{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T06:15:07Z","timestamp":1783318507257,"version":"3.54.6"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T00:00:00Z","timestamp":1783296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by localized cortical atrophy and large-scale disruption of brain connectivity. Although deep learning (DL) methods have shown promise for neuroimaging-based diagnosis, many approaches fail to jointly capture localized structural changes and global network-level degeneration.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose a topology-aware hybrid DL framework for AD classification from structural MRI. The model integrates (1) a 3D convolutional neural network (CNN) to extract volumetric morphometric features, (2) a dynamic graph attention network (GAT) to infer patient-specific structural connectivity without predefined atlases, and (3) a topology-biased Vision Transformer (Topo-ViT) that incorporates this connectivity into global attention. The framework is trained under strict subject-level data segregation and optimized using focal loss with an AUC-driven strategy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Evaluated on a structural MRI dataset derived from the OASIS cohort, the proposed model achieved a test ROC-AUC of 0.857, with an overall accuracy of 85% and high sensitivity in detecting demented cases. Ablation studies show that topology-guided attention improves performance over CNN and hybrid baselines. Additional analyses reveal stable connectivity patterns and well-separated latent representations<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The results demonstrate that integrating topology-aware mechanisms enables more coherent modeling of AD as a network-level disorder. The proposed framework captures both local and global structural patterns, offering improved diagnostic reliability. Further validation on larger datasets is required for clinical deployment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fncom.2026.1834764","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:36:51Z","timestamp":1783316211000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Topology-aware hybrid graph-transformer network for Alzheimer's disease diagnosis from structural magnetic resonance imaging"],"prefix":"10.3389","volume":"20","author":[{"given":"Nadhmi A.","family":"Gazem","sequence":"first","affiliation":[{"name":"Department of Information Systems","place":["College of Business Administration-Yanbu, Taibah University, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shahid","family":"Latif","sequence":"additional","affiliation":[{"name":"School of Computing and Creative Technologies, University of the West of England","place":["Bristol, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wad","family":"Ghaban","sequence":"additional","affiliation":[{"name":"Applied College, University of Tabuk","place":["Tabuk, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sultan Noman","family":"Qasem","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU)","place":["Riyadh, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1623141","DOI":"10.3389\/fnins.2025.1623141","article-title":"Graph neural networks in alzheimer's disease diagnosis: a review of unimodal and multimodal advances","volume":"19","author":"Ali","year":"2025","journal-title":"Front. Neurosci"},{"key":"B2","doi-asserted-by":"publisher","first-page":"69482","DOI":"10.1109\/ACCESS.2026.3690047","article-title":"ClinPatch-AD: Token-level fusion of 3D MRI patch transformers and clinical scores for subject-wise Alzheimer's disease screening","volume":"14","author":"Bansal","year":"2026","journal-title":"IEEE Access"},{"key":"B3","doi-asserted-by":"publisher","first-page":"e57","DOI":"10.1002\/brx2.57","article-title":"Comprehensive review of transformer-based models in neuroscience, neurology, and psychiatry","volume":"2","author":"Cong","year":"2024","journal-title":"Brain-X"},{"key":"B4","doi-asserted-by":"publisher","first-page":"3835","DOI":"10.1080\/03772063.2023.2206367","article-title":"Square static-deep hyper optimization and genetic meta-learning approach for disease classification","volume":"70","author":"Dhivya","year":"2024","journal-title":"IETE J. Res"},{"key":"B5","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1109\/ICIMCIS68501.2025.11326972","article-title":"\u201cResNet-50 transfer learning for early detection of Alzheimer's disease on OASIS-1 MRI with explainable ai interpretability analysis using Grad-CAM,\u201d","volume-title":"2025 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)","author":"Gunawan","year":"2025"},{"key":"B6","doi-asserted-by":"publisher","first-page":"5815","DOI":"10.1038\/s41598-025-85703-x","article-title":"Stacked cnn-based multichannel attention networks for alzheimer disease detection","volume":"15","author":"Hassan","year":"2025","journal-title":"Sci. Rep"},{"key":"B7","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s00521-026-12055-6","article-title":"Neuroxai-caps: an explainable CNN\u2013capsule network for early Alzheimer's diagnosis","volume":"38","author":"Ibad","year":"2026","journal-title":"Neural Comput. Appl"},{"key":"B8","doi-asserted-by":"publisher","first-page":"104229","DOI":"10.1016\/j.dsp.2023.104229","article-title":"Efficient multimodel method based on transformers and coatnet for Alzheimer's diagnosis","volume":"143","author":"Kadri","year":"2023","journal-title":"Digit. Signal Process"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.3390\/bioengineering10101225","article-title":"Explainable vision transformer with self-supervised learning to predict Alzheimer's disease progression using 18F-FDG PET","volume":"10","author":"Khatri","year":"2023","journal-title":"Bioengineering"},{"key":"B10","doi-asserted-by":"publisher","first-page":"102812","DOI":"10.1016\/j.media.2023.102812","article-title":"Learning pyramidal multi-scale harmonic wavelets for identifying the neuropathology propagation patterns of Alzheimer's disease","volume":"87","author":"Liu","year":"2023","journal-title":"Med. Image Anal"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1498","DOI":"10.1162\/jocn.2007.19.9.1498","article-title":"Open access series of imaging studies (OASIS): cross-sectional MRI data in young, middle aged, nondemented, and demented older adults","volume":"19","author":"Marcus","year":"2007","journal-title":"J. Cogn. Neurosci"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.3390\/info16121051","article-title":"Graph neural networks in medical imaging: methods, applications and future directions","volume":"16","author":"Mienye","year":"2025","journal-title":"Information"},{"key":"B13","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/s10462-025-11258-y","article-title":"Alzheimer's disease detection using deep learning and machine learning: a review","volume":"58","author":"Mohsen","year":"2025","journal-title":"Artif. Intellig. Rev"},{"key":"B14","doi-asserted-by":"publisher","first-page":"42217","DOI":"10.1038\/s41598-025-26259-8","article-title":"Detection of brain network abnormalities by graph invariants in Alzheimer's disease using mri images","volume":"15","author":"NallappaBhavithran","year":"2025","journal-title":"Sci. Rep"},{"key":"B15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IWSSIP66997.2025.11151973","article-title":"\u201cEnhanced Alzheimer's diagnosis with a lightweight transformer: a multimodal fusion of sagittal MRI and clinical data,\u201d","volume-title":"2025 32nd International Conference on Systems, Signals and Image Processing (IWSSIP)","author":"Otapo","year":"2025"},{"key":"B16","doi-asserted-by":"publisher","first-page":"355","DOI":"10.3390\/biomedicines11020355","article-title":"Detecting early cognitive decline in Alzheimer's disease with brain synaptic structural and functional evaluation","volume":"11","author":"Ribari\u010d","year":"2023","journal-title":"Biomedicines"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1577","DOI":"10.1016\/S0140-6736(20)32205-4","article-title":"Alzheimer's disease","volume":"397","author":"Scheltens","year":"2021","journal-title":"Lancet"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1000435","DOI":"10.3389\/fncom.2022.1000435","article-title":"Transfer learning-based modified inception model for the diagnosis of Alzheimer's disease","volume":"16","author":"Sharma","year":"2022","journal-title":"Front. Comput. Neurosci"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1444019","DOI":"10.3389\/fncom.2024.1444019","article-title":"A combinatorial deep learning method for Alzheimer's disease classification-based merging pretrained networks","volume":"18","author":"Slimi","year":"2024","journal-title":"Front. Comput. Neurosci"},{"key":"B20","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s44196-024-00502-y","article-title":"Alzheimer's disease detection via multiscale feature modelling using improved spatial attention guided depth separable CNN","volume":"17","author":"Tripathy","year":"2024","journal-title":"Int. J. Comput. Intellig. Syst"},{"key":"B21","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1038\/s41583-023-00731-8","article-title":"Connectome-based modelling of neurodegenerative diseases: towards precision medicine and mechanistic insight","volume":"24","author":"Vogel","year":"2023","journal-title":"Nat. Rev. Neurosci"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2401","DOI":"10.32604\/cmes.2025.072148","article-title":"Ceoe-net: Chaotic evolution algorithm-based optimized ensemble framework enhanced with dual-attention for Alzheimer's diagnosis","volume":"145","author":"Yang","year":"2025","journal-title":"Comp.Model. Eng. Sci"},{"key":"B23","doi-asserted-by":"publisher","first-page":"4338","DOI":"10.3390\/app16094338","article-title":"Attentionms-net: An attention-enhanced multi-scale framework for Alzheimer's disease classification with subject-level validation","volume":"16","author":"Yildiz","year":"2026","journal-title":"Applied Sciences"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2512.18986","article-title":"R-GenIMA: Integrating neuroimaging and genetics with interpretable multimodal ai for Alzheimer's disease progression","author":"Zhao","year":"2025","journal-title":"arXiv"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1657578","DOI":"10.3389\/fnagi.2026.1657578","article-title":"Research on Alzheimer's disease mri image classification based on spatial attention mechanism","volume":"18","author":"Zhao","year":"2026","journal-title":"Front. Aging Neurosci"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1038636","DOI":"10.3389\/fncom.2023.1038636","article-title":"Conventional machine learning and deep learning in Alzheimer's disease diagnosis using neuroimaging: a review","volume":"17","author":"Zhao","year":"2023","journal-title":"Front. Comput. Neurosci"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1834764\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:36:52Z","timestamp":1783316212000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1834764\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,6]]},"references-count":26,"alternative-id":["10.3389\/fncom.2026.1834764"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2026.1834764","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,6]]},"article-number":"1834764"}}