.1016/j.modpat.2025.100944 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Modern Pathology, 2026-02. Verfasst von Brittany McKelvey und 40 weiteren Autor:innen. Beteiligte Einrichtung: Friends of Cancer Research, Washington, District of Columbia. Hauptthemen laut MEDLINE: Erb-b2 Receptor Tyrosine Kinases, Breast Neoplasms, Artificial Intelligence, Biomarkers, Tumor. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Historically, eligibility for receiving human epidermal growth factor receptor 2 (HER2)-targeted therapies was limited to HER2-positive tumors (immunohistochemistry 3+ or in situ hybridization amplified), but recent advances in antibody-drug conjugates have expanded these criteria to include HER2-low and HER2-ultralow expression. This evolving therapeutic landscape underscores the need for precise and reproducible HER2 assessment. Digital and computational pathology tools may help address these needs, but their measurement variability must be evaluated to inform research and clinical use. We evaluated HER2 scoring variability across 10 independently developed computational pathology artificial intelligence models applied to 1124 whole-slide images from 733 patients with breast cancer. Analyses included American Society of Clinical Oncology-College of American Pathologists categorical scores (0, 1+, 2+, and 3+), H-scores, tumor cell staining percentages, and counts of total and stained invasive carcinoma cells. Agreement among models and 3 pathologists was assessed using pairwise overall percent agreement (OPA), Cohen kappa, and hierarchical clustering. Median model pairwise OPA for categorical HER2 scores was 65.1% (kappa, 0.51). Agreement was highest for HER2 3+ vs not 3+ (OPA, 97.3%; kappa, 0.86) and lowest for HER2-low cases, reflecting existing measurement challenges. For HER2 0 (negative) vs not 0 (positive) scoring, the average negative agreement was 65.3%, compared with the average positive agreement of 91.3%, suggesting more agreement in non-HER2 0 scores. H-score and cell count analyses indicated that scoring differences were more related to staining interpretation than tumor cell detection. Pathologists showed numerically higher concordance than models, but interobserver variability persisted. In exploratory analyses, sample type, staining artifacts, and heterogeneous HER2 expression appeared to be associated with discrepancies. Artificial intelligence-based HER2 scoring demonstrated high agreement in identifying HER2 3+ cases. Variability was most pronounced in borderline HER2 categories, particularly in HER2 low, underscoring the need for continued tool refinement for handling low-intensity staining. Standardized training data sets, validation frameworks, and regulatory alignment are important to improve reproducibility. Developing reference standards and benchmarking data sets is critical to evaluate performance, support regulatory decision-making, and ensure real-world applicability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Erb-b2 Receptor Tyrosine KinasesBreast NeoplasmsArtificial IntelligenceBiomarkers, TumorImage Interpretation, Computer-AssistedHumansFemaleImmunohistochemistryReproducibility of ResultsObserver Variation

Stichwörter der Autor:innen

HER2 scoringartificial intelligencebreast cancercomputational pathologywhole-slide imaging

Substanzen

Erb-b2 Receptor Tyrosine KinasesERBB2 protein, humanBiomarkers, Tumor

Autor:innen und Institutionen

  • Friends of Cancer Research, Washington, District of Columbia.
  • Division of Cancer Treatment and Diagnosis, National Cancer Institute, Bethesda, Maryland.
  • PA(2), Department of Pathology, Ziekenhuis aan de Stroom (ZAS), Antwerp, Belgium; Centre for Oncological Research (CORE), MIPPRO, Faculty of Medicine, Antwerp University, Antwerp, Belgium.
  • Lunit, Seoul, South Korea.
  • Panakeia Technologies, Cambridge, United Kingdom.
  • Nucleai, Chicago, Illinois.

Zitieren

APA

McKelvey, B., Torres-Saavedra, P. A., Li, J., Broeckx, G., Deman, F., Ali, S., Andrews, H. S., Arslan, S., Azulay, M., Balasubramanian, S., Barrett, J. C., Caie, P., Chen, M., Cohen, D., Dasgupta, T., Fahrer, D., Green, G., Gustavson, M., Hersey, S., …, & Allen, J. (2026). Agreement Across 10 Artificial Intelligence Models in Assessing Human Epidermal Growth Factor Receptor 2 (HER2) Expression in Breast Cancer Whole-Slide Images. Modern Pathology, 39(2), 100944. https://doi.org/10.1016/j.modpat.2025.100944

Vancouver

McKelvey B, Torres-Saavedra PA, Li J, Broeckx G, Deman F, Ali S, et al. Agreement Across 10 Artificial Intelligence Models in Assessing Human Epidermal Growth Factor Receptor 2 (HER2) Expression in Breast Cancer Whole-Slide Images. Modern Pathology. 2026;39(2):100944. doi:10.1016/j.modpat.2025.100944

BibTeX
@article{McKelvey2026,
  author = {McKelvey, Brittany and Torres-Saavedra, Pedro A and Li, Jessica and Broeckx, Glenn and Deman, Frederik and Ali, Siraj and Andrews, Hillary S and Arslan, Salim and Azulay, Meir and Balasubramanian, Santhosh and Barrett, J C and Caie, Peter and Chen, Ming and Cohen, Daniel and Dasgupta, Tathagata and Fahrer, Diana and Green, George and Gustavson, Mark and Hersey, Sarah and Hidalgo-Sastre, Ana and Jiwani, Shahanawaz and Joseph, Elaine and Jung, Wonkyung and Kulig, Kimary and Kushnarev, Vladimir and Lennerz, Jochen K and Li, Xiaoxian and Lodge, Meredith and Mancuso, Joan and Montalto, Mike and Mukhopadhyay, Satabhisa and Ntelemis, Foivos and Oberley, Matthew and Pandya, Pahini and Puig, Oscar and Richardson, Edward T and Sarachakov, Alexander and Stewart, Mark and McShane, Lisa M and Salgado, Roberto and Allen, Jeff},
  title = {Agreement Across 10 Artificial Intelligence Models in Assessing Human Epidermal Growth Factor Receptor 2 (HER2) Expression in Breast Cancer Whole-Slide Images},
  journal = {Modern Pathology},
  year = {2026},
  volume = {39},
  number = {2},
  pages = {100944},
  doi = {10.1016/j.modpat.2025.100944}
}
Kostenlos starten →