{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T05:55:09Z","timestamp":1781502909471,"version":"3.54.1"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"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. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Alzheimer\u2019s disease (AD) is responsible for many dementia-related deaths worldwide, and Mild Cognitive Impairment (MCI) is often its earliest clinical manifestation. Early detection of MCI is essential to initiate timely interventions that can slow progression and improve the patient\u2019s quality of life. The emergence of diffusion tensor imaging (DTI) has made it a powerful neuroimaging modality for MCI detection, offering greater sensitivity to microstructural changes in white matter than basic structural imaging.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A Multichannel Attention Residual Learning\u2013DTI (MARL\u2013DTI) architecture was designed with attention mechanisms and residual learning utilizing multiple DTI-derived diffusion metrics, including fractional anisotropy (FA), mean diffusivity (MD), radial diffusivity (RD), and axial diffusivity (AxD). To overcome the scarcity of labelled neuroimaging data, the model was supplemented with a few-shot learning framework. The dataset comprised 239 DTI scans from ADNI was used to evaluate the model. Local Interpretable Model-Agnostic Explanations (LIME) assists in analysing the model\u2019s decision-making process behaviour.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed MARL-DTI achieved a classification accuracy of 92.76%, outperforming baseline DenseNet variants, StatFusion-FCNN, and Matching Networks. Validation on an unseen dataset of 36 ADNI subjects yielded consistent accuracy (91.67%), confirming the model\u2019s reliability. LIME analysis was used to provide instance-level explanations, enabling qualitative assessment of the model\u2019s decision-making behaviour by highlighting feature contributions for individual predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These results demonstrate that the proposed MARL-DTI framework surpasses traditional deep learning architectures in the early identification of MCI using DTI data. The model consistently achieved strong performance while maintaining transparency, using LIME as a validation tool to examine its decision-making behaviour. These findings highlight the potential of combining multi-channel volumetric DTI data with explainable deep learning approaches to support reliable and clinically relevant early detection of Alzheimer\u2019s disease.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1867451","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T05:33:26Z","timestamp":1781501606000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Early Alzheimer\u2019s risk detection via diffusion tensor imaging using a few-shot multichannel attention residual learning network"],"prefix":"10.3389","volume":"9","author":[{"given":"Arpit","family":"Shet","sequence":"first","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saad","family":"Sabahuddin","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Priyadarshini","family":"B","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhanu Naga Sai Siva Ram","family":"Jami","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John Sahaya Rani","family":"Alex","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chih-Yang","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, National Central University","place":["Taoyuan, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi-Wen","family":"Lung","sequence":"additional","affiliation":[{"name":"Department of Creative Product Design, Asia University","place":["Taichung, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e05652","DOI":"10.1016\/J.HELIYON.2020.E05652","article-title":"Improving Alzheimer\u2019s stage categorization with convolutional neural network using transfer learning and different magnetic resonance imaging modalities","volume":"6","author":"Aderghal","year":"2020","journal-title":"Heliyon."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1016\/J.NURT.2007.05.011","article-title":"Diffusion tensor imaging of the brain","volume":"4","author":"Alexander","year":"2007","journal-title":"Neurotherapeutics"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1016\/j.neuroimage.2015.10.019","article-title":"An integrated approach to correction for off-resonance effects and subject movement in diffusion MR imaging","volume":"125","author":"Andersson","year":"2016","journal-title":"NeuroImage"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/S12559-024-10390-1","article-title":"Convolutional cross-modal autoencoder-based few-shot learning for data augmentation with application to Alzheimer dementia diagnosis","volume":"17","author":"Bazine","year":"2025","journal-title":"Cogn. Comput."},{"key":"ref5","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1554015","DOI":"10.3389\/FNINS.2025.1554015","article-title":"Early detection and classification of Alzheimer\u2019s disease through data fusion of MRI and DTI images using the YOLOv11 neural network","volume":"19","author":"Hechkel","year":"2025","journal-title":"Front. Neurosci."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1016\/J.NEUROIMAGE.2014.06.077","article-title":"Hierarchical feature representation and multimodal fusion with deep learning for AD\/MCI diagnosis","volume":"101","author":"Suk","year":"2014","journal-title":"NeuroImage"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"206","DOI":"10.3389\/FNAGI.2020.00206","article-title":"Identifying early mild cognitive impairment by multi-modality MRI-based deep learning","volume":"12","author":"Kang","year":"2020","journal-title":"Front. Aging Neurosci."},{"key":"ref9","author":"Khvostikov","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"312747","DOI":"10.3389\/FNINF.2018.00035","article-title":"Classification of Alzheimer\u2019s disease by combination of convolutional and recurrent neural networks using FDG-PET images","volume":"12","author":"Liu","year":"2018","journal-title":"Front. Neuroinform."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"17106","DOI":"10.1038\/s41598-022-20674-x","article-title":"Generalizable deep learning model for early Alzheimer\u2019s disease detection from structural MRIs","volume":"12","author":"Liu","year":"2022","journal-title":"Sci. Rep."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e0230409","DOI":"10.1371\/JOURNAL.PONE.0230409","article-title":"Alzheimer\u2019s disease diagnosis from diffusion tensor images using convolutional neural networks","volume":"15","author":"Marzban","year":"2020","journal-title":"PLoS One"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neuroimage.2009.01.054","article-title":"Regionally-specific diffusion tensor imaging in mild cognitive impairment and Alzheimer's disease","volume":"46","author":"Mielke","year":"2009","journal-title":"Neuroimage"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"101551","DOI":"10.1016\/J.IMU.2024.101551","article-title":"Detection of Alzheimer\u2019s disease using deep learning models: a systematic literature review","volume":"50","author":"Mohammed","year":"2024","journal-title":"Inform Med Unlocked."},{"key":"ref15","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"S132","DOI":"10.1016\/J.NEUROBIOLAGING.2014.05.037","article-title":"DTI-based maximum density path analysis and classification of Alzheimer\u2019s disease","volume":"36","author":"Nir","year":"2014","journal-title":"Neurobiol. Aging"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"287","DOI":"10.3233\/JAD-2011-0007","article-title":"DTI analyses and clinical applications in Alzheimer's disease","volume":"26","author":"Oishi","year":"2011","journal-title":"J Alzheimers Dis"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"2939778","DOI":"10.1145\/2939672.2939778","article-title":"\u201cWhy Should I Trust You?\u201d explaining the predictions of any classifier","author":"Ribeiro","year":"2016","journal-title":"arXiv"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/S12929-019-0524-Y","article-title":"Alzheimer\u2019s disease: risk factors and potentially protective measures","volume":"26","author":"Silva","year":"2019","journal-title":"J. Biomed. Sci."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1002\/HBM.10062","article-title":"Fast robust automated brain extraction","volume":"17","author":"Smith","year":"2002","journal-title":"Hum. Brain Mapp."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"e05175","DOI":"10.48550\/arXiv.1703.05175","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017","journal-title":"arXiv"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1016\/j.mri.2016.05.001","article-title":"Shape and diffusion tensor imaging based integrative analysis of the hippocampus and the amygdala in Alzheimer\u2019s disease","volume":"34","author":"Tang","year":"2016","journal-title":"Magn. Reson. Imaging"},{"key":"ref23","author":"Vinyals","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"489","DOI":"10.3390\/rs9050489","article-title":"Learning low dimensional convolutional neural networks for high-resolution remote sensing image retrieval","volume":"9","author":"Zhou","year":"2017","journal-title":"Remote Sens"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1867451\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T05:33:27Z","timestamp":1781501607000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1867451\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":24,"alternative-id":["10.3389\/frai.2026.1867451"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1867451","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,15]]},"article-number":"1867451"}}