Deep ensemble of multi-head attention CNNs for histopathological image-based of lung and colon cancer diagnosis
DIGITAL HEALTH · 2026-02 · 12
DOI: 10.1177/20552076261444271 ↗Kurz gefasst
Fachartikel in der Zeitschrift DIGITAL HEALTH, online erschienen am 24.04.2026. Verfasst von A K Z Rasel Rahman und 9 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science and Engineering Discipline, Khulna University, Khulna, Bangladesh. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Objectives
Classifying lung and colon cancer from histopathological images remains a significant challenge due to the high degree of intra-class feature similarity and complex tissue morphology, particularly in lung cancer cases. While convolutional neural networks (CNNs) have demonstrated strong spatial feature extraction capabilities, they cannot inherently model long-range dependencies and global contextual relationships. Although attention-based methods partially address these limitations, they often suffer from overfitting, limited generalization across heterogeneous datasets, and insufficient interpretability for clinical adoption. To address these challenges, this study presents a Multi-Head Attention-Based Convolutional Neural Network (MHAB-CNN) ensemble framework that captures localized and global feature interactions critical for robust cancer classification.
Methods
A k -fold cross-validation strategy is adopted to train multiple MHAB-CNN models, from which the empirically top-performing ones are selected and aggregated to form a compact ensemble. This approach improves robustness, reduces overfitting, and ensures computational efficiency. Grad-CAM-based visualizations interpret the discriminative regions influencing the model’s predictions.
Results
Experimental evaluation on the LC25000 dataset demonstrates that the proposed framework achieves an average validation accuracy of 99.84% across folds. Furthermore, the E3 ensemble configuration, comprising models M1, M6, and M9, achieves the highest classification score on the held-out test set.
Conclusion
The proposed MHAB-CNN ensemble framework effectively captures localized and global feature interactions critical for robust lung and colon cancer classification, while improving robustness, reducing overfitting, and enhancing interpretability for potential clinical adoption.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computer Science and Engineering Discipline, Khulna University, Khulna, Bangladesh.
- Department of Computer Science and Engineering, Bangladesh Army University of Science and Technology, Saidpur, Bangladesh.
- Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Mirpur, Dhaka, Bangladesh.
- Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Yongin, Republic of Korea.
- School of Science and Technology, University of London, London, UK.
- Department of Business Analytics, International American University, Los Angeles, CA, USA.
ORCID-Profile: Ahmed Wasif Reza, Anupam Kumar Bairagi, Mohammad Ali Moni
Zitieren
APA
Rahman, A. K. Z. R., Swapno, S. M. M. R., Raha, A. D., Biswas, S., Khan, S., Khushbu, K. G., Reza, A. W., Bairagi, A. K., Aloteibi, S., & Moni, M. A. (2026). Deep ensemble of multi-head attention CNNs for histopathological image-based of lung and colon cancer diagnosis. DIGITAL HEALTH, 12. https://doi.org/10.1177/20552076261444271
Vancouver
Rahman AKZR, Swapno SMMR, Raha AD, Biswas S, Khan S, Khushbu KG, et al. Deep ensemble of multi-head attention CNNs for histopathological image-based of lung and colon cancer diagnosis. DIGITAL HEALTH. 2026;12. doi:10.1177/20552076261444271
BibTeX
@article{Rahman2026,
author = {Rahman, A K Z Rasel and Swapno, S M Masfequier Rahman and Raha, Avi Deb and Biswas, Sujit and Khan, Shakil and Khushbu, Katura Gania and Reza, Ahmed Wasif and Bairagi, Anupam Kumar and Aloteibi, Saad and Moni, Mohammad Ali},
title = {Deep ensemble of multi-head attention CNNs for histopathological image-based of lung and colon cancer diagnosis},
journal = {DIGITAL HEALTH},
year = {2026},
volume = {12},
doi = {10.1177/20552076261444271}
}
EUVIMED