{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T21:50:40Z","timestamp":1792273840700,"version":"4.4.0"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,10]],"date-time":"2025-08-10T00:00:00Z","timestamp":1754784000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,10]],"date-time":"2025-08-10T00:00:00Z","timestamp":1754784000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Alzheimer\u2019s disease is a progressive neurodegenerative disorder marked by cognitive decline, memory loss, and behavioral changes. Early diagnosis, particularly identifying Early Mild Cognitive Impairment (EMCI), is vital for managing the disease and improving patient outcomes. Detecting EMCI is challenging due to the subtle structural changes in the brain, making precise slice selection from MRI scans essential for accurate diagnosis. In this context, the careful selection of specific MRI slices that provide distinct anatomical details significantly enhances the ability to identify these early changes. The chief novelty of the study is that instead of selecting all slices, an approach for identifying the important slices is developed. The ADNI-3 dataset was used as the dataset when running the models for early detection of Alzheimer\u2019s disease. Satisfactory results have been obtained by classifying with deep learning models, vision transformers (ViT) and by adding new structures to them, together with the model proposal. In the results obtained, while an accuracy of 99.45% was achieved with EfficientNetB2\u2009+\u2009FPN in AD vs. LMCI classification from the slices selected with SSIM, an accuracy of 99.19% was achieved in AD vs. EMCI classification, in fact, the study significantly advances early detection by demonstrating improved diagnostic accuracy of the disease at the EMCI stage. The results obtained with these methods emphasize the importance of developing deep learning models with slice selection integrated with the Vision Transformers architecture. Focusing on accurate slice selection enables early detection of Alzheimer\u2019s at the EMCI stage, allowing for timely interventions and preventive measures before the disease progresses to more advanced stages. This approach not only facilitates early and accurate diagnosis, but also lays the groundwork for timely intervention and treatment, offering hope for better patient outcomes in Alzheimer\u2019s disease. The study is finally evaluated by a statistical significance test.<\/jats:p>","DOI":"10.1038\/s41598-025-14476-0","type":"journal-article","created":{"date-parts":[[2025,8,10]],"date-time":"2025-08-10T09:22:38Z","timestamp":1754817758000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Improving early detection of Alzheimer\u2019s disease through MRI slice selection and deep learning techniques"],"prefix":"10.1038","volume":"15","author":[{"given":"Beg\u00fcm","family":"\u015eener","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koray","family":"A\u00e7\u0131c\u0131","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emre","family":"S\u00fcmer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,10]]},"reference":[{"issue":"3","key":"14476_CR1","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1016\/j.jalz.2010.03.006","volume":"6","author":"PS Aisen","year":"2010","unstructured":"Aisen, P. S. et al. Clinical core of the alzheimer\u2019s disease neuroimaging initiative: progress and plans. Alzheimer\u2019s Dement. 6 (3), 239\u2013246. https:\/\/doi.org\/10.1016\/j.jalz.2010.03.006 (2010).","journal-title":"Alzheimer\u2019s Dement."},{"issue":"8","key":"14476_CR2","doi-asserted-by":"publisher","first-page":"2118","DOI":"10.1111\/ejn.16261","volume":"59","author":"H Ma","year":"2024","unstructured":"Ma, H. et al. Classification of alzheimer\u2019s disease: application of a transfer learning deep Q-network method. Eur. J. Neurosci. 59 (8), 2118\u20132127. https:\/\/doi.org\/10.1111\/ejn.16261 (2024).","journal-title":"Eur. J. Neurosci."},{"issue":"4","key":"14476_CR3","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/j.jalz.2018.02.018","volume":"14","author":"CR Jack","year":"2018","unstructured":"Jack, C. R. et al. NIA-AA research framework: toward a biological definition of alzheimer\u2019s disease. Alzheimer\u2019s Dement. 14 (4), 535\u2013562. https:\/\/doi.org\/10.1016\/j.jalz.2018.02.018 (2018).","journal-title":"Alzheimer\u2019s Dement."},{"key":"14476_CR4","doi-asserted-by":"publisher","unstructured":"Cholli, N. G. & Naveen, N. Enhancing Early Alzheimer\u2019s Disease Detection: Leveraging Pre-trained. Networks Transf. Learn. 16 (1). https:\/\/doi.org\/10.5815\/ijisa.2024.01.05 (2024).","DOI":"10.5815\/ijisa.2024.01.05"},{"key":"14476_CR5","doi-asserted-by":"publisher","unstructured":"Duan, Y., Wang, R. & Li, Y. April. Aux-ViT: Classification of Alzheimer\u2019s Disease from MRI based on Vision Transformer with Auxiliary Branch. In 2023 5th International Conference on Communications, Information System and Computer Engineering (CISCE), pp, 382\u2013386. IEEE. (2023). https:\/\/doi.org\/10.1109\/CISCE58541.2023.10142358","DOI":"10.1109\/CISCE58541.2023.10142358"},{"key":"14476_CR6","first-page":"313","volume":"14","author":"R Kadri","year":"2022","unstructured":"Kadri, R., Bouaziz, B., Tmar, M. & Gargouri, F. Multimodal deep learning based on the combination of EfficientNetV2 and ViT for alzheimer\u2019s disease early diagnosis enhanced by SAGAN data augmentation. Int. J. Comput. Inf. Syst. Ind. Manag Appl. 14, 313\u2013325 (2022). https:\/\/www.researchgate.net\/publication\/362468328","journal-title":"Int. J. Comput. Inf. Syst. Ind. Manag Appl."},{"key":"14476_CR7","doi-asserted-by":"publisher","unstructured":"Liu, L. et al. TriFormer: A Multi-modal Transformer Framework For Mild Cognitive Impairment Conversion Prediction. In 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp. 1\u20134. IEEE. (2023). https:\/\/doi.org\/10.1109\/ISBI53787.2023.10230709","DOI":"10.1109\/ISBI53787.2023.10230709"},{"key":"14476_CR8","doi-asserted-by":"publisher","unstructured":"Chen, Q., Fu, Q., Bai, H. & Hong, Y. Longformer: Longitudinal Transformer for Alzheimer\u2019s Disease Classification With Structural MRIs. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp, 3575\u20133584. (2024). https:\/\/doi.org\/10.1109\/WACV57701.2024.00354","DOI":"10.1109\/WACV57701.2024.00354"},{"key":"14476_CR9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.01074","author":"Q Chen","year":"2024","unstructured":"Chen, Q., Hu, X., Wang, Z. & Hong, Y. AliFuse: aligning and fusing Multi-modal medical data for Computer-Aided diagnosis. ArXiv Preprint arXiv:2401 01074. https:\/\/doi.org\/10.48550\/arXiv.2401.01074 (2024).","journal-title":"ArXiv Preprint arXiv:2401 01074"},{"key":"14476_CR10","doi-asserted-by":"publisher","first-page":"115974","DOI":"10.1109\/ACCESS.2022.3218621","volume":"10","author":"A Gamal","year":"2022","unstructured":"Gamal, A., Elattar, M. & Selim, S. Automatic early diagnosis of alzheimer\u2019s disease using 3D deep ensemble approach. IEEE Access. 10, 115974\u2013115987. https:\/\/doi.org\/10.1109\/ACCESS.2022.3218621 (2022).","journal-title":"IEEE Access."},{"key":"14476_CR11","doi-asserted-by":"publisher","first-page":"e1877","DOI":"10.7717\/peerj-cs.1877","volume":"10","author":"B \u015eener","year":"2024","unstructured":"\u015eener, B., Acici, K. & S\u00fcmer, E. Categorization of alzheimer\u2019s disease stages using deep learning approaches with mcnemar\u2019s test. PeerJ Comput. Sci. 10, e1877. https:\/\/doi.org\/10.7717\/peerj-cs.1877 (2024).","journal-title":"PeerJ Comput. Sci."},{"issue":"1","key":"14476_CR12","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.jeconom.2022.04.007","volume":"235","author":"X Zhang","year":"2023","unstructured":"Zhang, X. & Liu, C. A. Model averaging prediction by K-fold cross-validation. J. Econ. 235 (1), 280\u2013301. https:\/\/doi.org\/10.1016\/j.jeconom.2022.04.007 (2023).","journal-title":"J. Econ."},{"issue":"12","key":"14476_CR13","doi-asserted-by":"publisher","first-page":"3376","DOI":"10.1111\/ejn.16361","volume":"59","author":"R Morais-Ribeiro","year":"2024","unstructured":"Morais-Ribeiro, R., Almeida, F. C., Coelho, A., Oliveira, T. G. & Alzheimer\u2019s Disease Neuroimaging Initiative. Differential atrophy along the longitudinal hippocampal axis in alzheimer\u2019s disease. Eur. J. Neurosci. 59 (12), 3376\u20133388. https:\/\/doi.org\/10.1111\/ejn.16361 (2024).","journal-title":"Eur. J. Neurosci."},{"key":"14476_CR14","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s11760-009-0144-1","volume":"5","author":"R Dosselmann","year":"2011","unstructured":"Dosselmann, R. & Yang, X. D. A comprehensive assessment of the structural similarity index. Signal. Image Video Process. 5, 81\u201391. https:\/\/doi.org\/10.1007\/s11760-009-0144-1 (2011).","journal-title":"Signal. Image Video Process."},{"issue":"4","key":"14476_CR15","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1007\/s13246-022-01165-9","volume":"45","author":"L Houria","year":"2022","unstructured":"Houria, L., Belkhamsa, N., Cherfa, A. & Cherfa, Y. Multi-modality MRI for alzheimer\u2019s disease detection using deep learning. Phys. Eng. Sci. Med. 45 (4), 1043\u20131053. https:\/\/doi.org\/10.1007\/s13246-022-01165-9 (2022).","journal-title":"Phys. Eng. Sci. Med."},{"issue":"4","key":"14476_CR16","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A. C., Sheikh, H. R. & Simoncelli, E. P. Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13 (4), 600\u2013612. https:\/\/doi.org\/10.1109\/TIP.2003.819861 (2004).","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"14476_CR17","doi-asserted-by":"publisher","first-page":"2354","DOI":"10.1111\/ejn.14129","volume":"48","author":"AM Penttinen","year":"2018","unstructured":"Penttinen, A. M. et al. Implementation of deep neural networks to count dopamine neurons in substantia Nigra. Eur. J. Neurosci. 48 (6), 2354\u20132361. https:\/\/doi.org\/10.1111\/ejn.14129 (2018).","journal-title":"Eur. J. Neurosci."},{"key":"14476_CR18","doi-asserted-by":"crossref","unstructured":"Zhou, H., Lei, H., Zhao, H., Huang, K., Wang, Y., Hong, R., \u2026 Li, F. 2024. Development and validation of a multi-parameter nomogram for venous thromboembolism in gastric cancer patients: a retrospective analysis. PeerJ, 12, e17527. https:\/\/doi.org\/10.7717\/peerj.17527.","DOI":"10.7717\/peerj.17527"},{"key":"14476_CR19","doi-asserted-by":"publisher","unstructured":"Bostanci, B. & Bostanci, E. An evaluation of classification algorithms using MC nemar\u2019s test. Adv. Intell. Syst. Comput. 15\u201326. https:\/\/doi.org\/10.1007\/978-81-322-1038-2_2 (2012).","DOI":"10.1007\/978-81-322-1038-2_2"},{"key":"14476_CR20","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.patrec.2021.01.013","volume":"144","author":"D Yun","year":"2021","unstructured":"Yun, D., Ryu, J. & Lim, J. Dual aggregated feature pyramid network for multi label classification. Pattern Recognit. Lett. 144, 75\u201381. https:\/\/doi.org\/10.1016\/j.patrec.2021.01.013 (2021).","journal-title":"Pattern Recognit. Lett."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14476-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14476-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14476-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,10]],"date-time":"2025-08-10T09:22:39Z","timestamp":1754817759000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14476-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,10]]},"references-count":20,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["14476"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-14476-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-6138954\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,10]]},"assertion":[{"value":"2 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"29260"}}