EUVIMEDUpptäck EUVIMED
Open access · CC BY 4.0

Ensemble Deep Learning-Based High-Precision Framework for Breast Cancer Detection from Histopathological Images

Faizan Ahmad, Arfan Jaffar, Ghazanfar Latif iD, Jaafar Alghazo, Sohail Masood Bhatti

Diagnostics · 2026-02-24 · 16 (5) · 653

DOI: 10.3390/diagnostics16050653 ↗

At a glance

Journal article in Diagnostics, published online on 2026-02-24. Written by Faizan Ahmad and 4 co-authors. Institution: Department of Computer Science, Superior University, Lahore 547700, Pakistan. Cited 7 times so far (Crossref); 44 references. The full text is freely available (open access, CC BY 4.0).

AbstractSubjectsBibliografiska uppgifterCiteRelated studies

Abstract (original language)

Background/Objectives: Analysis of histopathological images is the absolute standard of breast cancer diagnosis. However, modern deep learning- and ViT-based architecture still struggle to capture effective local and global discriminatory patterns that tend to make architecture more complex, increasing the risk of overfitting and optimization problems.

Methods

To address these problems, this paper proposes a four-phase hybrid framework that aims to enhance the feature fusion, improving the model’s strength, robustness, and generalization ability. In Phase 1, the BreakHis dataset was split patient-wise into a 70-15-15 manner to avoid data leakage, while extensive data augmentation, comprehensive normalization, and a five-fold cross-validation protocol were implemented to make the dataset more varied and reliably evaluated without bias. Phase 2 entailed the training of three CNNs (VGG16, ResNet50, and DenseNet121) and four ViTs (DeiT, CaiT, T2T-ViT, and Swin Transformer) independently to establish the strict baseline performance standards. In Phase 3, the CNN-based features were fused and classified with a soft voting mechanism to allow more stable and representative learning. Phase 4 depicts the Proposed Framework, which combines the two best-performing CNN and ViT models. Feature refinements were performed randomly by using Global Average Pooling and feature scaling, while a self-attention mechanism enabled the accurate cross-modal feature fusion. The generalization capability of the fused representation was further enhanced by the subsequent of dense layers followed by dropout.

Results

XGBoost exhibited the highest performance among the evaluated ML classifiers, achieving 98.7% accuracy and 98.7% F1-score on BreakHis, while achieving 95.8% accuracy on external BACH dataset backed by Grad-CAM- and Grad-CAM++-based interpretability.

Conclusions

By integrating CNNs and ViTs through self-attention, the proposed framework offers a robust and interpretable solution for automated breast cancer diagnosis.

Subjects

Author keywords

breast cancer screeningconvolutional neural networkcross-attentiondeep learningensemble learningfeature concatenationhistopathological imagesoverfitting mitigationprecision engineeringvision transformers

Authors and institutions

  • Department of Computer Science, Superior University, Lahore 547700, Pakistan.
  • Department of Computing Science, Thompson Rivers University, Kamloops, BC V2C 0C8, Canada.
  • Math, Science and Technology Department, University of Minnesota Crookston, Crookston, MN 56716, USA.

ORCID profiles: Ghazanfar Latif

Cite

APA

Ahmad, F., Jaffar, A., Latif, G., Alghazo, J., & Bhatti, S. M. (2026). Ensemble Deep Learning-Based High-Precision Framework for Breast Cancer Detection from Histopathological Images. Diagnostics, 16(5), 653. https://doi.org/10.3390/diagnostics16050653

Vancouver

Ahmad F, Jaffar A, Latif G, Alghazo J, Bhatti SM. Ensemble Deep Learning-Based High-Precision Framework for Breast Cancer Detection from Histopathological Images. Diagnostics. 2026;16(5):653. doi:10.3390/diagnostics16050653

BibTeX
@article{Ahmad2026,
  author = {Ahmad, Faizan and Jaffar, Arfan and Latif, Ghazanfar and Alghazo, Jaafar and Bhatti, Sohail Masood},
  title = {Ensemble Deep Learning-Based High-Precision Framework for Breast Cancer Detection from Histopathological Images},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {5},
  pages = {653},
  doi = {10.3390/diagnostics16050653}
}
Start for free →