{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T06:01:00Z","timestamp":1790834460278,"version":"4.1.0"},"reference-count":102,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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) affects an estimated 55 million people worldwide and is projected to nearly double by 2050, creating a need for scalable, non-invasive AI systems that can classify disease stage, support multimodal clinical reasoning, and interact in natural language. Most deep learning work on AD focuses on single-modality classification without natural-language interaction and typically assumes complete input data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We present MEMOIR-VLM (Multimodal Encoder with Missing-modality and Open-ended Inference for Retrieval), a modular two-stage vision-language framework trained and evaluated on 2,363 ADNI subjects. The first stage is a missing-modality-aware encoder that fuses T1-weighted MRI and DTI fractional anisotropy maps with structured clinical scores via cross-attention fusion with stochastic modality dropout, allowing a single set of weights to operate on any of the seven non-empty modality subsets without imputation. After CLIP\/InfoNCE contrastive pretraining, the encoder is fine-tuned for multi-task prediction of 3-way diagnosis, binary diagnosis, CDR-SB, age, and sex. The second stage extends the frozen encoder into a retrieval-augmented generation pipeline for case-based reasoning and open-ended visual question answering.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On held-out ADNI test data, with CDR-SB excluded from the inputs to remove a cognitive-score leak, the encoder achieved 91.3% balanced accuracy for CN vs. dementia and 68.2% balanced accuracy for 3-class diagnosis (macro-F1 = 0.681); age was predicted with a 5.96-year MAE. When the diagnosis field was withheld from retrieved captions, no evaluated LLM exceeded a retrieval-only k-NN majority vote (0.673), which itself closely matched the encoder's 3-class accuracy (0.682). The RAG-VQA layer showed strong text fidelity (BERTScore = 0.894; SBERT cosine similarity = 0.811). Zero-shot external validation on OASIS-3 (1,048 subjects, no diffusion data) retained 78.7% balanced accuracy for CN vs. impaired (AUC = 0.889) using identical ADNI-trained weights with the DTI branch masked.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>MEMOIR-VLM combines missing-modality-aware multimodal encoding, multi-task clinical prediction, and retrieval-grounded natural-language reasoning within a single modular framework. The results support using the encoder, optionally with k-NN voting, as the diagnostic component and the RAG-VQA layer as an interpretable natural-language interface that surfaces comparable cases and readable clinical summaries. The external validation results further demonstrate the practical value of the missing-modality mechanism when an imaging modality is unavailable.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fncom.2026.1902258","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:40:28Z","timestamp":1790833228000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MEMOIR-VLM\u2014a multimodal vision-language model for Alzheimer's disease classification and question answering"],"prefix":"10.3389","volume":"20","author":[{"given":"Sohail Haresh","family":"Gidwani","sequence":"first","affiliation":[{"name":"Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California","place":["Marina del Rey, CA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tamoghna","family":"Chattopadhyay","sequence":"additional","affiliation":[{"name":"Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California","place":["Marina del Rey, CA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sophia I.","family":"Thomopoulos","sequence":"additional","affiliation":[{"name":"Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California","place":["Marina del Rey, CA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul M.","family":"Thompson","sequence":"additional","affiliation":[{"name":"Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California","place":["Marina del Rey, CA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"200415","DOI":"10.1016\/j.iswa.2024.200415","article-title":"Generalisable deep learning framework to overcome catastrophic forgetting","volume":"23","author":"Alammar","year":"2024","journal-title":"Intell. Syst. Appli."},{"key":"B2","unstructured":"Dementia Statistics\n          \n          2021"},{"key":"B3","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1038\/s41746-025-01670-7","article-title":"A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation","volume":"8","author":"Asgari","year":"2025","journal-title":"NPJ Digit. Med."},{"key":"B4","first-page":"233","article-title":"\u201cMedical image retrieval using Resnet-18,\u201d","author":"Ayyachamy","year":"2019","journal-title":"Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s11063-024-11709-7","article-title":"Continual learning in medicine: a systematic literature review","volume":"57","author":"Bruno","year":"2025","journal-title":"Neural Process. Lett."},{"key":"B6","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1007\/s00259-011-2021-8","article-title":"Using PET with 18F-AV-45 (florbetapir) to quantify brain amyloid load in a clinical environment","volume":"39","author":"Camus","year":"2012","journal-title":"Eur. J. Nucl. Med. Mol. Imaging."},{"key":"B7","article-title":"VisTA: vision-text alignment model with contrastive learning using multimodal data for evidence-driven, reliable, and explainable alzheimer's disease diagnosis","author":"Can","year":"","journal-title":"arXiv"},{"key":"B8","first-page":"11179","article-title":"\u201cREMEMBER: retrieval-based explainable multimodal evidence-guided modeling for brain evaluation and reasoning in zero-and few-shot neurodegenerative diagnosis,\u201d","volume-title":"Proceedings of the 33rd ACM International Conference on Multimedia","author":"Can","year":""},{"key":"B9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3641289","article-title":"A survey on evaluation of large language models","volume":"15","author":"Chang","year":"2024","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"B10","first-page":"148","article-title":"\u201cEvaluating synthetic diffusion MRI maps created with diffusion denoising probabilistic models,\u201d","volume-title":"Medical Imaging 2025: imaging informatics, Vol. 13411","author":"Chattopadhyay","year":""},{"key":"B11","first-page":"1","article-title":"\u201cUsing diffusion transformers to generate synthetic diffusion scalar maps for data augmentation,\u201d","volume-title":"2025 21st International symposium on biomedical image processing and analysis (SIPAIM)","author":"Chattopadhyay","year":""},{"key":"B12","first-page":"1","article-title":"\u201cComparison of explainable AI models for MRI-based Alzheimer's disease classification,\u201d","volume-title":"2024 20th International symposium on medical information processing and analysis (SIPAIM)","author":"Chattopadhyay","year":""},{"key":"B13","first-page":"1","article-title":"\u201cBrain age analysis and dementia classification using convolutional neural networks trained on diffusion MRI: tests in Indian and North American cohorts,\u201d","volume-title":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","author":"Chattopadhyay","year":""},{"key":"B14","first-page":"1","article-title":"\u201cCan structural MRIs be used to detect amyloid positivity using deep learning?\u201d","volume-title":"2023 19th International symposium on medical information processing and analysis (SIPAIM)","author":"Chattopadhyay","year":""},{"key":"B15","first-page":"1","article-title":"\u201cGenerating diffusion MRI scalar maps from T1-weighted images using Reversible GANs,\u201d","volume-title":"2025 21st International symposium on biomedical image processing and analysis (SIPAIM)","author":"Chattopadhyay","year":""},{"key":"B16","doi-asserted-by":"publisher","first-page":"1387196","DOI":"10.3389\/fnins.2024.1387196","article-title":"Comparison of deep learning architectures for predicting amyloid positivity in Alzheimer's disease, mild cognitive impairment, and healthy aging, from T1-weighted brain structural MRI","volume":"18","author":"Chattopadhyay","year":"","journal-title":"Front. Neurosci"},{"key":"B17","first-page":"1","article-title":"\u201cPredicting longitudinal cognitive decline via multimodal deep learning fusing brain MRI and clinical data,\u201d","volume-title":"2025 21st international symposium on biomedical image processing and analysis (SIPAIM)","author":"Chattopadhyay","year":""},{"key":"B18","doi-asserted-by":"publisher","first-page":"1726037","DOI":"10.3389\/fnimg.2026.1726037","article-title":"Deep learning to predict future cognitive decline: a multimodal approach using brain MRI and clinical data","volume":"5","author":"Chattopadhyay","year":"2026","journal-title":"Front. Neuroimaging"},{"key":"B19","first-page":"90","article-title":"\u201cPredicting dementia severity by merging anatomical and diffusion MRI with deep 3D convolutional neural networks,\u201d","volume-title":"18th International symposium on medical information processing and analysis, Vol. 12567","author":"Chattopadhyay","year":""},{"key":"B20","doi-asserted-by":"publisher","first-page":"2404","DOI":"10.1007\/978-981-96-0908-6_6","article-title":"\u201cMedblip: bootstrapping language-image pre-training from 3D medical images and texts,\u201d","author":"Chen","year":"2024","journal-title":"Proceedings of the Asian Conference on Computer Vision"},{"key":"B21","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1186\/s13195-024-01567-9","article-title":"Reliability of the assessment of the clinical dementia rating scale from the analysis of medical records in comparison with the reference method","volume":"16","author":"Dauphinot","year":"2024","journal-title":"Alzheimer's Res. Therapy"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI61048.2026.11515735","article-title":"CALM-VLM: calibration and selective prediction in vision-language models for reliable brain MRI classification","author":"Dhinagar","year":"","journal-title":"bioRxiv"},{"key":"B23","first-page":"271","article-title":"\u201cParameter efficient fine-tuning of transformer-based masked autoencoder enhances resource constrained neuroimage analysis,\u201d","volume-title":"Medical imaging 2025: computer-aided diagnosis, Vol. 13407","author":"Dhinagar","year":""},{"key":"B24","first-page":"1392602","article-title":"\u201cMAVeRiC-AD: mixture-of-experts agentic vision-language ensemble for robust MRI classification of Alzheimer's disease,\u201d","volume-title":"Medical imaging 2026: computer-aided diagnosis, Vol. 13926","author":"Dhinagar","year":""},{"key":"B25","first-page":"1","article-title":"\u201cEfficiently training vision transformers on structural MRI scans for Alzheimer's disease detection,\u201d","volume-title":"2023 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","author":"Dhinagar","year":"2023"},{"key":"B26","first-page":"1","article-title":"\u201cLeveraging a vision-language model with natural text supervision for MRI retrieval, captioning, classification, and visual question answering,\u201d","volume-title":"2025 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","author":"Dhinagar","year":""},{"key":"B27","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/0022-3956(75)90026-6","article-title":"Mini-mental state","volume":"12","author":"Folstein","year":"1975","journal-title":"J. Psychiatr. Res"},{"key":"B28","article-title":"Retrieval-augmented generation for large language models: a survey. arXiv [preprint]","author":"Gao","year":"2023","journal-title":"arXiv:2312.10997"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e105","DOI":"10.1016\/S2468-2667(21)00249-8","article-title":"Estimation of the global prevalence of dementia in 2019 and forecasted prevalence in 2050: an analysis for the global burden of disease study 2019","volume":"7","year":"2022","journal-title":"Lancet Public Health"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2014","DOI":"10.1093\/jamia\/ocac168","article-title":"Multimodal attention-based deep learning for Alzheimer's disease diagnosis","volume":"29","author":"Golovanevsky","year":"2022","journal-title":"J. Am. Med. Informat. Assoc."},{"key":"B31","unstructured":"gemma-4-26B-A4B [Large language model]. Hugging Face\n          \n          2026"},{"key":"B32","doi-asserted-by":"crossref","DOI":"10.1109\/ICMLA66185.2025.00224","article-title":"\u201cBRAINS: A Retrieval-Augmented System For Alzheimer's Detection And Monitoring\u201d","volume-title":"2025 international conference on machine learning and applications (ICMLA)","author":"Gupta","year":"2025"},{"key":"B33","article-title":"Addressing catastrophic forgetting for medical domain expansion. arXiv [preprint]","author":"Gupta","year":"2021","journal-title":"arXiv:2103.13511"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1430984","DOI":"10.3389\/frai.2024.1430984","article-title":"Vision-language models for medical report generation and visual question answering: a review","volume":"7","author":"Hartsock","year":"2024","journal-title":"Front. Artif. Intell"},{"key":"B35","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1093\/occmed\/kqv078","article-title":"The Montreal cognitive assessment (MoCA)","volume":"65","author":"Hobson","year":"2015","journal-title":"Occupat. Med."},{"key":"B36","unstructured":"Huggingface.co\n          \n          2025"},{"key":"B37","doi-asserted-by":"crossref","first-page":"2029","DOI":"10.1093\/brain\/awad042","article-title":"Predicting amyloid PET and tau PET stages with plasma biomarkers","volume":"146","author":"Jack Jr","year":"2023","journal-title":"Brain"},{"key":"B38","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/j.jalz.2018.02.018","article-title":"NIA-AA research framework: toward a biological definition of Alzheimer's disease","volume":"14","author":"Jack","year":"2018","journal-title":"Alzheimer's Dement."},{"key":"B39","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1212\/WNL.0000000000002923","article-title":"A\/T\/N: an unbiased descriptive classification scheme for Alzheimer disease biomarkers","volume":"87","author":"Jack","year":"2016","journal-title":"Neurology"},{"key":"B40","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1002\/jmri.21049","article-title":"The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods","volume":"27","author":"Jack","year":"2008","journal-title":"J. Magn. Res. Imag."},{"key":"B41","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/j.neuroimage.2013.04.061","article-title":"Multi-site genetic analysis of diffusion images and voxelwise heritability analysis: a pilot project of the ENIGMA-DTI working group","volume":"81","author":"Jahanshad","year":"2013","journal-title":"Neuroimage"},{"key":"B42","doi-asserted-by":"publisher","first-page":"e70719","DOI":"10.1002\/alz.70719","article-title":"An AI-first framework for multimodal data in Alzheimer's disease and related dementias","volume":"21","author":"Jasodanand","year":"","journal-title":"Alzheimer's Demen."},{"key":"B43","doi-asserted-by":"publisher","first-page":"7407","DOI":"10.1038\/s41467-025-62590-4","article-title":"AI-driven fusion of multimodal data for Alzheimer's disease biomarker assessment","volume":"16","author":"Jasodanand","year":"","journal-title":"Nat. Commun."},{"key":"B44","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1016\/j.neuroimage.2011.09.015","article-title":"FSL","volume":"62","author":"Jenkinson","year":"2012","journal-title":"Neuroimage"},{"key":"B45","doi-asserted-by":"crossref","first-page":"12143","DOI":"10.18653\/v1\/2024.emnlp-main.677","article-title":"\u201cMedical adaptation of large language and vision-language models: Are we making progress?,\u201d","author":"Jeong","year":"2024","journal-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1827","DOI":"10.18653\/v1\/2023.findings-emnlp.123","article-title":"\u201cTowards mitigating LLM hallucination via self reflection,\u201d","author":"Ji","year":"2023","journal-title":"Findings of the Association for Computational Linguistics: EMNLP"},{"key":"B47","doi-asserted-by":"publisher","first-page":"106339","DOI":"10.1016\/j.ijmedinf.2026.106339","article-title":"Agentic memory-augmented retrieval and evidence grounding for medical question-answering tasks","volume":"212","author":"Jia","year":"2026","journal-title":"Int. J. Med. Inform."},{"key":"B48","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-scale similarity search with GPUs","volume":"7","author":"Johnson","year":"2019","journal-title":"IEEE Transact. Big Data"},{"key":"B49","doi-asserted-by":"crossref","first-page":"S72","DOI":"10.1016\/j.jalz.2012.10.007","article-title":"Florbetapir (F18-AV-45) PET to assess amyloid burden in Alzheimer's disease dementia, mild cognitive impairment, and normal aging","volume":"9","author":"Johnson","year":"2013","journal-title":"Alzheimers Dement."},{"key":"B50","doi-asserted-by":"publisher","first-page":"423","DOI":"10.3233\/JAD-170991","article-title":"The Alzheimer's disease assessment scale\u2013cognitive subscale (ADAS-Cog): modifications and responsiveness in pre-dementia populations. A narrative review","volume":"63","author":"Kueper","year":"2018","journal-title":"J. Alzheimer's Dis."},{"key":"B51","article-title":"3D grid-attention networks for interpretable age and Alzheimer's disease prediction from structural MRI. arXiv [preprint]","author":"Lam","year":"2020","journal-title":"arXiv:2011.09115"},{"key":"B52","first-page":"2019","article-title":"OASIS-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer disease","author":"LaMontagne","year":"2019","journal-title":"medrxiv"},{"key":"B53","doi-asserted-by":"publisher","first-page":"180251","DOI":"10.1038\/sdata.2018.251","article-title":"A dataset of clinically generated visual questions and answers about radiology images","volume":"5","author":"Lau","year":"2018","journal-title":"Scient. Data"},{"key":"B54","doi-asserted-by":"publisher","first-page":"e279","DOI":"10.1016\/S2589-7500(20)30102-3","article-title":"Clinical applications of continual learning machine learning","volume":"2","author":"Lee","year":"2020","journal-title":"Lancet Digit. Health"},{"key":"B55","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B56","doi-asserted-by":"crossref","first-page":"28541","DOI":"10.52202\/075280-1240","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B57","first-page":"74","article-title":"\u201cRouge: a package for automatic evaluation of summaries,\u201d","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"B58","doi-asserted-by":"publisher","first-page":"e71029","DOI":"10.1002\/alz.71029","article-title":"A vision-language foundation model for Alzheimer's disease diagnosis using MRI and clinical data","volume":"21","author":"Lin","year":"2025","journal-title":"Alzheimer's Demen."},{"key":"B59","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural. Inf. Process Syst"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.64898\/2026.03.30.26349106","article-title":"Vision-language framework for multi-sequence brain magnetic resonance imaging","author":"Lteif","year":"2026","journal-title":"Medrxiv"},{"key":"B61","first-page":"1","article-title":"\u201cTADPOLE challenge: accurate Alzheimer's disease prediction through crowdsourced forecasting of future data,\u201d","volume-title":"International Workshop on Predictive Intelligence in Medicine","author":"Marinescu","year":"2019"},{"key":"B62","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1056\/NEJM199802193380804","article-title":"Utility of the apolipoprotein E genotype in the diagnosis of Alzheimer's disease","volume":"338","author":"Mayeux","year":"1998","journal-title":"New Engl. J. Med."},{"key":"B63","doi-asserted-by":"crossref","first-page":"151","DOI":"10.14283\/jpad.2020.73","article-title":"Psychometric properties of the Clinical Dementia Rating-Sum of Boxes and other cognitive and functional outcomes in a prodromal Alzheimer's disease population","volume":"8","author":"McDougall","year":"2021","journal-title":"J. Prev. Alzheimers Dis."},{"key":"B64","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.media.2019.01.004","article-title":"Training recurrent neural networks robust to incomplete data: application to Alzheimer's disease progression modeling","volume":"53","author":"Mehdipour Ghazi","year":"2019","journal-title":"Med. Image Anal."},{"key":"B65","unstructured":"mistralai\/Mistral-7B-v0.1. Hugging Face\n          \n          2023"},{"key":"B66","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1038\/nature25456","article-title":"High performance plasma amyloid-\u03b2 biomarkers for Alzheimer's disease","volume":"554","author":"Nakamura","year":"2018","journal-title":"Nature"},{"key":"B67","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.nicl.2013.07.006","article-title":"Effectiveness of regional DTI measures in distinguishing Alzheimer's disease, MCI, and normal aging","volume":"3","author":"Nir","year":"2013","journal-title":"NeuroImage Clinical"},{"key":"B68","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1001\/archneur.65.8.1091","article-title":"Staging dementia using clinical dementia rating scale sum of boxes scores: a Texas Alzheimer's research consortium study","volume":"65","author":"O'Bryant","year":"2008","journal-title":"Arch. Neurol"},{"key":"B69","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018","journal-title":"arXiv preprint arXiv:1807.03748"},{"key":"B70","first-page":"311","article-title":"\u201cBleu: a method for automatic evaluation of machine translation,\u201d","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","author":"Papineni","year":"2002"},{"key":"B71","doi-asserted-by":"publisher","first-page":"5678","DOI":"10.1038\/s41467-021-25858-z","article-title":"Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging","volume":"12","author":"Perkonigg","year":"2021","journal-title":"Nat. Commun."},{"key":"B72","doi-asserted-by":"publisher","first-page":"1378","DOI":"10.1016\/S1388-2457(01)00579-X","article-title":"Recurrent neural network-based approach for early recognition of Alzheimer's disease in EEG","volume":"112","author":"Petrosian","year":"2001","journal-title":"Clin. Neurophysiol."},{"key":"B73","first-page":"8748","article-title":"\u201cLearning transferable visual models from natural language supervision,\u201d","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"B74","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.3390\/bioengineering12101107","article-title":"NeuroNet-AD: a multimodal deep learning framework for multiclass Alzheimer's disease diagnosis","volume":"12","author":"Rahman","year":"2025","journal-title":"Bioengineering"},{"key":"B75","doi-asserted-by":"crossref","first-page":"3982","DOI":"10.18653\/v1\/D19-1410","article-title":"\u201cSentence-bert: sentence embeddings using siamese bert-networks,\u201d","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Reimers","year":"2019"},{"key":"B76","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","article-title":"The future of digital health with federated learning","volume":"3","author":"Rieke","year":"2020","journal-title":"NPJ Digital Med."},{"key":"B77","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1111\/j.1532-5415.2000.tb05004.x","article-title":"Interrater reliability of the Clinical Dementia Rating in a multicenter trial","volume":"48","author":"Rockwood","year":"2000","journal-title":"J. Am. Geriatr. Soc."},{"key":"B78","article-title":"\u201cNew advances in the Clinica software platform for clinical neuroimaging studies,\u201d","author":"Routier","year":"2019","journal-title":"OHBM 2019-Annual Meeting on Organization for Human Brain Mapping."},{"key":"B79","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1080\/07317115.2022.2054391","article-title":"Inequitable access to dementia diagnosis and care in low-resource settings\u2013a global perspective","volume":"46","author":"Seeher","year":"2023","journal-title":"Clin. Gerontol."},{"key":"B80","article-title":"Medgemma 1.5 technical report. arXiv [preprint]","author":"Sellergren","year":"2026","journal-title":"arXiv:2604.05081"},{"key":"B81","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models","volume":"31","author":"Singhal","year":"2025","journal-title":"Nat. Med."},{"key":"B82","article-title":"Paligemma 2: A family of versatile vlms for transfer. arXiv [preprint]","author":"Steiner","year":"2024","journal-title":"arXiv:2412.03555"},{"key":"B83","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2024.101031","article-title":"A federated learning architecture for secure and private neuroimaging analysis","author":"Stripelis","year":"2024","journal-title":"Patterns"},{"key":"B84","first-page":"351","article-title":"\u201cSecure neuroimaging analysis using federated learning with homomorphic encryption,\u201d","volume-title":"17th international symposium on medical information processing and analysis, Vol. 12088","author":"Stripelis","year":"2021"},{"key":"B85","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat. Med."},{"key":"B86","first-page":"166","article-title":"\u201cDiffusion MRI metrics and their relation to dementia severity: effects of harmonization approaches,\u201d","volume-title":"17th international symposium on medical information processing and analysis, Vol. 12088","author":"Thomopoulos","year":"2021"},{"key":"B87","doi-asserted-by":"crossref","first-page":"AIoa2300138","DOI":"10.1056\/AIoa2300138","article-title":"Towards generalist biomedical AI","volume":"1","author":"Tu","year":"2024","journal-title":"Nejm Ai"},{"key":"B88","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1038\/s41746-026-02380-4","article-title":"Evaluation of large language models for diagnostic impression generation from brain MRI report findings: a multicenter benchmark and reader study","volume":"9","author":"Wang","year":"2026","journal-title":"NPJ Digit."},{"key":"B89","doi-asserted-by":"publisher","first-page":"9161","DOI":"10.1038\/s41598-018-27337-w","article-title":"Predictive modeling of the progression of Alzheimer's disease with recurrent neural networks","volume":"8","author":"Wang","year":"2018","journal-title":"Scientif. Rep."},{"key":"B90","article-title":"A self-supervised text-vision framework for automated brain abnormality detection","author":"Wood","year":"2024","journal-title":"arXiv"},{"key":"B91","doi-asserted-by":"crossref","first-page":"S173","DOI":"10.1016\/j.neuroimage.2008.10.055","article-title":"Bayesian analysis of neuroimaging data in FSL","volume":"45","author":"Woolrich","year":"2009","journal-title":"Neuroimage"},{"key":"B92","unstructured":"Dementia Fact Sheet\n          \n          2020"},{"key":"B93","article-title":"Can gpt-4v (ision) serve medical applications? Case studies on gpt-4v for multimodal medical diagnosis. arXiv [preprint]","author":"Wu","year":"2023","journal-title":"arXiv:2310.09909"},{"key":"B94","doi-asserted-by":"publisher","first-page":"7866","DOI":"10.1038\/s41467-025-62385-7","article-title":"Towards generalist foundation model for radiology by leveraging web-scale 2D and 3D medical data","volume":"16","author":"Wu","year":"2025","journal-title":"Nat. Commun."},{"key":"B95","article-title":"The dawn of LMMS: preliminary explorations with gpt-4v (ision). arXiv [preprint]","author":"Yang","year":"2023","journal-title":"arXiv:2309.17421"},{"key":"B96","article-title":"Towards general purpose medical ai: Continual learning medical foundation model. arXiv [preprint]","author":"Yi","year":"2023","journal-title":"arXiv:2303.06580"},{"key":"B97","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3389\/fninf.2019.00002","article-title":"Diffusion MRI indices and their relation to cognitive impairment in brain aging: the updated multi-protocol approach in ADNI3","volume":"13","author":"Zavaliangos-Petropulu","year":"2019","journal-title":"Front. Neuroinform."},{"key":"B98","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: a survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B99","doi-asserted-by":"publisher","first-page":"3129","DOI":"10.1038\/s41591-024-03185-2","article-title":"A generalist vision\u2013language foundation model for diverse biomedical tasks","volume":"30","author":"Zhang","year":"2024","journal-title":"Nat. Med."},{"key":"B100","first-page":"1","article-title":"\u201cDiffusion bridge models for 3d medical image translation,\u201d","volume-title":"2025 47th annual international conference of the IEEE engineering in medicine and biology society","author":"Zhang","year":"2025"},{"key":"B101","article-title":"BERTScore: evaluating text generation with bert","author":"Zhang","year":"2019","journal-title":"arXiv preprint arXiv:1904.09675"},{"key":"B102","doi-asserted-by":"crossref","first-page":"2012627","DOI":"10.1007\/s11704-026-60308-3","article-title":"A survey of large language models","volume":"20","author":"Zhao","year":"2023","journal-title":"Front. Comput. Sci."}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1902258\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:40:38Z","timestamp":1790833238000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1902258\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":102,"alternative-id":["10.3389\/fncom.2026.1902258"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2026.1902258","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]},"article-number":"1902258"}}