{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:46:41Z","timestamp":1781624801347,"version":"3.54.5"},"reference-count":46,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A\n                      <jats:italic toggle=\"yes\">k<\/jats:italic>\n                      -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\u2019s predictions.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076261444271","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:39:54Z","timestamp":1777052394000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep ensemble of multi-head attention CNNs for histopathological image-based of lung and colon cancer diagnosis"],"prefix":"10.1177","volume":"12","author":[{"given":"A. K. Z Rasel","family":"Rahman","sequence":"first","affiliation":[{"name":"Khulna University"},{"name":"Bangladesh Army University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S M Masfequier Rahman","family":"Swapno","sequence":"additional","affiliation":[{"name":"Bangladesh University of Business and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Avi Deb","family":"Raha","sequence":"additional","affiliation":[{"name":"Kyung Hee University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sujit","family":"Biswas","sequence":"additional","affiliation":[{"name":"University of London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shakil","family":"Khan","sequence":"additional","affiliation":[{"name":"International American University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katura Gania","family":"Khushbu","sequence":"additional","affiliation":[{"name":"East West University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4321-5880","authenticated-orcid":false,"given":"Ahmed Wasif","family":"Reza","sequence":"additional","affiliation":[{"name":"East West University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9132-8893","authenticated-orcid":false,"given":"Anupam Kumar","family":"Bairagi","sequence":"additional","affiliation":[{"name":"Khulna University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saad","family":"Aloteibi","sequence":"additional","affiliation":[{"name":"King Saud University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0756-1006","authenticated-orcid":false,"given":"Mohammad Ali","family":"Moni","sequence":"additional","affiliation":[{"name":"Daffodil International University"},{"name":"School of Health and Rehabilitation Sciences, The University of Queensland, St Lucia, Brisbane, QLD, Australia"},{"name":"AI &amp; Digital Health Technology, Rural Health Research Institute, Charles Sturt University, Orange, NSW, Australia"},{"name":"AI &amp; Digital Health Technolog, Artificial Intelligence &amp; Cyber Futures Centre, Charles Sturt University, Bathurst, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"e_1_3_4_2_2","volume-title":"Global cancer data 2023","author":"World Health Organization","year":"2023","unstructured":"World Health Organization. Global cancer data 2023. https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cancer, (2023, Online; accessed 2024-10-01)."},{"issue":"1","key":"e_1_3_4_3_2","first-page":"1","article-title":"Cancer statistics 2023: Lung and colorectal cancers","volume":"73","author":"American Cancer Society","year":"2023","unstructured":"American Cancer Society. Cancer statistics 2023: Lung and colorectal cancers. CA: A Cancer Journal for Clinicians 2023; 73(1): 1\u201332. https:\/\/doi.org\/10.3322\/caac.21660","journal-title":"CA: A Cancer Journal for Clinicians"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2024.054460"},{"key":"e_1_3_4_5_2","first-page":"104337","article-title":"Advances in deep learning for cancer diagnosis using histopathological images","volume":"139","author":"Walia P","year":"2023","unstructured":"Walia P, Rathore A, Kumar A. Advances in deep learning for cancer diagnosis using histopathological images. Journal of Biomedical Informatics 2023; 139: 104337. https:\/\/doi.org\/10.1016\/j.jbi.2023.104337","journal-title":"Journal of Biomedical Informatics"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_3_4_7_2","doi-asserted-by":"crossref","unstructured":"Deb Raha A Adhikary A Gain M et al. Boosting federated domain generalization: Understanding the role of advanced pre-trained architectures. arXiv preprint arXiv:2409.13527 2024.","DOI":"10.2139\/ssrn.4967928"},{"key":"e_1_3_4_8_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani A","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. Advances in neural information processing systems 2017; 30, URL. https:\/\/arxiv.org\/abs\/1706.03762","journal-title":"Advances in neural information processing systems"},{"key":"e_1_3_4_9_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Vaswani A","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 5998\u20136008. URL. https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_4_10_2","first-page":"1","article-title":"Advancing ultra-reliable 6 g: Transformer and semantic localization empowered robust beamforming in millimeter-wave communications","volume":"74","author":"Deb Raha A","year":"2025","unstructured":"Deb Raha A, Kim K, Adhikary A, et al. Advancing ultra-reliable 6 g: Transformer and semantic localization empowered robust beamforming in millimeter-wave communications. IEEE Transactions on Vehicular Technology 2025; 74: 1\u201316. https:\/\/doi.org\/10.1109\/TVT.2025.3573711","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3141826"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics8040370"},{"key":"e_1_3_4_14_2","first-page":"107619","article-title":"Colon and lung cancer classification from multi-modal images using resilient and efficient neural network architectures","volume":"169","author":"Hasib Uddin A","year":"2024","unstructured":"Hasib Uddin A, Chen Y-L, Akter R, et al. Colon and lung cancer classification from multi-modal images using resilient and efficient neural network architectures. Computers in Biology and Medicine 2024; 169: 107619. https:\/\/doi.org\/10.1016\/j.compbiomed.2024.107619","journal-title":"Computers in Biology and Medicine"},{"key":"e_1_3_4_15_2","doi-asserted-by":"crossref","unstructured":"Zhou Y Graham S Alemi Koohbanani N et al. Cgc-net: Cell graph convolutional network for grading of colorectal cancer histology images. arXiv preprint arXiv:1909.01068 2019.","DOI":"10.1109\/ICCVW.2019.00050"},{"key":"e_1_3_4_16_2","unstructured":"Wen H Lu J Feng J. Distract your attention: Multi-head cross attention network for facial expression recognition. arXiv preprint arXiv:2109.07270 2021."},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"e_1_3_4_18_2","unstructured":"Xiao A Yang M Zhou K. Repulsive attention: Rethinking multi-head attention as bayesian inference. arXiv preprint arXiv:2009.09364 2020."},{"key":"e_1_3_4_19_2","unstructured":"Sakamoto K Sato I. Benign or not-benign overfitting in token selection of attention mechanism. arXiv preprint arXiv:2409.17625 2024."},{"key":"e_1_3_4_20_2","unstructured":"Magen R Shang S Xu Z et al. Benign overfitting in single-head attention. arXiv preprint arXiv:2410.07746 2024."},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.3390\/technologies12040056"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10030383"},{"key":"e_1_3_4_23_2","article-title":"Classification of lung and colon cancer histopathological images using global context attention based convolutional neural network","author":"Al-Mamun Provath M","year":"2023","unstructured":"Al-Mamun Provath M, Deb K, Kumar Dhar P, et al. Classification of lung and colon cancer histopathological images using global context attention based convolutional neural network. IEEE Access 2023.","journal-title":"IEEE Access"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14202274"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124114"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.23919\/INDIACom61295.2024.10498812"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117695"},{"issue":"1","key":"e_1_3_4_28_2","first-page":"1","article-title":"Advanced deep learning for multi-class colorectal cancer histopathology: integrating transfer learning and ensemble methods","volume":"13","author":"Ke Q","year":"2023","unstructured":"Ke Q, Yap WS, Tee YK. Advanced deep learning for multi-class colorectal cancer histopathology: integrating transfer learning and ensemble methods. Quantitative Imaging in Medicine and Surgery 2023; 13(1): 1\u201312. https:\/\/doi.org\/10.21037\/qims-22-1234, URL. https:\/\/qims.amegroups.org\/article\/view\/135171\/html","journal-title":"Quantitative Imaging in Medicine and Surgery"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02628-7"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1177\/15330338221124372"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1002\/ima.22769"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15051591"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40031-024-00992-6"},{"key":"e_1_3_4_35_2","unstructured":"Borkowski AA Bui MM Thomas LB et al. Lung and colon cancer histopathological image dataset (lc25000). arXiv preprint 2019 URL. https:\/\/www.kaggle.com\/datasets\/javaidahmadwani\/lc25000"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_4_37_2","volume-title":"Deep Learning","author":"Goodfellow I","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A. Deep Learning. MIT Press, 2016. URL. https:\/\/www.deeplearningbook.org\/"},{"key":"e_1_3_4_38_2","volume-title":"A guide to convolution arithmetic for deep learning","author":"Vincent D","year":"2016","unstructured":"Vincent D, Visin F. A guide to convolution arithmetic for deep learning, 2016."},{"key":"e_1_3_4_39_2","first-page":"315","volume-title":"Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Glorot X","year":"2011","unstructured":"Glorot X, Bordes A, Bengio Y. Deep sparse rectifier neural networks. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), 2011, pp. 315\u2013323."},{"issue":"1","key":"e_1_3_4_40_2","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research 2014; 15(1): 1929\u20131958.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"e_1_3_4_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3285821"},{"key":"e_1_3_4_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-023-02546-x"},{"key":"e_1_3_4_45_2","first-page":"83","volume-title":"International Conference on Machine Intelligence and Emerging Technologies","author":"Rahman AKZR","year":"2024","unstructured":"Rahman AKZR, Ghosh P, Deb Raha A, et al. Focusing on subtleties: Class-specific attention-based deep learning for precise diagnosis of lung and colon cancers. In: International Conference on Machine Intelligence and Emerging Technologies. Springer, 2024, pp. 83\u2013100."},{"key":"e_1_3_4_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA58977.2023.00196"},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3385099"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261444271","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261444271","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261444271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:56:56Z","timestamp":1777399016000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261444271"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":46,"alternative-id":["10.1177\/20552076261444271"],"URL":"https:\/\/doi.org\/10.1177\/20552076261444271","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261444271"}}