{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T07:52:19Z","timestamp":1791359539545,"version":"4.3.1"},"reference-count":150,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neuroinform."],"abstract":"<jats:p>Functional magnetic resonance imaging (fMRI) serves as a pivotal tool for investigating the functional organization and dynamic connectivity of the human brain, indirectly reflecting neural activity through blood oxygen level-dependent (BOLD) signals. However, the high-dimensional spatiotemporal structure, prominent noise interference, and inter-individual variability of fMRI data pose significant challenges for traditional modeling methods in characterizing complex brain functional patterns. In recent years, the Transformer architecture has gained significant traction in fMRI data analysis, leveraging its self-attention mechanism to model global dependencies. It has demonstrated superior performance in tasks such as brain disease classification, functional connectivity modeling, and brain representation learning. Compared to convolutional and recurrent neural networks, Transformers can more effectively capture long-range spatiotemporal dependencies and offer stronger structural scalability and cross-task transfer potential. To systematically map the development of this field, this paper proposes a unified taxonomy for Transformer-fMRI methods based on modeling dimensions. It categorizes existing research into four primary paradigms: temporal modeling, spatial modeling, spatiotemporal joint modeling, and self-supervised learning, providing a comparative analysis of their structural characteristics and applicable scenarios. Furthermore, this paper summarizes the key challenges regarding computational complexity, data dependency, and interpretability, while exploring the integration of neuroscientific priors with large-scale pre-trained models. Finally, we discuss future directions for Transformers in the construction of brain foundation models and their clinical utility.<\/jats:p>","DOI":"10.3389\/fninf.2026.1869687","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T07:17:33Z","timestamp":1791357453000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Transformers for fMRI analysis: from spatiotemporal modeling to brain foundation models"],"prefix":"10.3389","volume":"20","author":[{"given":"Xiaomin","family":"Yang","sequence":"first","affiliation":[{"name":"School of Media Engineering, Communication University of Zhejiang","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Li","sequence":"additional","affiliation":[{"name":"School of Media Engineering, Communication University of Zhejiang","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Media Engineering, Communication University of Zhejiang","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bocheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Media Engineering, Communication University of Zhejiang","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3389\/fninf.2014.00014","article-title":"Machine learning for neuroimaging with scikit-learn","volume":"8","author":"Abraham","year":"2014","journal-title":"Front. Neuroinform"},{"key":"B2","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1038\/s41467-020-20655-6","article-title":"Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning","volume":"12","author":"Abrol","year":"2021","journal-title":"Nat. Commun"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1548","DOI":"10.3390\/math13101548","article-title":"Transformer and convolutional neural network: A hybrid model for multimodal data in multiclass classification of alzheimer's disease","volume":"13","author":"Alorf","year":"2025","journal-title":"Mathematics"},{"key":"B4","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1162\/netn_a_00281","article-title":"A transformer model for learning spatiotemporal contextual representation in fMRI data","volume":"7","author":"Asadi","year":"2023","journal-title":"Netw. Neurosci"},{"key":"B5","doi-asserted-by":"publisher","first-page":"981642","DOI":"10.3389\/fnimg.2022.981642","article-title":"Deep learning in neuroimaging data analysis: Applications, challenges, and solutions","volume":"1","author":"Avber\u0161ek","year":"2022","journal-title":"Front. Neuroimag"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.01271","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv"},{"key":"B7","first-page":"287","article-title":"\u201cCommunity-aware transformer for autism prediction in fMRI connectome,\u201d","volume-title":"Medical Image Computing and Computer Assisted Intervention-MICCAI 2023","author":"Bannadabhavi","year":"2023"},{"key":"B8","doi-asserted-by":"publisher","first-page":"102841","DOI":"10.1016\/j.media.2023.102841","article-title":"BolT: Fused window transformers for fMRI time series analysis","volume":"88","author":"Bedel","year":"2023","journal-title":"Med. Image Anal"},{"key":"B9","unstructured":"\u201cBrain-IT: image reconstruction from fMRI via Brain-Interaction Transformer,\u201d\n          \n          \n            \n              Beliy\n              R.\n            \n            \n              Zalcher\n              A.\n            \n            \n              Jonathan Kogman\n              J.\n            \n            \n              Wasserman\n              N.\n            \n            \n              Irani\n              M.\n            \n          \n          The Fourteenth International Conference on Learning Representations\n          \n          2026"},{"key":"B10","doi-asserted-by":"publisher","first-page":"5833","DOI":"10.1109\/TPAMI.2022.3209686","article-title":"Graph neural networks in network neuroscience","volume":"45","author":"Bessadok","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1392661","DOI":"10.3389\/fninf.2024.1392661","article-title":"Explainable deep-learning framework: decoding brain states and prediction of individual performance in false-belief task at early childhood stage","volume":"18","author":"Bhavna","year":"2024","journal-title":"Front. Neuroinform"},{"key":"B12","doi-asserted-by":"publisher","first-page":"S163","DOI":"10.1016\/j.neuroimage.2008.10.057","article-title":"A review of group ICA for fMRI data and ICA for joint inference of imaging, genetic, and ERP data","volume":"45","author":"Calhoun","year":"2009","journal-title":"Neuroimage"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04306","article-title":"TransUNet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","journal-title":"arXiv"},{"key":"B14","first-page":"236","article-title":"\u201cCore-periphery principle guided state space model for functional connectome classification,\u201d","volume-title":"Proceedings of Medical Image Computing and Computer Assisted Intervention-MICCAI 2025","author":"Chen","year":"2025"},{"key":"B15","doi-asserted-by":"publisher","first-page":"102444","DOI":"10.1016\/j.media.2022.102444","article-title":"Recent advances and clinical applications of deep learning in medical image analysis","volume":"79","author":"Chen","year":"2022","journal-title":"Med. Image Anal"},{"key":"B16","doi-asserted-by":"crossref","first-page":"22710","DOI":"10.1109\/CVPR52729.2023.02175","article-title":"\u201cSeeing beyond the brain: Conditional diffusion model with sparse masked modeling for vision decoding,\u201d","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chen","year":"2023"},{"key":"B17","first-page":"1","article-title":"\u201cMasked momentum contrastive dynamic transformer for self-supervised functional connectivity representation learning,\u201d","volume-title":"2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)","author":"Cheng","year":""},{"key":"B18","doi-asserted-by":"publisher","first-page":"121370","DOI":"10.1016\/j.neuroimage.2025.121370","article-title":"STF: A spherical transformer for versatile cortical surfaces applications","volume":"318","author":"Cheng","year":"","journal-title":"Neuroimage"},{"key":"B19","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":"B20","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1109\/TMI.2022.3218745","article-title":"BrainGB: A benchmark for brain network analysis with graph neural networks","volume":"42","author":"Cui","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B21","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.neuroimage.2019.02.062","article-title":"Benchmarking functional connectome-based predictive models for resting-state fMRI","volume":"192","author":"Dadi","year":"2019","journal-title":"Neuroimage"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e26542","DOI":"10.1002\/hbm.26542","article-title":"Classification of MDD using a transformer classifier with large-scale multisite resting-state fMRI data","volume":"45","author":"Dai","year":"2024","journal-title":"Hum. Brain Mapp"},{"key":"B23","doi-asserted-by":"publisher","first-page":"e1012795","DOI":"10.1371\/journal.pcbi.1012795","article-title":"DySCo: a general framework for dynamic functional connectivity","volume":"21","author":"de Alteriis","year":"2025","journal-title":"PLoS Comput. Biol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1038\/s41562-020-01003-6","article-title":"Revisiting the global workspace orchestrating the hierarchical organization of the human brain","volume":"5","author":"Deco","year":"2021","journal-title":"Nat. Human Behav"},{"key":"B25","doi-asserted-by":"publisher","first-page":"123184","DOI":"10.1016\/j.ins.2026.123184","article-title":"Machine learning on dynamic functional connectivity: Promise, pitfalls, and interpretations","volume":"740","author":"Ding","year":"2026","journal-title":"Inf. Sci"},{"key":"B26","doi-asserted-by":"publisher","first-page":"107927","DOI":"10.1016\/j.neunet.2025.107927","article-title":"STARFormer: A novel spatio-temporal aggregation reorganization transformer of FMRI for brain disorder diagnosis","volume":"192","author":"Dong","year":"2025","journal-title":"Neural Networks"},{"key":"B27","first-page":"122100","article-title":"\u201cBrain harmony: A multimodal foundation model unifying morphology and function into 1D tokens,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Dong","year":"2025"},{"key":"B28","unstructured":"\u201cAn image is worth 16 \u00d7 16 words: transformers for image recognition at scale,\u201d\n          \n          \n            \n              Dosovitskiy\n              A.\n            \n            \n              Beyer\n              L.\n            \n            \n              Kolesnikov\n              A.\n            \n            \n              Weissenborn\n              D.\n            \n            \n              Zhai\n              X.\n            \n            \n              Unterthiner\n              T.\n            \n          \n          International Conference on Learning Representations\n          \n          2021"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1056","DOI":"10.3390\/app16021056","article-title":"Synchronization, information, and brain dynamics in consciousness research","volume":"16","author":"Esteban","year":"2026","journal-title":"Appl. Sci"},{"key":"B30","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1109\/ACAIT63902.2024.11022253","article-title":"\u201cA multibranch cross-attention transformer model for psychiatric disorders diagnosis using multi-modal MRI data,\u201d","volume-title":"2024 8th Asian Conference on Artificial Intelligence Technology (ACAIT)","author":"Fan","year":"2024"},{"key":"B31","doi-asserted-by":"publisher","first-page":"906290","DOI":"10.3389\/fnins.2022.906290","article-title":"Explainable AI: A review of applications to neuroimaging data","volume":"16","author":"Farahani","year":"2022","journal-title":"Front. Neurosci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"127468","DOI":"10.1016\/j.neucom.2024.127468","article-title":"Sparsity in transformers: a systematic literature review","volume":"582","author":"Farina","year":"2024","journal-title":"Neurocomputing"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/netn_a_00204","article-title":"Edges in brain networks: Contributions to models of structure and function","volume":"6","author":"Faskowitz","year":"2022","journal-title":"Netw. Neurosci"},{"key":"B34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/EMBC58623.2025.11254125","article-title":"\u201cSelf-supervised transformer-based foundation model for functional magnetic resonance imaging,\u201d","volume-title":"2025 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","author":"Ferrante","year":"2025"},{"key":"B35","first-page":"528","article-title":"\u201cSpatio-temporal graph convolution for resting-state fMRI analysis,\u201d","volume-title":"Medical Image Computing and Computer Assisted Intervention-MICCAI 2020","author":"Gadgil","year":"2020"},{"key":"B36","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1109\/TMI.2024.3467384","article-title":"An explainable unified framework of spatio-temporal coupling learning with application to dynamic brain functional connectivity analysis","volume":"44","author":"Gao","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B37","doi-asserted-by":"publisher","first-page":"103861","DOI":"10.1016\/j.media.2025.103861","article-title":"3D masked autoencoder with spatiotemporal transformer for modeling of 4D fMRI data","volume":"107","author":"Gao","year":"2026","journal-title":"Med. Image Anal"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1162\/IMAG.a.1162","article-title":"NeuroConText: contrastive learning for neuroscience meta-analysis with rich text representation","author":"Ghayem","year":"2026","journal-title":"Imaging Neurosci."},{"key":"B39","first-page":"1","article-title":"\u201cNew interpretable patterns and discriminative features from brain functional network connectivity using dictionary learning,\u201d","author":"Ghayem","year":"2023","journal-title":"ICASSP 2023"},{"key":"B40","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1038\/s41586-023-05964-2","article-title":"A somato-cognitive action network alternates with effector regions in motor cortex","volume":"617","author":"Gordon","year":"2023","journal-title":"Nature"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.17720","article-title":"Mindformer: Semantic alignment of multi-subject fmri for brain decoding","author":"Han","year":"2024","journal-title":"arXiv"},{"key":"B42","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B43","doi-asserted-by":"publisher","first-page":"17702","DOI":"10.1109\/TNNLS.2025.3554755","article-title":"Hypergraph foundation model for brain disease diagnosis","volume":"36","author":"Han","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B44","first-page":"574","article-title":"\u201cUNETR: Transformers for 3D medical image segmentation,\u201d","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Hatamizadeh","year":"2022"},{"key":"B45","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.imed.2022.07.002","article-title":"Transformers in medical image analysis","volume":"3","author":"He","year":"2023","journal-title":"Intellig. Med"},{"key":"B46","doi-asserted-by":"publisher","first-page":"108762","DOI":"10.1016\/j.compbiomed.2024.108762","article-title":"A spatiotemporal graph transformer approach for Alzheimer's disease diagnosis with rs-fMRI","volume":"178","author":"He","year":"2024","journal-title":"Comput. Biol. Med"},{"key":"B47","doi-asserted-by":"publisher","first-page":"4010","DOI":"10.1109\/TMI.2024.3506734","article-title":"FM-APP: Foundation model for any phenotype prediction via fMRI to sMRI knowledge transfer","volume":"44","author":"He","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B48","doi-asserted-by":"publisher","first-page":"2727","DOI":"10.1109\/TNSRE.2024.3434343","article-title":"BrainNPT: Pre-training transformer networks for brain network classification","volume":"32","author":"Hu","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabilitat. Eng"},{"key":"B49","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TNSRE.2026.3658628","article-title":"Sub-connection learning for fMRI-based brain functional network","volume":"34","author":"Huang","year":"2026","journal-title":"IEEE Trans. Neural Syst. Rehabilitat. Eng"},{"key":"B50","doi-asserted-by":"publisher","first-page":"3058","DOI":"10.1002\/hbm.24580","article-title":"The spatial chronnectome reveals a dynamic interplay between functional segregation and integration","volume":"40","author":"Iraji","year":"2019","journal-title":"Hum. Brain Mapp"},{"key":"B51","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s12868-024-00854-3","article-title":"State-transition dynamics of resting-state functional magnetic resonance imaging data: model comparison and test-to-retest analysis","volume":"25","author":"Islam","year":"2024","journal-title":"BMC Neurosci"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.14005","article-title":"ASDFormer: a transformer with mixtures of pooling-classifier experts for robust autism diagnosis and biomarker discovery","author":"Izadi","year":"2025","journal-title":"arXiv"},{"key":"B53","doi-asserted-by":"publisher","first-page":"3410","DOI":"10.1002\/hbm.26289","article-title":"Enhancing the network specific individual characteristics in rs-fMRI functional connectivity by dictionary learning","volume":"44","author":"Jain","year":"2023","journal-title":"Hum. Brain Mapp"},{"key":"B54","first-page":"3543","article-title":"\u201cAttention is not explanation,\u201d","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Jain","year":"2019"},{"key":"B55","article-title":"Transformers for multimodal brain state decoding: Integrating functional magnetic resonance imaging data and medical metadata","author":"Jazi","year":"2025","journal-title":"arXiv [preprint]"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1101\/2025.09.02.25334737","article-title":"Interpretable transformer models for rs-fMRI epilepsy classification and biomarker discovery","author":"Jeyabose","year":"2025","journal-title":"medRxiv"},{"key":"B57","first-page":"469","article-title":"\u201cMindLink: Subject-agnostic Cross-Subject Brain Decoding Framework,\u201d","volume-title":"Proceedings of Medical Image Computing and Computer Assisted Intervention-MICCAI 2025","author":"Jung","year":"2025"},{"key":"B58","first-page":"618","article-title":"\u201cFBNETGEN: Task-aware GNN-based fMRI analysis via functional brain network generation,\u201d","volume-title":"Proceedings of The 5th International Conference on Medical Imaging with Deep Learning","author":"Kan","year":""},{"key":"B59","doi-asserted-by":"publisher","first-page":"25586","DOI":"10.52202\/068431-1855","article-title":"Brain network transformer","volume":"35","author":"Kan","year":"","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B60","first-page":"150","article-title":"\u201cBrainMT: a hybrid Mamba-transformer architecture for modeling long-range dependencies in functional MRI data,\u201d","volume-title":"Proceedings of Medical Image Computing and Computer Assisted Intervention-MICCAI 2025","author":"Kannan","year":"2025"},{"key":"B61","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1016\/j.neuroimage.2016.09.046","article-title":"BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopment","volume":"146","author":"Kawahara","year":"2017","journal-title":"Neuroimage"},{"key":"B62","doi-asserted-by":"publisher","first-page":"e70364","DOI":"10.1002\/hbm.70364","article-title":"St-DenseViT: a weakly supervised spatiotemporal vision transformer for dense prediction of dynamic brain networks","volume":"46","author":"Kazemivash","year":"2025","journal-title":"Hum. Brain Mapp"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.18314","article-title":"Brainsymphony: a parameter-efficient multimodal foundation model for brain dynamics with limited data","author":"Khajehnejad","year":"2025","journal-title":"arXiv"},{"key":"B64","first-page":"4314","article-title":"Learning dynamic graph representation of brain connectome with spatio-temporal attention","volume":"34","author":"Kim","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B65","first-page":"42015","article-title":"\u201cSwiFT: Swin 4D fMRI transformer,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Kim","year":"2023"},{"key":"B66","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1109\/TMI.2024.3448214","article-title":"Multi-scale spatial-temporal attention networks for functional connectome classification","volume":"44","author":"Kong","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B67","doi-asserted-by":"publisher","first-page":"00440","DOI":"10.1162\/imag_a_00440","article-title":"Predicting task-related brain activity from resting-state brain dynamics with fMRI transformer","volume":"3","author":"Kwon","year":"2025","journal-title":"Imaging Neurosci"},{"key":"B68","doi-asserted-by":"publisher","first-page":"5675","DOI":"10.1073\/pnas.89.12.5675","article-title":"Dynamic magnetic resonance imaging of human brain activity during primary sensory stimulation","volume":"89","author":"Kwong","year":"1992","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"B69","article-title":"\u201cScaling vision transformers for functional MRI with flat maps,\u201d","volume-title":"ICML","author":"Lane","year":"2026"},{"key":"B70","doi-asserted-by":"publisher","DOI":"10.1109\/NER61569.2025.11589005","article-title":"\u201cVoxelformer: Parameter-efficient multi-subject visual decoding from fMRI,\u201d","author":"Le","year":"2025","journal-title":"2025 12th International IEEE\/EMBS Conference on Neural Engineering (NER)"},{"key":"B71","doi-asserted-by":"publisher","first-page":"18062","DOI":"10.1109\/TNNLS.2023.3311195","article-title":"Site-invariant meta-modulation learning for multisite autism spectrum disorders diagnosis","volume":"35","author":"Lee","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B72","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ISBI60581.2025.10981292","article-title":"\u201cSelf-supervised graph transformer with contrastive learning for brain connectivity analysis towards improving autism detection,\u201d","volume-title":"2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)","author":"Leng","year":"2025"},{"key":"B73","doi-asserted-by":"publisher","first-page":"102233","DOI":"10.1016\/j.media.2021.102233","article-title":"BrainGNN: Interpretable brain graph neural network for fMRI analysis","volume":"74","author":"Li","year":"2021","journal-title":"Med. Image Anal"},{"key":"B74","doi-asserted-by":"publisher","first-page":"4772","DOI":"10.1002\/hbm.26415","article-title":"Accounting for temporal variability in functional magnetic resonance imaging improves prediction of intelligence","volume":"44","author":"Li","year":"2023","journal-title":"Hum. Brain Mapp"},{"key":"B75","doi-asserted-by":"publisher","first-page":"277","DOI":"10.3390\/brainsci16030277","article-title":"A dual-stream transformer with self-supervised contrastive training for fMRI-based autism spectrum disorder classification","volume":"16","author":"Li","year":"2026","journal-title":"Brain Sci"},{"key":"B76","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.aiopen.2022.10.001","article-title":"A survey of transformers","volume":"3","author":"Lin","year":"2022","journal-title":"AI Open"},{"key":"B77","doi-asserted-by":"publisher","first-page":"2358","DOI":"10.1002\/hbm.24528","article-title":"Modular preprocessing pipelines can reintroduce artifacts into fmri data","volume":"40","author":"Lindquist","year":"2019","journal-title":"Hum. Brain Mapp"},{"key":"B78","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.15978","article-title":"A survey on fMRI-based brain decoding for reconstructing multimodal stimuli","author":"Liu","year":"2025","journal-title":"arXiv"},{"key":"B79","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1038\/s42254-019-0040-8","article-title":"The physics of brain network structure, function and control","volume":"1","author":"Lynn","year":"2019","journal-title":"Nat. Rev. Phys"},{"key":"B80","first-page":"1","article-title":"\u201cGlacier: Glass-box transformer for interpretable dynamic neuroimaging,\u201d","author":"Mahmood","year":"2023","journal-title":"ICASSP 2023"},{"key":"B81","first-page":"895","article-title":"\u201cSelf-supervised transformers for fMRI representation,\u201d","volume-title":"Proceedings of The 5th International Conference on Medical Imaging with Deep Learning","author":"Malkiel","year":"2022"},{"key":"B82","doi-asserted-by":"publisher","first-page":"106791","DOI":"10.1016\/j.compbiomed.2023.106791","article-title":"MedViT: a robust vision transformer for generalized medical image classification","volume":"157","author":"Manzari","year":"2023","journal-title":"Comput. Biol. Med"},{"key":"B83","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41586-022-04492-9","article-title":"Reproducible brain-wide association studies require thousands of individuals","volume":"603","author":"Marek","year":"2022","journal-title":"Nature"},{"key":"B84","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s40708-026-00305-1","article-title":"Benchmarking resting state fMRI connectivity pipelines for classification: Robust accuracy despite processing variability in cross-site eye state prediction","volume":"13","author":"Medvedeva","year":"2026","journal-title":"Brain Inform"},{"key":"B85","doi-asserted-by":"publisher","first-page":"2469","DOI":"10.1016\/j.neuron.2023.04.023","article-title":"20 years of the default mode network: a review and synthesis","volume":"111","author":"Menon","year":"2023","journal-title":"Neuron"},{"key":"B86","doi-asserted-by":"publisher","first-page":"17","DOI":"10.3390\/brainsci15010017","article-title":"Graph neural networks in brain connectivity studies: methods, challenges, and future directions","volume":"15","author":"Mohammadi","year":"2025","journal-title":"Brain Sci"},{"key":"B87","doi-asserted-by":"publisher","DOI":"10.1162\/imag_a_00214","article-title":"Applications of interpretable deep learning in neuroimaging: a comprehensive review","author":"Munroe","year":"2024","journal-title":"Imag. Neurosci"},{"key":"B88","doi-asserted-by":"publisher","first-page":"102540","DOI":"10.1016\/j.media.2022.102540","article-title":"A transformer-based neural language model that synthesizes brain activation maps from free-form text queries","volume":"81","author":"Ngo","year":"2022","journal-title":"Med. Image Anal"},{"key":"B89","doi-asserted-by":"publisher","first-page":"129213","DOI":"10.1016\/j.neucom.2024.129213","article-title":"Brainformer: Mimic human visual brain functions to machine vision models via fMRI","volume":"620","author":"Nguyen","year":"2025","journal-title":"Neurocomputing"},{"key":"B90","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/EMBC58623.2025.11254044","article-title":"\u201cBrain network state transformer: Leveraging state functional connectivity for enhanced brain network analysis,\u201d","volume-title":"2025 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","author":"Nie","year":"2025"},{"key":"B91","first-page":"565","article-title":"\u201cBrainLM: A foundation model for brain activity recordings,\u201d","author":"Ortega Caro","year":"2024","journal-title":"International Conference on Learning Representations"},{"key":"B92","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1038\/s41586-023-06098-1","article-title":"Geometric constraints on human brain function","volume":"618","author":"Pang","year":"2023","journal-title":"Nature"},{"key":"B93","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.neuroimage.2016.12.061","article-title":"The dynamic functional connectome: state-of-the-art and perspectives","volume":"160","author":"Preti","year":"2017","journal-title":"Neuroimage"},{"key":"B94","doi-asserted-by":"publisher","DOI":"10.1162\/IMAG.a.1129","article-title":"Deep learning interpretability in neuroimaging: a comprehensive survey and methodological recommendations","author":"Rahman","year":"2026","journal-title":"Imag. Neurosci"},{"key":"B95","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/EMBC58623.2025.11254303","article-title":"\u201cNeuroMoE: a transformer-based mixture-of-experts framework for multi-modal neurological disorder classification,\u201d","volume-title":"2025 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","author":"Raza","year":"2025"},{"key":"B96","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1038\/s41592-025-02599-1","article-title":"DeepPrep: An accelerated, scalable and robust pipeline for neuroimaging preprocessing empowered by deep learning","volume":"22","author":"Ren","year":"2025","journal-title":"Nat. Methods"},{"key":"B97","first-page":"1","article-title":"\u201cModelling spatio-temporal features of task FMRI data via spatio-temporal fusion-transformer,\u201d","volume-title":"2024 IEEE International Symposium on Biomedical Imaging (ISBI)","author":"Ren","year":"2024"},{"key":"B98","doi-asserted-by":"publisher","DOI":"10.1162\/IMAG.a.1076","article-title":"From maps to models: a survey on the reliability of small studies of task-based fMRI","author":"Sadil","year":"2026","journal-title":"Imag. Neurosci"},{"key":"B99","doi-asserted-by":"publisher","first-page":"260","DOI":"10.3390\/brainsci13020260","article-title":"OViTAD: Optimized vision transformer to predict various stages of Alzheimer's disease using resting-state fMRI and structural MRI data","volume":"13","author":"Sarraf","year":"2023","journal-title":"Brain Sci"},{"key":"B100","doi-asserted-by":"publisher","first-page":"120562","DOI":"10.1016\/j.neuroimage.2024.120562","article-title":"Stochastic brain dynamics exhibits differential regional distribution and maturation-related changes","volume":"290","author":"Scarciglia","year":"2024","journal-title":"Neuroimage"},{"key":"B101","doi-asserted-by":"publisher","first-page":"3095","DOI":"10.1093\/cercor\/bhx179","article-title":"Local-global parcellation of the human cerebral cortex from intrinsic functional connectivity MRI","volume":"28","author":"Schaefer","year":"2018","journal-title":"Cereb. Cortex"},{"key":"B102","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1038\/s41583-023-00718-5","article-title":"Brain network communication: Concepts, models and applications","volume":"24","author":"Seguin","year":"2023","journal-title":"Nat. Rev. Neurosci"},{"key":"B103","article-title":"\u201cScalable diffusion transformer for conditional 4d fMRI synthesis,\u201d","author":"Seo","year":"2025","journal-title":"NeurIPS 2025 Workshop on Foundation Models for the Brain and Body"},{"key":"B104","doi-asserted-by":"publisher","first-page":"102802","DOI":"10.1016\/j.media.2023.102802","article-title":"Transformers in medical imaging: a survey","volume":"88","author":"Shamshad","year":"2023","journal-title":"Med. Image Anal"},{"key":"B105","doi-asserted-by":"publisher","first-page":"4388","DOI":"10.1109\/JBHI.2025.3538040","article-title":"Dynamic graph transformer for brain disorder diagnosis","volume":"29","author":"Shehzad","year":"2025","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B106","doi-asserted-by":"publisher","first-page":"98083","DOI":"10.52202\/079017-3113","article-title":"Neuro-vision to language: Enhancing brain recording-based visual reconstruction and language interaction","volume":"37","author":"Shen","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B107","doi-asserted-by":"publisher","first-page":"136147","DOI":"10.1016\/j.neulet.2021.136147","article-title":"Strategies for multivariate analyses of imaging genetics study in Alzheimer's disease","volume":"762","author":"Sheng","year":"2021","journal-title":"Neurosci. Lett"},{"key":"B108","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2023.1199312","article-title":"Self-supervised pretraining improves the performance of classification of task functional magnetic resonance imaging","author":"Shi","year":"2023","journal-title":"Front. Neurosci"},{"key":"B109","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1038\/s43856-025-01015-1","article-title":"Transformer-based structural connectivity networks for ADHD-related connectivity alterations","volume":"5","author":"Shi","year":"2025","journal-title":"Commun. Med"},{"key":"B110","doi-asserted-by":"publisher","first-page":"2370","DOI":"10.1109\/TMI.2024.3453419","article-title":"Knowledge-aware multisite adaptive graph transformer for brain disorder diagnosis","volume":"44","author":"Song","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B111","first-page":"136","article-title":"\u201cPredicting human brain states with transformer,\u201d","volume-title":"Medical Image Computing and Computer Assisted Intervention-MICCAI 2024 Workshops","author":"Sun","year":""},{"key":"B112","doi-asserted-by":"publisher","first-page":"8719","DOI":"10.1109\/JBHI.2025.3613793","article-title":"Voxel-level brain states prediction using swin transformer","volume":"29","author":"Sun","year":"","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B113","doi-asserted-by":"publisher","first-page":"29654","DOI":"10.52202\/075280-1290","article-title":"Brain encoding models based on multimodal transformers can transfer across language and vision","volume":"36","author":"Tang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B114","doi-asserted-by":"publisher","first-page":"108137","DOI":"10.1016\/j.neunet.2025.108137","article-title":"Graph neural networks for fMRI functional brain networks: a survey","volume":"194","author":"Tang","year":"2026","journal-title":"Neural Netw"},{"key":"B115","doi-asserted-by":"publisher","first-page":"103462","DOI":"10.1016\/j.media.2025.103462","article-title":"DSAM: A deep learning framework for analyzing temporal and spatial dynamics in brain networks","volume":"101","author":"Thapaliya","year":"2025","journal-title":"Med. Image Anal"},{"key":"B116","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1152\/jn.00338.2011","article-title":"The organization of the human cerebral cortex estimated by intrinsic functional connectivity","volume":"106","author":"Thomas Yeo","year":"2011","journal-title":"J. Neurophysiol"},{"key":"B117","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1109\/JBHI.2024.3471186","article-title":"Transformer3: A pure transformer framework for fMRI-based representations of human brain function","volume":"29","author":"Tian","year":"2025","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B118","article-title":"\u201cAttention is all you need,\u201d","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B119","doi-asserted-by":"publisher","DOI":"10.1162\/imag_a_00363","article-title":"Dynamic functional connectivity: why the controversy?","author":"Vidaurre","year":"2024","journal-title":"Imag. Neurosci"},{"key":"B120","doi-asserted-by":"publisher","first-page":"107557","DOI":"10.1016\/j.bspc.2025.107557","article-title":"ViT transfer learning for fMRI (VTFF): a highway to achieve superior performance for multi-classification of cognitive decline","volume":"104","author":"Wang","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"B121","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-026-01666-y","article-title":"Towards a general-purpose foundation model for functional MRI analysis","author":"Wang","year":"2026","journal-title":"Nat. Biomed. Eng"},{"key":"B122","doi-asserted-by":"crossref","first-page":"2639","DOI":"10.1109\/BIBM62325.2024.10821838","article-title":"\u201cLocal-global spatio-temporal encoding with adaptive brain region signal segmentation for mild cognitive impairment detection,\u201d","volume-title":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Wang","year":"2024"},{"key":"B123","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1162\/netn_a_00171","article-title":"Graph convolutional network for fMRI analysis based on connectivity neighborhood","volume":"5","author":"Wang","year":"2021","journal-title":"Netw. Neurosci"},{"key":"B124","doi-asserted-by":"publisher","first-page":"378","DOI":"10.3390\/brainsci16040378","article-title":"A multi-atlas dynamic connectivity transformer fused with 4D spatiotemporal modeling for autism spectrum disorder recognition","volume":"16","author":"Wang","year":"","journal-title":"Brain Sci"},{"key":"B125","doi-asserted-by":"publisher","first-page":"2241","DOI":"10.1109\/TBME.2019.2957921","article-title":"Spatial-temporal dependency modeling and network hub detection for functional MRI analysis via convolutional-recurrent network","volume":"67","author":"Wang","year":"2020","journal-title":"IEEE Trans. Biomed. Eng"},{"key":"B126","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2512.21881","article-title":"SLIM-brain: a data- and training-efficient foundation model for fMRI data analysis","author":"Wang","year":"","journal-title":"arXiv"},{"key":"B127","article-title":"\u201cOmni-fMRI: a universal atlas-free fMRI foundation model,\u201d","volume-title":"Forty-Third International Conference on Machine Learning","author":"Wang","year":""},{"key":"B128","doi-asserted-by":"publisher","first-page":"1322967","DOI":"10.3389\/fnins.2023.1322967","article-title":"Dynamic functional connectivity analysis with temporal convolutional network for attention deficit\/hyperactivity disorder identification","volume":"17","author":"Wang","year":"2023","journal-title":"Front. Neurosci"},{"key":"B129","first-page":"109","article-title":"\u201cTransBTS: Multimodal brain tumor segmentation using transformer,\u201d","volume-title":"Medical Image Computing and Computer Assisted Intervention-MICCAI 2021","author":"Wang","year":"2021"},{"key":"B130","doi-asserted-by":"publisher","DOI":"10.64898\/2025.11.30.691403","article-title":"Representation, alignment, and generation: A comprehensive survey of foundation models for non-invasive brain decoding","author":"Wang","year":"2026","journal-title":"bioRxiv"},{"key":"B131","volume-title":"Creative","author":"Watters","year":"2024"},{"key":"B132","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.02044","article-title":"A brain graph foundation model: Pre-training and prompt-tuning across broad atlases and disorders","author":"Wei","year":"2026","journal-title":"arXiv"},{"key":"B133","first-page":"4541","article-title":"\u201cBrainMoE: Cognition joint embedding via mixture-of-expert towards robust brain foundation model,\u201d","volume-title":"Advances in Neural Information Processing Systems, volume 38, Main Conference","author":"Wei","year":"2025"},{"key":"B134","doi-asserted-by":"publisher","first-page":"67826","DOI":"10.52202\/079017-2166","article-title":"Neuropath: A neural pathway transformer for joining the dots of human connectomes","volume":"37","author":"Wei","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B135","doi-asserted-by":"crossref","first-page":"11","DOI":"10.18653\/v1\/D19-1002","article-title":"\u201cAttention is not not explanation,\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":"Wiegreffe","year":"2019"},{"key":"B136","doi-asserted-by":"publisher","first-page":"133067","DOI":"10.1109\/ACCESS.2024.3445580","article-title":"fMRI-based static and dynamic functional connectivity analysis for post-stroke motor dysfunction patient: a review","volume":"12","author":"Wu","year":"2024","journal-title":"IEEE Access"},{"key":"B137","doi-asserted-by":"publisher","DOI":"10.64898\/2026.02.08.704658","article-title":"MAMBAxBrain: A multi-task neural framework linking brain functional dynamics to individual fingerprints, cognitive and disease states","author":"Xia","year":"2026","journal-title":"bioRxiv"},{"key":"B138","first-page":"46","article-title":"\u201cAdaptive embedding for long-range high-order dependencies via time-varying transformer on fMRI,\u201d","volume-title":"Proceedings of Medical Image Computing and Computer Assisted Intervention-MICCAI 2025","author":"Xue","year":"2025"},{"key":"B139","doi-asserted-by":"publisher","first-page":"2764","DOI":"10.1109\/TMI.2026.3662157","article-title":"Moving beyond functional connectivity: time-series modeling for fMRI-based brain disorder classification","volume":"45","author":"Yu","year":"2026","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B140","doi-asserted-by":"publisher","DOI":"10.31449\/inf.v50i5.12777","article-title":"Leveraging local and global features: A CNN-transformer hybrid for fMRI-based autism diagnosis","volume":"50","author":"Yu","year":"2026","journal-title":"Informatica"},{"key":"B141","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.09225","article-title":"Disentangling spatial-temporal functional brain networks via twin-transformers","author":"Yu","year":"2022","journal-title":"arXiv"},{"key":"B142","doi-asserted-by":"publisher","first-page":"e34245","DOI":"10.1016\/j.heliyon.2024.e34245","article-title":"STDCformer: Spatial-temporal dual-path cross-attention model for fMRI-based autism spectrum disorder identification","volume":"10","author":"Zhang","year":"2024","journal-title":"Heliyon"},{"key":"B143","first-page":"1","article-title":"\u201cClassiffication of mild cognitive impairment based on dynamic functional connectivity using spatio-temporal transformer,\u201d","volume-title":"2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)","author":"Zhang","year":""},{"key":"B144","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.1109\/TMI.2024.3486086","article-title":"Asynchronous functional brain network construction with spatiotemporal transformer for MCI classification","volume":"44","author":"Zhang","year":"","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B145","first-page":"352","article-title":"\u201cGraph disentanglement learning for fMRI analysis: decoupling disease, covariates, and individual variability,\u201d","volume-title":"Proceedings of Medical Image Computing and Computer Assisted Intervention-MICCAI 2025","author":"Zhang","year":""},{"key":"B146","doi-asserted-by":"publisher","first-page":"kkaf007","DOI":"10.1093\/psyrad\/kkaf007","article-title":"Advances in functional magnetic resonance imaging-based brain function mapping: a deep learning perspective","volume":"5","author":"Zhao","year":"2025","journal-title":"Psychoradiology"},{"key":"B147","doi-asserted-by":"publisher","first-page":"5114","DOI":"10.1109\/JBHI.2025.3631655","article-title":"4DfCF: 4D fMRI CrossFormer vision transformer","volume":"30","author":"Zheng","year":"2026","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B148","doi-asserted-by":"publisher","first-page":"4319","DOI":"10.1109\/TMI.2024.3421360","article-title":"Lcgnet: Local sequential feature coupling global representation learning for functional connectivity network analysis with fmri","volume":"43","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B149","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/978-3-031-78761-4_14","article-title":"\u201cSelf-supervised pre-training tasks for an fMRI time-series transformer in autism detection,\u201d","volume-title":"Machine Learning in Clinical Neuroimaging","author":"Zhou","year":"2025"},{"key":"B150","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICCWAMTIP64812.2024.10873788","article-title":"\u201cBraintransformer: Subject-wise patch embed transformer for cross-subject brain visual information decoding,\u201d","volume-title":"2024 21st International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","author":"Zongxin","year":"2024"}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2026.1869687\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T07:17:44Z","timestamp":1791357464000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2026.1869687\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":150,"alternative-id":["10.3389\/fninf.2026.1869687"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2026.1869687","relation":{},"ISSN":["1662-5196"],"issn-type":[{"value":"1662-5196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"article-number":"1869687"}}