{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T11:33:13Z","timestamp":1781955193694,"version":"3.54.5"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["10078953"],"award-info":[{"award-number":["10078953"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Brain Inf."],"published-print":{"date-parts":[[2024,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Transformers have dominated the landscape of Natural Language Processing (NLP) and revolutionalized generative AI applications. Vision Transformers (VT) have recently become a new state-of-the-art for computer vision applications. Motivated by the success of VTs in capturing short and long-range dependencies and their ability to handle class imbalance, this paper proposes an ensemble framework of VTs for the efficient classification of Alzheimer\u2019s Disease (AD). The framework consists of four vanilla VTs, and ensembles formed using hard and soft-voting approaches. The proposed model was tested using two popular AD datasets: OASIS and ADNI. The ADNI dataset was employed to assess the models\u2019 efficacy under imbalanced and data-scarce conditions. The ensemble of VT saw an improvement of around 2% compared to individual models. Furthermore, the results are compared with state-of-the-art and custom-built Convolutional Neural Network (CNN) architectures and Machine Learning (ML) models under varying data conditions. The experimental results demonstrated an overall performance gain of 4.14% and 4.72% accuracy over the ML and CNN algorithms, respectively. The study has also identified specific limitations and proposes avenues for future research. The codes used in the study are made publicly available.<\/jats:p>","DOI":"10.1186\/s40708-024-00238-7","type":"journal-article","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T17:02:12Z","timestamp":1727974932000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Ensemble of vision transformer architectures for efficient Alzheimer\u2019s Disease classification"],"prefix":"10.1186","volume":"11","author":[{"given":"Noushath","family":"Shaffi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vimbi","family":"Viswan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mufti","family":"Mahmud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"238_CR1","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1590\/S1980-57642009DN30300003","volume":"3","author":"VdJRd Paula","year":"2009","unstructured":"Paula VdJRd, Guimar\u00e3es FM, Diniz BS, Forlenza OV (2009) Neurobiological pathways to Alzheimer\u2019s disease: amyloid-beta, tau protein or both? Dementia Neuropsychologia 3:188\u2013194","journal-title":"Dementia Neuropsychologia"},{"issue":"3","key":"238_CR2","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.3233\/JAD-181049","volume":"68","author":"T Yan","year":"2019","unstructured":"Yan T, Wang Y, Weng Z et al (2019) Early-stage identification and pathological development of AD using multimodal MRI. J Alzheimer\u2019s Dis 68(3):1013","journal-title":"J Alzheimer\u2019s Dis"},{"key":"238_CR3","volume-title":"World Alzheimer report 2022: life after diagnosis - navigating treatment, care and support","author":"S Gauthier","year":"2022","unstructured":"Gauthier S, Webster C, Sarvaes S et al (2022) World Alzheimer report 2022: life after diagnosis - navigating treatment, care and support. Alzheimer\u2019s Disease International, London"},{"key":"238_CR4","volume-title":"World Alzheimer report 2023: reducing dementia risk: never too early, never too late","author":"S Long","year":"2023","unstructured":"Long S, Benoist C, Weidner W (2023) World Alzheimer report 2023: reducing dementia risk: never too early, never too late. Alzheimer\u2019s Disease International, London"},{"key":"238_CR5","doi-asserted-by":"crossref","unstructured":"Shaffi N, Subramanian K, Vimbi V, Hajamohideen F, Abdesselam A, Mahmud M (2024) Performance evaluation of deep, shallow and ensemble machine learning methods for the automated classification of Alzheimer\u2019s disease. Int J Neural Syst","DOI":"10.1142\/S0129065724500291"},{"key":"238_CR6","doi-asserted-by":"crossref","unstructured":"Shaffi N, Vimbi V, Mahmud M, Subramanian K, Hajamohideen F (2023) Bagging the best: A hybrid svm-knn ensemble for accurate and early detection of alzheimer\u2019s and parkinson\u2019s diseases International Conference on Brain Informatics. Springer, Berlin. 443\u2013455","DOI":"10.1007\/978-3-031-43075-6_38"},{"issue":"1","key":"238_CR7","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao A, Xu C, Xu Y et al (2022) A survey on vision transformer. IEEE Trans Pattern Anal Machine Intell 45(1):87\u2013110","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"238_CR8","first-page":"10012","volume-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Z Liu","year":"2021","unstructured":"Liu Z, Lin Y, Cao Y et al (2021) Swin transformer: Hierarchical vision transformer using shifted windows. ICCV, Virtual, pp 10012\u201310022"},{"key":"238_CR9","unstructured":"Touvron H, Cord M, Douze M, et al (2021) Training data-efficient image transformers & distillation through attention. Proc. ICML. pp. 10347\u201310357"},{"key":"238_CR10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.08254","author":"H Bao","year":"2021","unstructured":"Bao H, Dong L, Piao S, Wei F (2021) BEit: BERT pre-training of image transformers. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2106.08254","journal-title":"arXiv"},{"key":"238_CR11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929","author":"A Dosovitskiy","year":"2020","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2010.11929","journal-title":"arXiv"},{"issue":"10s","key":"238_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505244","volume":"54","author":"S Khan","year":"2022","unstructured":"Khan S, Naseer M, Hayat M et al (2022) Transformers in vision: a survey. ACM Comput Surv (CSUR) 54(10s):1\u201341","journal-title":"ACM Comput Surv (CSUR)"},{"key":"238_CR13","doi-asserted-by":"publisher","first-page":"2763","DOI":"10.3390\/healthcare11202763","volume":"11","author":"MF Almufareh","year":"2023","unstructured":"Almufareh MF, Tehsin S, Humayun M et al (2023) Artificial cognition for detection of mental disability: a vision transformer approach for Alzheimer\u2019s disease. Healthcare 11:2763","journal-title":"Healthcare"},{"key":"238_CR14","doi-asserted-by":"publisher","DOI":"10.1109\/ICECONF57129.2023.10084260","author":"P Sherwani","year":"2023","unstructured":"Sherwani P, Nandhakumar P, Srivastava P et al (2023) Comparative analysis of Alzheimer\u2019s disease detection via MRI scans using convolutional neural network and vision transformer. Proc ICECONF. https:\/\/doi.org\/10.1109\/ICECONF57129.2023.10084260","journal-title":"Proc ICECONF"},{"key":"238_CR15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.17239","author":"H Touvron","year":"2021","unstructured":"Touvron H, Cord M, Sablayrolles A, Synnaeve G et al (2021) Going deeper with image transformers. Proc ICCV. https:\/\/doi.org\/10.48550\/arXiv.2103.17239","journal-title":"Proc ICCV"},{"issue":"5","key":"238_CR16","doi-asserted-by":"publisher","first-page":"1218","DOI":"10.3390\/electronics12051218","volume":"12","author":"M Odusami","year":"2023","unstructured":"Odusami M, Maskeli\u016bnas R, Dama\u0161evi\u010dius R (2023) Pixel-level fusion approach with vision transformer for early detection of Alzheimer\u2019s disease. Electronics 12(5):1218","journal-title":"Electronics"},{"issue":"1145\/3529190","key":"238_CR17","first-page":"3534754","volume":"10","author":"Y Lyu","year":"2022","unstructured":"Lyu Y, Yu X, Zhu D et al (2022) Classification of Alzheimer\u2019s disease via vision transformer: classification of Alzheimer\u2019s disease via vision transformer. Proc ICPETRA 10(1145\/3529190):3534754","journal-title":"Proc ICPETRA"},{"issue":"2","key":"238_CR18","doi-asserted-by":"publisher","first-page":"260","DOI":"10.3390\/brainsci13020260","volume":"13","author":"S Sarraf","year":"2023","unstructured":"Sarraf S, Sarraf A, DeSouza DD, Anderson JA, Kabia M, Initiative ADN (2023) Ovitad: optimized vision transformer to predict various stages of Alzheimer\u2019s disease using resting-state FMRI and structural MRI data. Brain ScI 13(2):260","journal-title":"Brain ScI"},{"issue":"16","key":"238_CR19","doi-asserted-by":"publisher","first-page":"9310","DOI":"10.3390\/app13169310","volume":"13","author":"Y Huang","year":"2023","unstructured":"Huang Y, Li W (2023) Resizer SWIN transformer-based classification using SMRI for Alzheimer\u2019s disease. Appl Sci 13(16):9310","journal-title":"Appl Sci"},{"issue":"6","key":"238_CR20","doi-asserted-by":"publisher","first-page":"3453","DOI":"10.3390\/app13063453","volume":"13","author":"H Shin","year":"2023","unstructured":"Shin H, Jeon S, Seol Y, Kim S, Kang D (2023) Vision transformer approach for classification of Alzheimer\u2019s disease using 18F-Florbetaben brain images. Appl Sci 13(6):3453","journal-title":"Appl Sci"},{"key":"238_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2023.104229","volume":"143","author":"R Kadri","year":"2023","unstructured":"Kadri R, Bouaziz B, Tmar M, Gargouri F (2023) Efficient multimodel method based on transformers and coatnet for Alzheimer\u2019s diagnosis. Digital Signal Process 143:104229","journal-title":"Digital Signal Process"},{"key":"238_CR22","doi-asserted-by":"publisher","first-page":"124962","DOI":"10.1109\/ACCESS.2023.3330442","volume":"11","author":"L Nanni","year":"2023","unstructured":"Nanni L, Loreggia A, Barcellona L, Ghidoni S (2023) Building ensemble of deep networks: convolutional networks and transformers. IEEE Access 11:124962\u2013124974. https:\/\/doi.org\/10.1109\/ACCESS.2023.3330442","journal-title":"IEEE Access"},{"key":"238_CR23","doi-asserted-by":"crossref","unstructured":"Chen W, Sun F, Luo Y, Wang X (2023) Ensemble model for predicting Alzheimer\u2019s disease and disease stages with CNN and transformer models. In: Proceedings of the 2023 2nd International Conference on Algorithms, Data Mining, and Information Technology. ADMIT \u201923, pp. 46\u201351. Association for Computing Machinery, New York, NY, USA. 10.1145\/3625403.3625414","DOI":"10.1145\/3625403.3625414"},{"key":"238_CR24","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI52829.2022.9761584","author":"X Xing","year":"2022","unstructured":"Xing X, Liang G, Zhang Y, Khanal S, Lin A-L, Jacobs N (2022) Advit: vision transformer on multi-modality pet images for Alzheimer disease diagnosis. IEEE Int Sympos Biomed Imag (ISBI). https:\/\/doi.org\/10.1109\/ISBI52829.2022.9761584","journal-title":"IEEE Int Sympos Biomed Imag (ISBI)"},{"key":"238_CR25","first-page":"8821","volume":"139","author":"A Ramesh","year":"2021","unstructured":"Ramesh A, Pavlov M, Goh G et al (2021) Zero-shot text-to-image generation. Proc ICML 139:8821\u20138831","journal-title":"Proc ICML"},{"issue":"3","key":"238_CR26","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/MCAS.2006.1688199","volume":"6","author":"R Polikar","year":"2006","unstructured":"Polikar R (2006) Ensemble based systems in decision making. IEEE Circuits Syst Mag 6(3):21\u201345","journal-title":"IEEE Circuits Syst Mag"},{"key":"238_CR27","unstructured":"Hugging Face Datasets. 2022. https:\/\/huggingface.co\/datasets. Accessed 08 Apr 2024"},{"issue":"1","key":"238_CR28","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1002\/mrm.1910150117","volume":"15","author":"J Mugler","year":"1990","unstructured":"Mugler J, Brookeman J (1990) Three-dimensional magnetization-prepared rapid gradient-echo imaging. Magn Reson Med 15(1):152\u2013157","journal-title":"Magn Reson Med"},{"issue":"16","key":"238_CR29","doi-asserted-by":"publisher","first-page":"10415","DOI":"10.1007\/s00521-021-05799-w","volume":"33","author":"Y AbdulAzeem","year":"2021","unstructured":"AbdulAzeem Y, Bahgat WM, Badawy M (2021) A CNN based framework for classification of Alzheimer\u2019s disease. Neural Comput Appl 33(16):10415\u201310428","journal-title":"Neural Comput Appl"},{"issue":"5","key":"238_CR30","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1007\/s12559-021-09946-2","volume":"14","author":"HA Helaly","year":"2022","unstructured":"Helaly HA, Badawy M, Haikal AY (2022) Deep learning approach for early detection of Alzheimer\u2019s disease. Cognit Comput 14(5):1711\u20131727","journal-title":"Cognit Comput"},{"key":"238_CR31","doi-asserted-by":"publisher","first-page":"16376","DOI":"10.1109\/ACCESS.2023.3244952","volume":"11","author":"FJM Shamrat","year":"2023","unstructured":"Shamrat FJM, Akter S, Azam S, Karim A, Ghosh P, Tasnim Z, Hasib KM, De Boer F, Ahmed K (2023) Alzheimernet: an effective deep learning based proposition for Alzheimer\u2019s disease stages classification from functional brain changes in magnetic resonance images. IEEE Access 11:16376\u201316395","journal-title":"IEEE Access"},{"key":"238_CR32","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785","author":"T Chen","year":"2016","unstructured":"Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. Proc (ICKDDM). https:\/\/doi.org\/10.1145\/2939672.2939785","journal-title":"Proc (ICKDDM)"},{"issue":"2","key":"238_CR33","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/S0019-9958(70)90081-1","volume":"16","author":"EA Patrick","year":"1970","unstructured":"Patrick EA, Fischer FP III (1970) A generalized k-nearest neighbor rule. Inf Control 16(2):128\u2013152","journal-title":"Inf Control"},{"key":"238_CR34","doi-asserted-by":"publisher","DOI":"10.1007\/b95439","volume-title":"Support vector machines: theory and applications","author":"L Wang","year":"2005","unstructured":"Wang L (2005) Support vector machines: theory and applications, vol 177. Springer, Berlin"},{"key":"238_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.dajour.2022.100071","volume":"3","author":"M Bansal","year":"2022","unstructured":"Bansal M, Goyal A et al (2022) A comparative analysis of KNN, Genetic, SVM, Decision Tree, and LSTM algorithms in machine learning. Decis Anal J 3:100071","journal-title":"Decis Anal J"},{"issue":"1","key":"238_CR36","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s40708-024-00222-1","volume":"11","author":"V Vimbi","year":"2024","unstructured":"Vimbi V, Shaffi N, Mahmud M (2024) Interpreting artificial intelligence models: a systematic review on the application of LIME and SHAP in Alzheimer\u2019s disease detection. Brain Inform 11(1):10","journal-title":"Brain Inform"},{"issue":"1","key":"238_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12559-023-10192-x","volume":"16","author":"V Viswan","year":"2024","unstructured":"Viswan V, Shaffi N, Mahmud M, Subramanian K, Hajamohideen F (2024) Explainable artificial intelligence in Aheimer\u2019s disease classification: a systematic review. Cognit Comput 16(1):1\u201344","journal-title":"Cognit Comput"}],"container-title":["Brain Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40708-024-00238-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40708-024-00238-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40708-024-00238-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T17:03:41Z","timestamp":1727975021000},"score":1,"resource":{"primary":{"URL":"https:\/\/braininformatics.springeropen.com\/articles\/10.1186\/s40708-024-00238-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,3]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["238"],"URL":"https:\/\/doi.org\/10.1186\/s40708-024-00238-7","relation":{},"ISSN":["2198-4018","2198-4026"],"issn-type":[{"value":"2198-4018","type":"print"},{"value":"2198-4026","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,3]]},"assertion":[{"value":"23 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This work is based on secondary datasets available online. Hence ethical approval was not necessary.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors have seen and approved the current version of the paper.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Mufti Mahmud is an editorial board member of the Brain Informatics journal and was not involved in the editorial review or the decision to publish this article. All authors declare that there are no other Competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"25"}}