Related Experiment Video
Updated: Jan 18, 2026
Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers
Published on: December 5, 2017
Transformer-Based HER2 Scoring in Breast Cancer: Comparative Performance of a Foundation and a Lightweight Model
Yeh-Han Wang1,2, Min-Hsiang Chang3, Hsin-Hsiu Tsai4
1Department of Anatomical Pathology, Fu Jen Catholic University Hospital, Fu Jen Catholic University, New Taipei City 24352, Taiwan.
Abstract:
Background/Objectives: Human epidermal growth factor 2 (HER2) scoring is critical for modern breast cancer therapies, especially with emerging indications of antibody-drug conjugates for HER2-low tumors. However, inter-observer agreement remains limited in borderline cases. Automatic artificial intelligence-based scoring has the potential to improve diagnostic consistency and scalability. This study aimed to develop two transformer-based models for HER2 scoring of breast cancer whole-slide images (WSIs) and compare their performance. Methods: We adapted a large-scale foundation model (Virchow) and a lightweight model (TinyViT). Both were trained using patch-level annotations and integrated into a WSI scoring pipeline. Performance was evaluated on a clinical test set (n = 66), including clinical decision tasks and inference efficiency. Results: Both models achieved substantial agreement with pathologist reports (linear weighted kappa: 0.860 for Virchow, 0.825 for TinyViT). Virchow showed slightly higher WSI-level accuracy than TinyViT, whereas TinyViT reduced inference times by 60%. In three binary clinical tasks, both models demonstrated a diagnostic performance comparable to pathologists, particularly in identifying HER2-low tumors for antibody-drug conjugate (ADC) therapy. A continuous scoring framework demonstrated a strong correlation between the two models (Pearson's r = 0.995) and aligned with human assessments. Conclusions: Both transformer-based artificial intelligence models achieved human-level accuracy for automated HER2 scoring with interpretable outputs. While the foundation model offers marginally higher accuracy, the lightweight model provides practical advantages for clinical deployment. In addition, continuous scoring may provide a more granular HER2 quantification, especially in borderline cases. This could support a new interpretive paradigm for HER2 assessment aligned with the evolving indications of ADC.
