{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T05:50:08Z","timestamp":1791352208021,"version":"4.3.1"},"reference-count":42,"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\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Functional brain time-series classification is constrained by small clinical cohorts. Handcrafted features are sample-efficient but discard temporal detail; end-to-end networks must estimate many temporal parameters from limited labels; and frozen time-series foundation models reduce that estimation burden but typically encode each channel independently, leaving coordinated activity across brain regions unmodeled.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We introduce the Frozen Temporal-Hypergraph Network (FroHyNet), an asymmetric parallel framework that preserves channel-wise temporal representations from a frozen MantisV2 encoder while a trainable spatio-temporal hypergraph branch learns topology-aware spatial corrections. Bottleneck-mix Top-K (BM-TopK) then residual-injects these corrections only along selected channel and latent-feature axes, treating the spatial stream as a selective update rather than a dense overwrite of the temporal representation. We conduct five-fold cross-validation across two functional near-infrared spectroscopy (fNIRS) and three functional magnetic resonance imaging (fMRI) datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>FroHyNet achieves the best average accuracy and area under the receiver-operating-characteristic curve (AUC) among methods evaluated on all five datasets, while keeping the trainable-parameter count well below those of from-scratch temporal networks. Gains are concentrated on fNIRS, with more modest improvements on the smaller fMRI cohorts. Branch ablations indicate dataset-dependent complementarity between the two streams, and fusion ablations on HC-D favor BM-TopK over the evaluated dense and recurrent alternatives.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1966334","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T04:53:13Z","timestamp":1791348793000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FroHyNet: frozen temporal priors and trainable hypergraph fusion for brain time-series classification"],"prefix":"10.3389","volume":"13","author":[{"given":"Mingyao","family":"Gao","sequence":"first","affiliation":[{"name":"College of Biomedical Engineering, Sichuan University","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"He","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering, Sichuan University","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Li","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering, Sichuan University","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yajing","family":"Meng","sequence":"additional","affiliation":[{"name":"Mental Health Center, West China Hospital, Sichuan University and Sichuan Clinical Medical Research Center for Mental Disorders","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Mental Health Center, West China Hospital, Sichuan University and Sichuan Clinical Medical Research Center for Mental Disorders","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changjian","family":"Qiu","sequence":"additional","affiliation":[{"name":"Mental Health Center, West China Hospital, Sichuan University and Sichuan Clinical Medical Research Center for Mental Disorders","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering, Sichuan University","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1006\/nimg.2002.1227","article-title":"A quantitative comparison of simultaneous BOLD FMRI and NIRS recordings during functional brain activation","volume":"17","author":"Strangman","year":"2002","journal-title":"Neuroimage"},{"key":"B2","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1016\/j.tins.2022.08.004","article-title":"Neurovascular coupling: motive unknown","volume":"45","author":"Drew","year":"2022","journal-title":"Trends Neurosci"},{"key":"B3","doi-asserted-by":"publisher","first-page":"4213","DOI":"10.1002\/hbm.24241","article-title":"Statistical harmonization corrects site effects in functional connectivity measurements from multi-site fMRI data","volume":"39","author":"Yu","year":"2018","journal-title":"Hum Brain Mapp"},{"key":"B4","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3389\/fnhum.2015.00003","article-title":"fNIRS-based brain-computer interfaces: a review","volume":"9","author":"Naseer","year":"2015","journal-title":"Front Hum Neurosci"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.1109\/TBME.2021.3122813","article-title":"Constructing multi-view high-order functional connectivity networks for diagnosis of autism spectrum disorder","volume":"69","author":"Zhao","year":"2022","journal-title":"IEEE Trans Biomed Eng"},{"key":"B6","author":"Liu","year":""},{"key":"B7","author":"Wang","year":""},{"key":"B8","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.neuroimage.2017.06.061","article-title":"Cross-validation failure: small sample sizes lead to large error bars","volume":"180","author":"Varoquaux","year":"2018","journal-title":"Neuroimage"},{"key":"B9","author":"Feng","year":""},{"key":"B10","author":"Kipf","year":""},{"key":"B11","author":"Feofanov","year":""},{"key":"B12","author":"Goswami","year":""},{"key":"B13","article-title":"Nutime: Numerically multi-scaled embedding for large-scale time-series pretraining","author":"Lin","year":"2024","journal-title":"Trans Mach Learn Res. arXiv [Preprint]. arXiv:2310.07402"},{"key":"B14","author":"Feofanov","year":""},{"key":"B15","doi-asserted-by":"publisher","first-page":"4314","DOI":"10.48550\/arXiv.2105.13495","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":"B16","doi-asserted-by":"publisher","first-page":"103632","DOI":"10.1016\/j.media.2025.103632","article-title":"Similarity-guided multi-view functional brain network fusion","volume":"105","author":"Li","year":"2025","journal-title":"Med Image Anal"},{"key":"B17","doi-asserted-by":"publisher","first-page":"3501","DOI":"10.1109\/TNSRE.2023.3309847","article-title":"Multi-scale dynamic graph learning for brain disorder detection with functional MRI","volume":"31","author":"Ma","year":"2023","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"B18","author":"Chen","year":""},{"key":"B19","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.neuroimage.2013.05.004","article-title":"A review on continuous wave functional near-infrared spectroscopy and imaging instrumentation and methodology","volume":"85","author":"Scholkmann","year":"2014","journal-title":"Neuroimage"},{"key":"B20","author":"He","year":""},{"key":"B21","author":"Yu","year":""},{"key":"B22","author":"Das","year":""},{"key":"B23","author":"Nie","year":""},{"key":"B24","author":"Yu","year":""},{"key":"B25","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":"B26","doi-asserted-by":"publisher","first-page":"2559","DOI":"10.1109\/JBHI.2022.3140531","article-title":"Transformer model for functional near-infrared spectroscopy classification","volume":"26","author":"Wang","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1871","DOI":"10.1109\/TII.2025.3632147","article-title":"A unified fNIRS classification framework informed by local brain activation patterns","volume":"22","author":"Wang","year":"2025","journal-title":"IEEE Trans Ind Inform"},{"key":"B28","doi-asserted-by":"publisher","first-page":"109706","DOI":"10.1016\/j.bspc.2026.109706","article-title":"Mamba neurodynamics integration net: a cross-task highly generalizable fNIRS-based brain decoding framework","volume":"118","author":"Han","year":"2026","journal-title":"Biomed Signal Process Control"},{"key":"B29","author":"Veli\u010dkovi\u0107","year":""},{"key":"B30","first-page":"1601","article-title":"\u201cLearning with hypergraphs: Clustering, classification, and embedding.\u201d In: Sch\u00f6lkopf B, Platt J, Hofmann T, editors","volume-title":"Advances in Neural Information Processing Systems 19","author":"Zhou","year":"2006"},{"key":"B31","author":"Xu","year":""},{"key":"B32","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B33","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1159\/000545381","article-title":"Yoga asana increases prefrontal cortex activity and reduces resting-state functional connectivity","volume":"32","author":"Goodrick","year":"2025","journal-title":"Complement Med Res"},{"key":"B34","doi-asserted-by":"publisher","first-page":"21841","DOI":"10.52202\/075280-0955","article-title":"Data-driven network neuroscience: on data collection and benchmark","volume":"36","author":"Xu","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"key":"B35","doi-asserted-by":"publisher","first-page":"e0188196","DOI":"10.1371\/journal.pone.0188196","article-title":"Exploring the reproducibility of functional connectivity alterations in Parkinson\u2019s disease","volume":"12","author":"Badea","year":"2017","journal-title":"PLoS One"},{"key":"B36","doi-asserted-by":"publisher","first-page":"025008","DOI":"10.1117\/1.NPh.8.2.025008","article-title":"Analysis methods for measuring passive auditory fNIRS responses generated by a block-design paradigm","volume":"8","author":"Luke","year":"2021","journal-title":"Neurophotonics"},{"key":"B37","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.neuroimage.2018.09.025","article-title":"Temporal derivative distribution repair (TDDR): a motion correction method for fNIRS","volume":"184","author":"Fishburn","year":"2019","journal-title":"Neuroimage"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1433","DOI":"10.1088\/0031-9155\/33\/12\/008","article-title":"Estimation of optical pathlength through tissue from direct time of flight measurement","volume":"33","author":"Delpy","year":"1988","journal-title":"Phys Med Biol"},{"key":"B39","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1016\/j.neuroimage.2005.08.065","article-title":"A temporal comparison of BOLD, ASL, and NIRS hemodynamic responses to motor stimuli in adult humans","volume":"29","author":"Huppert","year":"2006","journal-title":"Neuroimage"},{"key":"B40","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":"B41","author":"Loshchilov","year":""},{"key":"B42","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J Mach Learn Res"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1966334\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T04:53:15Z","timestamp":1791348795000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1966334\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":42,"alternative-id":["10.3389\/fmed.2026.1966334"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1966334","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"article-number":"1966334"}}