EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Bridging Global Attention and Local Hierarchies: A Robust Hybrid Ensemble Framework With Multi-Perspective Explainability for Automated HER2-IHC Scoring

Hossam Magdy Balaha iD, Norah Saleh Alghamdi, Nithya Rekha Sivakumar, Shakila Basheer, Khadiga M Ali, Ayman El-Baz iD

Technology in Cancer Research & Treatment · 2026-07 · 25

DOI: 10.1177/15330338261465522 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technology in Cancer Research & Treatment, online erschienen am 04.07.2026. Verfasst von Hossam Magdy Balaha und 5 weiteren Autor:innen. Beteiligte Einrichtung: Bioengineering Department, J.B. Speed School of Engineering, University of Louisville, Louisville, KY, USA. Hauptthemen laut MEDLINE: Erb-b2 Receptor Tyrosine Kinases, Breast Neoplasms, Immunohistochemistry, Biomarkers, Tumor. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Determining the HER2 status accurately is a critical determinant in breast cancer treatment planning. Manual scoring remains highly susceptible to inter- and intra-observer variability, particularly in diagnostically ambiguous cases (HER2 1+/2+). Furthermore, contemporary deep learning models frequently lack the robustness and interpretability required for safe clinical integration.

Methods

We propose a hybrid ensemble framework that synergizes EVA-02-Large, Vision Transformer-Base, and ConvNeXt-V2-Nano architectures via an adaptive late-fusion mechanism. The model was trained on the expert-annotated HER2-IHC-40x dataset ( N = 10 , 997 patches) and rigorously evaluated across ten independent trials. The experimental protocol incorporated comprehensive perturbation analysis across 20+ image corruption types and multi-perspective Explainable AI (XAI) assessment using Grad-CAM, Grad-CAM++, and Layer-CAM to validate alignment with pathologist-recognized morphological features.

Results

The fused ensemble achieved state-of-the-art weighted accuracy ( 98.05 % ± 0.10 % ) and Balanced Accuracy ( 98.25 % ± 0.11 % ), outperforming the strongest single backbone by 0.45%. Misclassification rates for equivocal classes decreased by >18%. The framework demonstrated high resilience to structural perturbations ( m C E < 0.05 ) while exhibiting expected sensitivity to extreme photometric variations. XAI analysis confirmed that model attention consistently prioritizes clinically relevant membrane staining patterns, mirroring expert diagnostic reasoning.

Conclusion

This study establishes a highly accurate and interpretable pipeline for automated HER2-IHC scoring, demonstrating that hybrid transformer-CNN ensembles can effectively resolve diagnostically challenging cases. By combining superior predictive performance, structural robustness, and transparent decision-making, the proposed framework offers a highly promising foundational framework that, following prospective multi-reader clinical validation, could serve as a robust decision-support tool to standardize HER2 assessment, reduce inter-observer variability, and accelerate precision oncology workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Erb-b2 Receptor Tyrosine KinasesBreast NeoplasmsImmunohistochemistryBiomarkers, TumorImage Interpretation, Computer-AssistedHumansFemaleDeep LearningImage Processing, Computer-AssistedEnsemble Learning

Stichwörter der Autor:innen

ConvNeXtHER2-IHC scoringbreast cancerdigital pathologyensemble learningexplainable AI (XAI)hybrid deep learningrobustness analysisvision transformers

Substanzen

Erb-b2 Receptor Tyrosine KinasesERBB2 protein, humanBiomarkers, Tumor

Autor:innen und Institutionen

  • Bioengineering Department, J.B. Speed School of Engineering, University of Louisville, Louisville, KY, USA.
  • Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University (PNU), Riyadh, Saudi Arabia.
  • Department of Information Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University (PNU), Riyadh, Saudi Arabia.
  • Pathology Department, Faculty of Medicine, Mansoura University, Mansoura, Egypt.

ORCID-Profile: Hossam Magdy Balaha, Ayman El-Baz

Zitieren

APA

Balaha, H. M., Alghamdi, N. S., Sivakumar, N. R., Basheer, S., Ali, K. M., & El-Baz, A. (2026). Bridging Global Attention and Local Hierarchies: A Robust Hybrid Ensemble Framework With Multi-Perspective Explainability for Automated HER2-IHC Scoring. Technology in Cancer Research & Treatment, 25. https://doi.org/10.1177/15330338261465522

Vancouver

Balaha HM, Alghamdi NS, Sivakumar NR, Basheer S, Ali KM, El-Baz A. Bridging Global Attention and Local Hierarchies: A Robust Hybrid Ensemble Framework With Multi-Perspective Explainability for Automated HER2-IHC Scoring. Technology in Cancer Research & Treatment. 2026;25. doi:10.1177/15330338261465522

BibTeX
@article{Balaha2026,
  author = {Balaha, Hossam Magdy and Alghamdi, Norah Saleh and Sivakumar, Nithya Rekha and Basheer, Shakila and Ali, Khadiga M and El-Baz, Ayman},
  title = {Bridging Global Attention and Local Hierarchies: A Robust Hybrid Ensemble Framework With Multi-Perspective Explainability for Automated HER2-IHC Scoring},
  journal = {Technology in Cancer Research & Treatment},
  year = {2026},
  volume = {25},
  doi = {10.1177/15330338261465522}
}
Kostenlos starten →