{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T16:34:55Z","timestamp":1782491695006,"version":"3.54.5"},"reference-count":58,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T00:00:00Z","timestamp":1713312000000},"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><jats:title>Introduction<\/jats:title><jats:p>The blood oxygen level-dependent (BOLD) signal derived from functional neuroimaging is commonly used in brain network analysis and dementia diagnosis. Missing the BOLD signal may lead to bad performance and misinterpretation of findings when analyzing neurological disease. Few studies have focused on the restoration of brain functional time-series data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this paper, a novel <jats:italic>U<\/jats:italic>-shaped convolutional transformer GAN (UCT-GAN) model is proposed to restore the missing brain functional time-series data. The proposed model leverages the power of generative adversarial networks (GANs) while incorporating a <jats:italic>U<\/jats:italic>-shaped architecture to effectively capture hierarchical features in the restoration process. Besides, the multi-level temporal-correlated attention and the convolutional sampling in the transformer-based generator are devised to capture the global and local temporal features for the missing time series and associate their long-range relationship with the other brain regions. Furthermore, by introducing multi-resolution consistency loss, the proposed model can promote the learning of diverse temporal patterns and maintain consistency across different temporal resolutions, thus effectively restoring complex brain functional dynamics.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We theoretically tested our model on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and our experiments demonstrate that the proposed model outperforms existing methods in terms of both quantitative metrics and qualitative assessments. The model's ability to preserve the underlying topological structure of the brain functional networks during restoration is a particularly notable achievement.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Overall, the proposed model offers a promising solution for restoring brain functional time-series and contributes to the advancement of neuroscience research by providing enhanced tools for disease analysis and interpretation.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fncom.2024.1387004","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T04:41:48Z","timestamp":1713328908000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["U-shaped convolutional transformer GAN with multi-resolution consistency loss for restoring brain functional time-series and dementia diagnosis"],"prefix":"10.3389","volume":"18","author":[{"given":"Qiankun","family":"Zuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binghua","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixian","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,4,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13041-022-00937-4","article-title":"Blood-brain barrier: emerging trends on transport models and new-age strategies for therapeutics intervention against neurological disorders","volume":"15","author":"Alajangi","year":"2022","journal-title":"Mol. Brain"},{"key":"B2","doi-asserted-by":"publisher","first-page":"3043","DOI":"10.1038\/s41467-021-23311-9","article-title":"Predicting optimal deep brain stimulation parameters for Parkinson's disease using functional MRI and machine learning","volume":"12","author":"Boutet","year":"2021","journal-title":"Nat. Commun"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1174937","DOI":"10.3389\/fnins.2023.1174937","article-title":"Ara-net: an attention-aware retinal atrophy segmentation network coping with fundus images","volume":"17","author":"Chen","year":"2023","journal-title":"Front. Neurosci"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.04208","article-title":"Adversarial audio synthesis","author":"Donahue","year":"2018","journal-title":"arXiv"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.02633","article-title":"Real-valued (medical) time series generation with recurrent conditional gans","author":"Esteban","year":"2017","journal-title":"arXiv"},{"key":"B6","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.jneumeth.2018.12.012","article-title":"A survey on applications and analysis methods of functional magnetic resonance imaging for Alzheimer's disease","volume":"317","author":"Forouzannezhad","year":"2019","journal-title":"J. Neurosci. Methods"},{"key":"B7","doi-asserted-by":"publisher","first-page":"109155","DOI":"10.1016\/j.knosys.2022.109155","article-title":"Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation","volume":"250","author":"Hong","year":"2022","journal-title":"Knowl.-Based Syst"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2023.3266819","article-title":"3-D brain reconstruction by hierarchical shape-perception network from a single incomplete image","author":"Hu","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2941","DOI":"10.1002\/hbm.25369","article-title":"Diagnostic power of resting-state fMRI for detection of network connectivity in Alzheimer's disease and mild cognitive impairment: a systematic review","volume":"42","author":"Ibrahim","year":"2021","journal-title":"Hum. Brain Mapp"},{"key":"B10","first-page":"14745","article-title":"Transgan: two pure transformers can make one strong Gan, and that can scale up","volume":"34","author":"Jiang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B11","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":"B12","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1038\/s41572-021-00269-y","article-title":"Alzheimer disease","volume":"7","author":"Knopman","year":"2021","journal-title":"Nat. Rev. Dis. Primers"},{"key":"B13","doi-asserted-by":"publisher","first-page":"597","DOI":"10.3233\/JAD-180121","article-title":"Deep brain stimulation targeting the fornix for mild Alzheimer dementia (the advance trial): a two year follow-up including results of delayed activation","volume":"64","author":"Leoutsakos","year":"2018","journal-title":"J. Alzheimers Dis"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1130609","DOI":"10.3389\/fnins.2023.1130609","article-title":"Myopiadetr: end-to-end pathological myopia detection based on transformer using 2D fundus images","volume":"17","author":"Li","year":"2023","journal-title":"Front. Neurosci"},{"key":"B15","first-page":"133","article-title":"\u201cTTS-GAN: a transformer-based time-series generative adversarial network,\u201d","volume-title":"International Conference on Artificial Intelligence in Medicine","author":"Li","year":"2022"},{"key":"B16","doi-asserted-by":"publisher","first-page":"3632","DOI":"10.1109\/TKDE.2021.3130234","article-title":"DCT-GAN: dilated convolutional transformer-based GAN for time series anomaly detection","volume":"35","author":"Li","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B17","first-page":"1","article-title":"\u201cAct: adversarial convolutional transformer for time series forecasting,\u201d","volume-title":"2022 International Joint Conference on Neural Networks (IJCNN)","author":"Li","year":"2022"},{"key":"B18","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1038\/s41582-019-0145-9","article-title":"Long-term outcomes of deep brain stimulation in Parkinson disease","volume":"15","author":"Limousin","year":"2019","journal-title":"Nat. Rev. Neurol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1712","DOI":"10.3171\/2022.9.JNS221640","article-title":"Altered brain network centrality in Parkinson's disease patients after deep brain stimulation: a functional MRI study using a voxel-wise degree centrality approach","volume":"138","author":"Luo","year":"2022","journal-title":"J. Neurosurg"},{"key":"B20","article-title":"\u201cMultivariate time series imputation with generative adversarial networks,\u201d","author":"Luo","year":"2018","journal-title":"Advances in Neural Information Processing Systems 31 (NeurIPS 2018)"},{"key":"B21","first-page":"3094","article-title":"\u201cE2GAN: end-to-end generative adversarial network for multivariate time series imputation,\u201d","volume-title":"Proceedings of the 28th International Joint Conference on Artificial Intelligence","author":"Luo","year":"2019"},{"key":"B22","doi-asserted-by":"publisher","first-page":"5615","DOI":"10.1109\/TITS.2021.3055258","article-title":"Short-term traffic flow prediction for urban road sections based on time series analysis and lstm_bilstm method","volume":"23","author":"Ma","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.02089","article-title":"Transformer-based conditional generative adversarial network for multivariate time series generation","author":"Madane","year":"2022","journal-title":"arXiv"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1014","DOI":"10.1038\/s41587-020-0664-3","article-title":"Green light for deep brain stimulator incorporating neurofeedback","volume":"38","author":"Medtronic","year":"2020","journal-title":"Nat. Biotechnol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1611.09904","article-title":"Continuous recurrent neural networks with adversarial training","author":"Mogren","year":"2016","journal-title":"arXiv"},{"key":"B26","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1016\/j.tins.2023.03.009","article-title":"Insights and opportunities for deep brain stimulation as a brain circuit intervention","volume":"46","author":"Neumann","year":"2023","journal-title":"Trends Neurosci"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.05421","article-title":"Conditional sig-wasserstein gans for time series generation","author":"Ni","year":"2020","journal-title":"arXiv"},{"key":"B28","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1038\/s41378-019-0106-x","article-title":"Glassy carbon microelectrodes minimize induced voltages, mechanical vibrations, and artifacts in magnetic resonance imaging","volume":"5","author":"Nimbalkar","year":"2019","journal-title":"Microsyst. Nanoeng"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1093\/cercor\/bhab273","article-title":"Dynamic time warping identifies functionally distinct fMRI resting state cortical networks specific to VTA and SNC: a proof of concept","volume":"32","author":"Philips","year":"2022","journal-title":"Cereb. Cortex"},{"key":"B30","doi-asserted-by":"publisher","first-page":"7707","DOI":"10.1038\/s41467-022-34510-3","article-title":"Optimal deep brain stimulation sites and networks for stimulation of the fornix in Alzheimer's disease","volume":"13","author":"R\u00edos","year":"2022","journal-title":"Nat. Commun"},{"key":"B31","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1089\/brain.2020.0847","article-title":"Disrupted dynamic functional network connectivity among cognitive control networks in the progression of Alzheimer's disease","volume":"13","author":"Sendi","year":"2023","journal-title":"Brain Connect"},{"key":"B32","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1038\/s41386-023-01670-9","article-title":"The future of brain circuit-targeted therapeutics","volume":"49","author":"Siddiqi","year":"2023","journal-title":"Neuropsychopharmacology"},{"key":"B33","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s41398-023-02565-5","article-title":"Closing the loop between brain and electrical stimulation: towards precision neuromodulation treatments","volume":"13","author":"Soleimani","year":"2023","journal-title":"Transl. Psychiatry"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.11164","article-title":"Time-series transformer generative adversarial networks","author":"Srinivasan","year":"2022","journal-title":"arXiv"},{"key":"B35","unstructured":"Probabilistic transformer for time series analysis2359223608\n            TangB.\n            MattesonD. S.\n          Adv. Neural Inf. Process. Syst342021"},{"key":"B36","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1006\/nimg.2001.0978","article-title":"Automated anatomical labeling of activations in spm using a macroscopic anatomical parcellation of the MNI MRI single-subject brain","volume":"15","author":"Tzourio-Mazoyer","year":"2002","journal-title":"Neuroimage"},{"key":"B37","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1038\/s41583-023-00731-8","article-title":"Connectome-based modelling of neurodegenerative diseases: towards precision medicine and mechanistic insight","volume":"24","author":"Vogel","year":"2023","journal-title":"Natu. Rev. Neurosci"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1160040","DOI":"10.3389\/fnins.2023.1160040","article-title":"GDNET-EEG: an attention-aware deep neural network based on group depth-wise convolution for ssvep stimulation frequency recognition","volume":"17","author":"Wan","year":"","journal-title":"Front. Neurosci"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1148855","DOI":"10.3389\/fnins.2023.1148855","article-title":"Eegformer: a transformer-based brain activity classification method using eeg signal","volume":"17","author":"Wan","year":"","journal-title":"Front. Neurosci"},{"key":"B40","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1109\/JBHI.2023.3265006","article-title":"CellT-Net: a composite transformer method for 2-d cell instance segmentation","volume":"28","author":"Wan","year":"","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3318604","article-title":"C2bnet: a deep learning architecture with coupled composite backbone for parasitic egg detection in microscopic images","author":"Wan","year":"","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B42","doi-asserted-by":"publisher","first-page":"6569","DOI":"10.3390\/app13116569","article-title":"A wireless sensor system for diabetic retinopathy grading using mobilevit-plus and resnet-based hybrid deep learning framework","volume":"13","author":"Wan","year":"","journal-title":"Appl. Sci"},{"key":"B43","doi-asserted-by":"publisher","first-page":"386","DOI":"10.3389\/fnhum.2015.00386","article-title":"Gretna: a graph theoretical network analysis toolbox for imaging connectomics","volume":"9","author":"Wang","year":"2015","journal-title":"Front. Hum. Neurosci"},{"key":"B44","doi-asserted-by":"publisher","first-page":"8657","DOI":"10.1007\/s00521-021-06816-8","article-title":"Brain stroke lesion segmentation using consistent perception generative adversarial network","volume":"34","author":"Wang","year":"2022","journal-title":"Neural Comput. Appl"},{"key":"B45","doi-asserted-by":"publisher","first-page":"121352","DOI":"10.1016\/j.biomaterials.2021.121352","article-title":"Subdural neural interfaces for long-term electrical recording, optical microscopy and magnetic resonance imaging","volume":"281","author":"Wang","year":"2022","journal-title":"Biomaterials"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JTEHM.2018.2874887","article-title":"Classification of Alzheimer's disease, mild cognitive impairment and normal control subjects using resting-state fMRI based network connectivity analysis","volume":"6","author":"Wang","year":"2018","journal-title":"IEEE J. Transl. Eng. Health Med"},{"key":"B47","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1111\/jon.13063","article-title":"Functional magnetic resonance imaging, deep learning, and Alzheimer's disease: a aystematic review","volume":"33","author":"Warren","year":"2023","journal-title":"J. Neuroimaging"},{"key":"B48","unstructured":"Adversarial sparse transformer for time series forecasting1710517115\n            WuS.\n            XiaoX.\n            DingQ.\n            ZhaoP.\n            WeiY.\n            HuangJ.\n          Adv. Neural Inf. Process. Syst332020"},{"key":"B49","doi-asserted-by":"publisher","first-page":"104276","DOI":"10.1016\/j.bspc.2022.104276","article-title":"Generative adversarial network with transformer generator for boosting ecg classification","volume":"80","author":"Xia","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B50","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.3390\/life13071472","article-title":"Exploring the frontiers of neuroimaging: a review of recent advances in understanding brain functioning and disorders","volume":"13","author":"Yen","year":"2023","journal-title":"Life"},{"key":"B51","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1016\/j.neucom.2020.05.113","article-title":"Deep learning for brain disorder diagnosis based on fMRI images","volume":"469","author":"Yin","year":"2022","journal-title":"Neurocomputing"},{"key":"B52","article-title":"\u201cTime-series generative adversarial networks,\u201d","author":"Yoon","year":"2019","journal-title":"Advances in Neural Information Processing Systems 32 (NeurIPS 2019)"},{"key":"B53","doi-asserted-by":"publisher","first-page":"8802","DOI":"10.1109\/TNNLS.2022.3153088","article-title":"Fine perceptive GANS for brain MR image super-resolution in wavelet domain","volume":"34","author":"You","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B54","doi-asserted-by":"crossref","first-page":"2114","DOI":"10.1145\/3447548.3467401","article-title":"\u201cA transformer-based framework for multivariate time series representation learning,\u201d","volume-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","author":"Zerveas","year":"2021"},{"key":"B55","unstructured":"Improved transformer for high-resolution gans1836718380\n            ZhaoL.\n            ZhangZ.\n            ChenT.\n            MetaxasD.\n            ZhangH.\n          Adv. Neural Inf. Process. Syst342021"},{"key":"B56","doi-asserted-by":"publisher","first-page":"1087176","DOI":"10.3389\/fnins.2022.1087176","article-title":"Constructing brain functional network by adversarial temporal-spatial aligned transformer for early ad analysis","volume":"16","author":"Zuo","year":"2022","journal-title":"Front. Neurosci"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3344641","article-title":"Prior-guided adversarial learning with hypergraph for predicting abnormal connections in Alzheimer's disease","author":"Zuo","year":"2024","journal-title":"IEEE Trans. Cybern"},{"key":"B58","doi-asserted-by":"publisher","first-page":"4017","DOI":"10.1109\/TNSRE.2023.3323432","article-title":"Brain structure-function fusing representation learning using adversarial decomposed-vae for analyzing MCI","volume":"31","author":"Zuo","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2024.1387004\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T04:41:55Z","timestamp":1713328915000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2024.1387004\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,17]]},"references-count":58,"alternative-id":["10.3389\/fncom.2024.1387004"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2024.1387004","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,17]]},"article-number":"1387004"}}