جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.
مقالوصول مفتوح2025SDG 38 استشهاد

Explainable multi-view transformer framework with mutual learning for precision breast cancer pathology image classification

Haewon Byeon،Mahmood Abdulrazzaq Alsaadi،Richa Vijay،Purshottam J. Assudani،Ashit Kumar Dutta،Monika Bansal،Pavitar Parkash Singh،Mukesh Soni،Mohammed Wasim Bhatt ✉

Frontiers in Oncology · مج 15 · 1626785-1626785 · 2025

الملخّص

Breast cancer remains the most prevalent cancer among women, where accurate and interpretable analysis of pathology images is vital for early diagnosis and personalized treatment planning. However, conventional single-network models fall short in balancing both performance and explainability—Convolutional Neural Networks (CNNs) lack the capacity to capture global contextual information, while Transformers are limited in modeling fine-grained local details. To overcome these challenges and contribute to the advancement of Explainable AI (XAI) in precision cancer diagnosis, this paper proposes MVT-OFML (Multi-View Transformer Online Fusion Mutual Learning), a novel and interpretable classification framework for breast cancer pathology images. MVT-OFML combines ResNet-50 for extracting detailed local features and a multi-view Transformer encoding module for capturing comprehensive global context across multiple perspectives. A key innovation is the Online Fusion Mutual Learning (OFML) mechanism, which enables bidirectional knowledge sharing between the CNN and Transformer branches by aligning both intermediate feature representations and prediction logits. This mutual learning framework enhances performance while also producing interpretable attention maps and feature-level visualizations that reveal the decision-making process of the model—promoting transparency, trust, and clinical usability. Extensive experiments on the BreakHis and BACH datasets demonstrate that MVT-OFML significantly outperforms the strongest baseline models, achieving accuracy improvements of 0.90% and 2.26%, and F 1 -score gains of 4.75% and 3.21%, respectively. By integrating complementary modeling paradigms with explainable learning strategies, MVT-OFML offers a promising AI solution for precise and interpretable breast cancer diagnosis and prognosis, supporting informed decision-making in clinical settings.

التفاصيل

المجلة
Frontiers in Oncology
الناشر
Frontiers Media
المجلد
15
العدد
—
الصفحات
1626785-1626785
الترقيم الدولي ISSN
2234-943X
السنة
2025
اللغة
en
الترخيص
cc-by
الوصول المفتوح
gold
الاستشهادات
8
المصدر
scopus

الموضوعات

Computer scienceArtificial intelligenceMachine learningDeep learningConvolutional neural networkTransformer

AI in cancer detection (Computer Science) · Explainable Artificial Intelligence (XAI) (Computer Science) · Advanced Neural Network Applications (Computer Science)

استشهد بهذا

APA
Byeon, H., Alsaadi, M. A., Vijay, R., Assudani, P. J., Dutta, A. K., Bansal, M., Singh, P. P., Soni, M., Bhatt, M. W. (2025). Explainable multi-view transformer framework with mutual learning for precision breast cancer pathology image classification. Frontiers in Oncology, 15, 1626785-1626785. https://doi.org/10.3389/fonc.2025.1626785
Harvard
Byeon, H., Alsaadi, M. A., Vijay, R., Assudani, P. J., Dutta, A. K., Bansal, M., Singh, P. P., Soni, M., Bhatt, M. W. 2025, 'Explainable multi-view transformer framework with mutual learning for precision breast cancer pathology image classification', Frontiers in Oncology, vol. 15, 1626785-1626785. Available at: https://doi.org/10.3389/fonc.2025.1626785
Vancouver
Byeon H, Alsaadi MA, Vijay R, Assudani PJ, Dutta AK, Bansal M, Singh PP, Soni M, Bhatt MW. Explainable multi-view transformer framework with mutual learning for precision breast cancer pathology image classification. Frontiers in Oncology. 2025;15, 1626785-1626785.
BibTeX
@article{byeon2025646,
  title = {Explainable multi-view transformer framework with mutual learning for precision breast cancer pathology image classification},
  author = {Haewon Byeon and Mahmood Abdulrazzaq Alsaadi and Richa Vijay and Purshottam J. Assudani and Ashit Kumar Dutta and Monika Bansal and Pavitar Parkash Singh and Mukesh Soni and Mohammed Wasim Bhatt},
  year = {2025},
  journal = {Frontiers in Oncology},
  volume = {15},
  pages = {1626785-1626785},
  publisher = {Frontiers Media},
  doi = {10.3389/fonc.2025.1626785},
  url = {https://doi.org/10.3389/fonc.2025.1626785}
}
RIS
TY  - JOUR
AU  - Haewon Byeon
AU  - Mahmood Abdulrazzaq Alsaadi
AU  - Richa Vijay
AU  - Purshottam J. Assudani
AU  - Ashit Kumar Dutta
AU  - Monika Bansal
AU  - Pavitar Parkash Singh
AU  - Mukesh Soni
AU  - Mohammed Wasim Bhatt
TI  - Explainable multi-view transformer framework with mutual learning for precision breast cancer pathology image classification
PY  - 2025
JO  - Frontiers in Oncology
VL  - 15
SP  - 1626785-1626785
DO  - 10.3389/fonc.2025.1626785
UR  - https://doi.org/10.3389/fonc.2025.1626785
ER  - 

مخرجات ذات صلة