EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Explainable hybrid vision transformer-convolutional neural network with cross-attention fusion for multi-institutional breast cancer receptor status prediction from H&E histopathology images

Elham Saleh Albalawi iD, Jibran Qayyum, Junaid Qayyum

Science Progress · 2026-10 · 109 (4)

DOI: 10.1177/00368504261504501 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Progress, online erschienen am 05.11.2026. Verfasst von Elham Saleh Albalawi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, Faculty of Medicine, University of Tabuk, Tabuk, Kingdom of Saudi Arabia. Hauptthemen laut MEDLINE: Breast Neoplasms, Erb-b2 Receptor Tyrosine Kinases, Receptors, Progesterone, Receptors, Estrogen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The integration of artificial intelligence (AI) into digital pathology has revolutionised breast cancer diagnostics, offering transformative opportunities to automate and refine molecular profiling, which is essential to precision oncology. Accurate determination of receptor status—estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2)—remains pivotal in guiding personalised treatment planning and prognostic assessment. However, traditional immunohistochemistry (IHC) and molecular assays are limited by resource intensity, lengthy turnaround times, and inter-observer variability, underscoring the need for scalable computational alternatives. This study proposes a novel integrative AI-driven framework for predicting breast cancer receptor profiles directly from hematoxylin and eosin (H&E)-stained histopathology images. The framework employs a hybrid vision transformer-convolutional neural network (ViT-CNN) architecture with a cross-attention fusion mechanism to capture both global contextual information and fine-grained local features. Experiments show AUCs of 0.967, 0.952, and 0.941 for ER, PR, and HER2 prediction, respectively, representing relative improvements of 12.4%, 9.8%, and 10.8% over the best-performing prior method (DCS-ST), re-evaluated under our identical protocol (absolute AUC differences of 0.107, 0.085 and 0.092). Furthermore, the framework enables automated molecular subtyping into luminal A, luminal B, HER2-enriched, and triple-negative categories with a macro-averaged F1-score of 95.7%. A comprehensive multi-institutional validation was performed on 2,847 external whole-slide images from three partner institutions (not including the primary BINO Hospital test set), showing consistent performance (a mean AUC reduction of 0.83 percentage points relative to the internal test set) across the staining protocols and scanners represented. Integrated explainability modules, including attention visualisations and Grad-CAM, enhance interpretability, supporting pathologist review. In a single-institution retrospective workflow audit, AI assistance was associated with an estimated 72.7% reduction in diagnostic turnaround time (from a conventional mean of 72.4 hours to 19.8 hours; Section 6.10, where approximately 65% of the AI-assisted time is un-itemised queueing and logistics) and, in a 120-WSI reader study, with higher inter-observer agreement (kappa 0.847 to 0.967). These clinical-impact estimates are hypothesis-generating and require prospective validation. The findings position the framework as a promising, explainable approach to AI-assisted digital pathology that warrants prospective, multi-centre clinical evaluation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsErb-b2 Receptor Tyrosine KinasesReceptors, ProgesteroneReceptors, EstrogenHumansFemaleConvolutional Neural NetworksEosine Yellowish-(YS)Artificial IntelligenceImage Processing, Computer-AssistedHematoxylinImmunohistochemistryNeural Networks, Computer

Stichwörter der Autor:innen

Breast CancerConvolutional Neural NetworksDigital PathologyExplainable AIMolecular SubtypingReceptor Status PredictionVision Transformers

Substanzen

Erb-b2 Receptor Tyrosine KinasesReceptors, ProgesteroneReceptors, EstrogenERBB2 protein, humanEosine Yellowish-(YS)Hematoxylin

Autor:innen und Institutionen

  • Department of Pathology, Faculty of Medicine, University of Tabuk, Tabuk, Kingdom of Saudi Arabia.
  • Department of Pharmacy, University of Peshawar, Peshawar, Pakistan.
  • College of Information Engineering, Jinhua University of Vocational Technology, Jinhua, Zhejiang, China.
  • Waikato International College, Jinhua University of Vocational Technology, Jinhua, Zhejiang, China.

ORCID-Profile: Elham Saleh Albalawi

Zitieren

APA

Albalawi, E. S., Qayyum, J., & Qayyum, J. (2026). Explainable hybrid vision transformer-convolutional neural network with cross-attention fusion for multi-institutional breast cancer receptor status prediction from H&E histopathology images. Science Progress, 109(4). https://doi.org/10.1177/00368504261504501

Vancouver

Albalawi ES, Qayyum J, Qayyum J. Explainable hybrid vision transformer-convolutional neural network with cross-attention fusion for multi-institutional breast cancer receptor status prediction from H&E histopathology images. Science Progress. 2026;109(4). doi:10.1177/00368504261504501

BibTeX
@article{Albalawi2026,
  author = {Albalawi, Elham Saleh and Qayyum, Jibran and Qayyum, Junaid},
  title = {Explainable hybrid vision transformer-convolutional neural network with cross-attention fusion for multi-institutional breast cancer receptor status prediction from H&E histopathology images},
  journal = {Science Progress},
  year = {2026},
  volume = {109},
  number = {4},
  doi = {10.1177/00368504261504501}
}
Kostenlos starten →