{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T06:06:33Z","timestamp":1782281193166,"version":"3.54.5"},"reference-count":40,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:00:00Z","timestamp":1782259200000},"content-version":"vor","delay-in-days":23,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:00:00Z","timestamp":1782259200000},"content-version":"tdm","delay-in-days":23,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Alzheimer\u2019s disease (AD) is a progressive neurodegenerative disorder for which accurate and early diagnosis remains difficult. Structural magnetic resonance imaging is widely used to assess disease-related brain changes, but automated classification methods are frequently affected by class imbalance, inter-subject anatomical variability, and orientation-dependent structural patterns. This study addresses three recognised limitations of existing automated systems, namely orientation-blind fusion, fixed expert weighting, and the absence of subject-adaptive plane relevance estimation, by proposing a plane-aware multi-stage mixture-of-experts framework, designated PAM-MoE-AD, for T1-weighted structural MRI. Axial, coronal, and sagittal 2.5D slice stacks were constructed through a content-aware slice-selection procedure, and each plane was modelled with an independent Swin Transformer V2 encoder. Training proceeded through three sequential stages comprising plane-specific representation learning, supervised refinement of plane-specific experts, and mixture-of-experts fusion governed by a learned gating network. Experiments were conducted on subject-level data splits derived from the AD Neuroimaging Initiative. Under five-fold subject-level cross-validation the framework achieved a mean accuracy of 97.21% and a mean balanced accuracy (BACC) of 93.14%, with 95% confidence intervals from 96.71% to 97.71% and from 92.47% to 93.81% respectively. External evaluation on a 124-scan AIBL subset, performed without fine-tuning, retained an accuracy of 93.52% and a BACC of 91.31%. The framework outperformed three same-split baselines comprising a three-dimensional (3D) ResNet-18, a 3D Swin Transformer, and a multi-plane CNN. Quantitative Grad-CAM analysis grounded model decisions in established atrophic regions including the hippocampus and entorhinal cortex.<\/jats:p>","DOI":"10.1088\/2057-1976\/ae7c0a","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T22:48:24Z","timestamp":1781218104000},"page":"035092","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PAM-MoE-AD: A plane-aware multi-stage mixture-of-experts framework for Alzheimer\u2019s disease classification from sMRI"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0603-4394","authenticated-orcid":true,"given":"Hemant","family":"Kumar","sequence":"first","affiliation":[{"name":"Harcourt Butler Technical University"},{"name":"Chandigarh University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5768-5894","authenticated-orcid":true,"given":"Rashi","family":"Agarwal","sequence":"additional","affiliation":[{"name":"Harcourt Butler Technical University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,6,24]]},"reference":[{"key":"bpexae7c0abib1","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1016\/j.jalz.2010.03.007","type":"journal-article","article-title":"The alzheimer\u2019s disease neuroimaging initiative: progress report and future plans","volume":"6","author":"Weiner","year":"2010","journal-title":"Alzheimers Dementia"},{"key":"bpexae7c0abib2","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1503\/jpn.180016","type":"journal-article","article-title":"An artificial neural network model for clinical score prediction in Alzheimer disease using structural neuroimaging measures","volume":"44","author":"Bhagwat","year":"2019","journal-title":"J. Psychiatry Neurosci."},{"key":"bpexae7c0abib3","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1111\/ene.15556","type":"journal-article","article-title":"Magnetic resonance imaging locus coeruleus abnormality in amnestic mild cognitive impairment is associated with future progression to dementia","volume":"30","author":"Galgani","year":"2022","journal-title":"Eur. J. Neurol."},{"key":"bpexae7c0abib4","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1186\/s13195-021-00900-w","type":"journal-article","article-title":"Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer\u2019s disease dementia: a systematic review","volume":"13","author":"Grueso","year":"2021","journal-title":"Alzheimers Res. Ther."},{"key":"bpexae7c0abib5","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1007\/s11357-025-01626-5","type":"journal-article","article-title":"Predicting the progression of MCI and Alzheimer\u2019s disease on structural brain integrity and other features with machine learning","volume":"48","author":"ADNI","year":"2025","journal-title":"GeroScience"},{"key":"bpexae7c0abib6","doi-asserted-by":"publisher","first-page":"8410","DOI":"10.1038\/s41598-025-92577-6","type":"journal-article","article-title":"A comprehensive interpretable machine learning framework for mild cognitive impairment and Alzheimer\u2019s disease diagnosis","volume":"15","author":"Vlontzou","year":"2025","journal-title":"Sci. Rep."},{"key":"bpexae7c0abib7","doi-asserted-by":"publisher","DOI":"10.1101\/456277","type":"preprint","article-title":"Deep learning on MRI affirms the prominence of the hippocampal formation in Alzheimer\u2019s disease classification","author":"Feng","year":"2018"},{"key":"bpexae7c0abib8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0331870","type":"journal-article","article-title":"CQ-CNN: a lightweight hybrid classical\u2013quantum CNN for AD detection using 3D structural brain MRI","volume":"20","author":"Islam","year":"2025","journal-title":"PLoS One"},{"key":"bpexae7c0abib9","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.8.2.024503","type":"journal-article","article-title":"Convolutional neural networks for Alzheimer\u2019s disease detection on MRI images","volume":"8","author":"ADNI","year":"2021","journal-title":"Proc. SPIE"},{"key":"bpexae7c0abib10","doi-asserted-by":"publisher","first-page":"47","DOI":"10.3233\/JAD-200830","type":"journal-article","article-title":"Construction of MRI-based Alzheimer\u2019s disease score based on an efficient 3D CNN","volume":"79","author":"Yee","year":"2020","journal-title":"JAD"},{"key":"bpexae7c0abib11","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2022.871706","type":"journal-article","article-title":"Alzheimer\u2019s disease diagnosis with brain structural MRI using multiview-slice attention and 3D CNN","volume":"14","author":"Chen","year":"2022","journal-title":"Front. Aging Neurosci."},{"key":"bpexae7c0abib12","doi-asserted-by":"publisher","first-page":"2997","DOI":"10.3390\/diagnostics15232997","type":"journal-article","article-title":"ConvNeXt-driven detection of Alzheimer\u2019s disease: a benchmark study across anatomical planes","volume":"15","author":"Basereh","year":"2025","journal-title":"Diagnostics"},{"key":"bpexae7c0abib13","doi-asserted-by":"publisher","first-page":"20686","DOI":"10.1109\/CVPR52688.2022.02006","type":"conference-proceedings","article-title":"M3T: three-dimensional medical image classifier using multi-plane and multi-slice transformer.","author":"Jang","year":"2022"},{"key":"bpexae7c0abib14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929","type":"conference-proceedings","article-title":"An image is worth 16\u00d716 words: transformers for image recognition at scale.","author":"Dosovitskiy","year":"2020"},{"key":"bpexae7c0abib15","doi-asserted-by":"publisher","first-page":"9992","DOI":"10.1109\/ICCV48922.2021.00986","type":"conference-proceedings","article-title":"Swin Transformer: hierarchical vision transformer using shifted windows.","author":"Liu","year":"2021"},{"key":"bpexae7c0abib16","article-title":"Outrageously large neural networks: the sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","type":"conference-proceedings"},{"key":"bpexae7c0abib17","doi-asserted-by":"publisher","first-page":"612","DOI":"10.3390\/brainsci15060612","type":"journal-article","article-title":"Hybrid deep learning architecture with adaptive feature fusion for multi-stage Alzheimer\u2019s disease classification","volume":"15","author":"Muhammad","year":"2025","journal-title":"Brain Sci."},{"key":"bpexae7c0abib18","doi-asserted-by":"publisher","first-page":"329","DOI":"10.22266\/ijies2022.0228.30","type":"journal-article","article-title":"Multiplane convolutional neural network (Mp-CNN) for Alzheimer\u2019s disease classification","volume":"15","author":"Very","year":"2022","journal-title":"Int. J. Intell. Eng. Syst."},{"key":"bpexae7c0abib19","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1109\/WI-IAT59888.2023.00082","type":"conference-proceedings","article-title":"Multi-planar MRI-based classification of Alzheimer\u2019s disease using tree-based machine learning algorithms","author":"Shaffi","year":"2023"},{"key":"bpexae7c0abib20","article-title":"An interpretable multi-plane fusion framework with Kolmogorov\u2013Arnold network guided attention enhancement for Alzheimer\u2019s disease diagnosis","author":"Yang","year":"2025","type":"preprint"},{"key":"bpexae7c0abib21","doi-asserted-by":"publisher","first-page":"21663","DOI":"10.1609\/aaai.v40i26.39316","type":"journal-article","article-title":"A stage-aware mixture of experts framework for neurodegenerative disease progression modelling","volume":"40","author":"He","year":"2025","journal-title":"Proc. of the AAAI Conf. on Artificial Intelligence"},{"key":"bpexae7c0abib22","doi-asserted-by":"publisher","first-page":"26","DOI":"10.9781\/ijimai.2021.04.005","type":"journal-article","article-title":"Alzheimer disease detection techniques and methods: a review","volume":"6","author":"Afzal","year":"2021","journal-title":"IJIMAI"},{"key":"bpexae7c0abib23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2014\/862307","type":"journal-article","article-title":"An ensemble-of-classifiers based approach for early diagnosis of Alzheimer\u2019s disease","volume":"2014","author":"Farhan","year":"2014","journal-title":"Comput. Math. Methods Med."},{"key":"bpexae7c0abib24","doi-asserted-by":"publisher","first-page":"7661","DOI":"10.3390\/s22197661","type":"journal-article","article-title":"Voting ensemble approach for enhancing Alzheimer\u2019s disease classification","volume":"22","author":"Chatterjee","year":"2022","journal-title":"Sensors"},{"key":"bpexae7c0abib25","doi-asserted-by":"publisher","first-page":"95","DOI":"10.7717\/peerj-cs.1177","type":"journal-article","article-title":"Alzheimer\u2019s disease diagnosis and classification using deep learning techniques","volume":"3","author":"Saleh","year":"2022","journal-title":"Peer J Computer Science"},{"key":"bpexae7c0abib26","doi-asserted-by":"publisher","first-page":"332","DOI":"10.52465\/joscex.v5i4.493","type":"journal-article","article-title":"Eye disease classification using deep learning CNNs","volume":"5","author":"Rachmawanto","year":"2024","journal-title":"J. Soft Comput. Explor."},{"key":"bpexae7c0abib27","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2020.576194","type":"journal-article","article-title":"Comparison of transfer learning and conventional machine learning applied to structural brain MRI","volume":"11","author":"Nanni","year":"2020","journal-title":"Front. Neurol."},{"key":"bpexae7c0abib28","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-38240-4","type":"journal-article","article-title":"Deep joint learning of pathological region localization and Alzheimer\u2019s disease diagnosis","volume":"13","author":"Park","year":"2023","journal-title":"Sci. Rep."},{"key":"bpexae7c0abib29","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-981-97-2089-7_16","type":"book","article-title":"ViT-ALZ: vision transformer with deep neural network for Alzheimer\u2019s disease detection","volume":"Vol 971","author":"Kumar","year":"2024"},{"key":"bpexae7c0abib30","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/ICIPCN63822.2024.00027","type":"conference-proceedings","article-title":"Ensemble Deep Neural Networks: An assessment for early Alzheimer\u2019s Disease diagnosis with structural MRI","author":"Gawade","year":"2024"},{"key":"bpexae7c0abib31","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109438","type":"journal-article","article-title":"Multi-scale multimodal deep learning framework for Alzheimer\u2019s disease diagnosis","volume":"184","author":"Abdelaziz","year":"2025","journal-title":"Computers in Biology and Medicine"},{"key":"bpexae7c0abib32","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1002\/jmri.21049","type":"journal-article","article-title":"The Alzheimer\u2019s disease neuroimaging initiative (ADNI): MRI methods","volume":"27","author":"Jack","year":"2008","journal-title":"Magn. Reson. Imaging"},{"key":"bpexae7c0abib33","doi-asserted-by":"publisher","first-page":"4952","DOI":"10.1002\/hbm.24750","type":"journal-article","article-title":"Automated brain extraction of multisequence MRI using artificial neural networks","volume":"40","author":"Isensee","year":"2019","journal-title":"Hum. Brain Mapp."},{"key":"bpexae7c0abib34","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","type":"journal-article","article-title":"N4ITK: improved N3 bias correction","volume":"29","author":"Tustison","year":"2010","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae7c0abib35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2511.14021","type":"preprint","article-title":"MRI plane orientation detection using a context-aware 2.5D model","author":"Kim","year":"2025"},{"key":"bpexae7c0abib36","doi-asserted-by":"publisher","first-page":"11999","DOI":"10.1109\/CVPR52688.2022.01170.","type":"conference-proceedings","article-title":"Swin Transformer V2: scaling up capacity and resolution","author":"Liu","year":"2022"},{"key":"bpexae7c0abib37","first-page":"148","type":"conference-proceedings","article-title":"VICReg: variance-invariance-covariance regularization for self-supervised learning","volume":"91","author":"Bardes","year":"2022"},{"key":"bpexae7c0abib38","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","type":"journal-article","article-title":"Adaptive mixtures of local experts","volume":"3","author":"Jacobs","year":"1991","journal-title":"Neural Comput."},{"key":"bpexae7c0abib39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103664","type":"journal-article","article-title":"Mixture of experts (MoE): a big data perspective","volume":"127","author":"Gan","year":"2026","journal-title":"Inf. Fusion"},{"key":"bpexae7c0abib40","author":"","journal-title":"Laboratory of Neuro Imaging (LONI), University of Southern California","type":"journal-article"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7c0a","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7c0a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7c0a","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7c0a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7c0a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7c0a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7c0a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7c0a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:36:23Z","timestamp":1782279383000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7c0a"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":40,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,6,24]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae7c0a","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,1]]},"assertion":[{"value":"PAM-MoE-AD: A plane-aware multi-stage mixture-of-experts framework for Alzheimer\u2019s disease classification from sMRI","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-04-01","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-06-11","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-06-24","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}