{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T20:23:42Z","timestamp":1787862222262,"version":"build-2784847793"},"reference-count":39,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"vor","delay-in-days":218,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate measurement of physiological signals such as respiration and cardiac activity is essential for modeling physiological confounds in BOLD-fMRI data. However, external monitoring devices such as respiratory belts and photoplethysmographs often suffer from signal loss, noise, or incomplete recordings, and many fMRI datasets lack physiological measurements altogether due to practical constraints. In this work, we propose a data-driven framework to reconstruct respiratory variation (RV) and heart rate variation (HRV) directly from resting-state fMRI data using a hybrid machine learning architecture that combines one-dimensional convolutional neural networks (1D-CNN) with gated recurrent units (GRUs). The model processes BOLD signals from 630 regions of interest (ROIs), spanning cortical and subcortical gray matter, white matter, and cerebrospinal fluid. For RV estimation, six head motion parameters were included as additional inputs to capture motion-related physiological information. The proposed method was trained and evaluated on three cohorts across the lifespan from the Human Connectome Project (HCP), including HCP in Development (HCP-D, ages 5\u201321 years), HCP in Young Adults (HCP-YA, ages 22\u201335 years), and HCP in Aging (HCP-A, ages 36\u2013100 years). Age-specific architectural tuning was applied to accommodate developmental, neurovascular, and physiological variability across these populations. When compared against established CNN- and RNN-based baselines under matched preprocessing and native temporal resolution, the proposed architecture achieved consistent performance gains across all evaluation metrics. The largest relative improvements were observed for error-based and temporal alignment metrics, with MAE, MSE, and DTW reduced by approximately 7\u201310%, indicating lower absolute reconstruction error and improved temporal fidelity, while correlation-based improvements were more modest (approximately 5\u20137%). These results demonstrate the feasibility and effectiveness of reconstructing RV and HRV directly from fMRI time series using spatially and temporally enriched neural architectures. Building on earlier efforts in this domain, the proposed framework extends prior work through evaluation across multiple cohorts, broader anatomical coverage, and enhanced modeling capacity, offering a robust alternative for physiological modeling in the absence of external recordings.<\/jats:p>","DOI":"10.1162\/imag.a.1346","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T20:01:46Z","timestamp":1786132906000},"update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving respiratory and heart rate variation estimation from resting-state BOLD fMRI across the lifespan using a functionally informed, tissue-aware deep learning framework"],"prefix":"10.1162","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2727-4557","authenticated-orcid":false,"given":"Abdoljalil","family":"Addeh","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Schulich School of Engineering, University of Calgary, Calgary, Canada"},{"name":"Department of Electrical & Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, Canada"},{"name":"Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Canada"},{"name":"Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6676-4992","authenticated-orcid":false,"given":"Karen","family":"Ardila","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Schulich School of Engineering, University of Calgary, Calgary, Canada"},{"name":"Department of Electrical & Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, Canada"},{"name":"Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Canada"},{"name":"Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5526-6707","authenticated-orcid":false,"given":"Pattarawut","family":"Charatpangoon","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Schulich School of Engineering, University of Calgary, Calgary, Canada"},{"name":"Department of Electrical & Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, Canada"},{"name":"Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Canada"},{"name":"Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ethan","family":"Church","sequence":"additional","affiliation":[{"name":"Department of Computer Science, McGill University, Montr\u00e9al, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8949-1197","authenticated-orcid":false,"given":"Rebecca J.","family":"Williams","sequence":"additional","affiliation":[{"name":"Brain-Behaviour Research Group, University of New England, Armidale, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8924-683X","authenticated-orcid":false,"given":"G. Bruce","family":"Pike","sequence":"additional","affiliation":[{"name":"Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Canada"},{"name":"Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, Canada"},{"name":"Department of Clinical Neurosciences, Cumming School of Medicine, University of Calgary, Calgary, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5421-3536","authenticated-orcid":false,"given":"M. Ethan","family":"MacDonald","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Schulich School of Engineering, University of Calgary, Calgary, Canada"},{"name":"Department of Electrical & Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, Canada"},{"name":"Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Canada"},{"name":"Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2026,8,27]]},"reference":[{"key":"2026082715555890700_IMAG.a.1346-b1","doi-asserted-by":"crossref","first-page":"119904","DOI":"10.1016\/j.neuroimage.2023.119904","article-title":"Direct machine learning reconstruction of respiratory variation waveforms from resting state fMRI data in a pediatric population","volume":"269","author":"Addeh","year":"2023","journal-title":"NeuroImage"},{"issue":"3","key":"2026082715555890700_IMAG.a.1346-b2","doi-asserted-by":"crossref","first-page":"1365","DOI":"10.1002\/mrm.30330","article-title":"Machine learning-based estimation of respiratory fluctuations in a healthy adult population using resting state BOLD fMRI and head motion parameters","volume":"93","author":"Addeh","year":"2025","journal-title":"Magnetic Resonance in Medicine"},{"issue":"7","key":"2026082715555890700_IMAG.a.1346-b3","doi-asserted-by":"crossref","first-page":"e70076","DOI":"10.1002\/nbm.70076","article-title":"Physiological confounds in BOLD-fMRI and their correction","volume":"38","author":"Addeh","year":"2025","journal-title":"NMR in Biomedicine"},{"key":"2026082715555890700_IMAG.a.1346-b4","doi-asserted-by":"crossref","unstructured":"Bayrak, R. G., Hansen, C. B., Salas, J. A., Ahmed, N., Lyu, I., Huo, Y., & Chang, C. (2021). From brain to body: Learning low-frequency respiration and cardiac signals from fMRI dynamics. Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021, Cham. https:\/\/doi.org\/10.1007\/978-3-030-87234-2_52","DOI":"10.1007\/978-3-030-87234-2_52"},{"key":"2026082715555890700_IMAG.a.1346-b5","doi-asserted-by":"crossref","DOI":"10.1162\/IMAG.a.163","article-title":"DeepPhysioRecon: Tracing peripheral physiology in low frequency fMRI dynamics","volume":"3","author":"Bayrak","year":"2025","journal-title":"Imaging Neuroscience"},{"key":"2026082715555890700_IMAG.a.1346-b6","doi-asserted-by":"crossref","unstructured":"Bayrak, R. G., Salas, J. A., Huo, Y., & Chang, C. (2020). A deep pattern recognition approach for inferring respiratory volume fluctuations from fMRI data. Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020, Cham. https:\/\/doi.org\/10.1007\/978-3-030-59728-3_42","DOI":"10.1007\/978-3-030-59728-3_42"},{"issue":"1","key":"2026082715555890700_IMAG.a.1346-b7","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.neuroimage.2007.04.042","article-title":"A component based noise correction method (CompCor) for BOLD and perfusion based fMRI","volume":"37","author":"Behzadi","year":"2007","journal-title":"NeuroImage"},{"issue":"6","key":"2026082715555890700_IMAG.a.1346-b8","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1111\/j.1469-8986.1997.tb02140.x","article-title":"Heart rate variability: Origins, methods, and interpretive caveats","volume":"34","author":"Berntson","year":"1997","journal-title":"Psychophysiology"},{"issue":"4","key":"2026082715555890700_IMAG.a.1346-b9","doi-asserted-by":"crossref","first-page":"1536","DOI":"10.1016\/j.neuroimage.2006.02.048","article-title":"Separating respiratory-variation-related fluctuations from neuronal-activity-related fluctuations in fMRI","volume":"31","author":"Birn","year":"2006","journal-title":"NeuroImage"},{"issue":"2","key":"2026082715555890700_IMAG.a.1346-b10","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1016\/j.neuroimage.2007.11.059","article-title":"The respiration response function: The temporal dynamics of fMRI signal fluctuations related to changes in respiration","volume":"40","author":"Birn","year":"2008","journal-title":"NeuroImage"},{"key":"2026082715555890700_IMAG.a.1346-b11","volume-title":"Pattern recognition and machine learning","author":"Bishop","year":"2006"},{"issue":"3","key":"2026082715555890700_IMAG.a.1346-b12","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1016\/j.neuroimage.2008.09.029","article-title":"Influence of heart rate on the BOLD signal: The cardiac response function","volume":"44","author":"Chang","year":"2009","journal-title":"NeuroImage"},{"issue":"4","key":"2026082715555890700_IMAG.a.1346-b13","doi-asserted-by":"crossref","first-page":"1381","DOI":"10.1016\/j.neuroimage.2009.04.048","article-title":"Relationship between respiration, end-tidal CO2, and BOLD signals in resting-state fMRI","volume":"47","author":"Chang","year":"2009","journal-title":"NeuroImage"},{"key":"2026082715555890700_IMAG.a.1346-b14","doi-asserted-by":"crossref","first-page":"116707","DOI":"10.1016\/j.neuroimage.2020.116707","article-title":"Resting-state \u201cphysiological networks","volume":"213","author":"Chen","year":"2020","journal-title":"NeuroImage"},{"issue":"5997","key":"2026082715555890700_IMAG.a.1346-b15","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1126\/science.1194144","article-title":"Prediction of individual brain maturity using fMRI","volume":"329","author":"Dosenbach","year":"2010","journal-title":"Science"},{"key":"2026082715555890700_IMAG.a.1346-b16","doi-asserted-by":"crossref","first-page":"116400","DOI":"10.1016\/j.neuroimage.2019.116400","article-title":"Correction of respiratory artifacts in MRI head motion estimates","volume":"208","author":"Fair","year":"2020","journal-title":"NeuroImage"},{"issue":"7615","key":"2026082715555890700_IMAG.a.1346-b17","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1038\/nature18933","article-title":"A multi-modal parcellation of human cerebral cortex","volume":"536","author":"Glasser","year":"2016","journal-title":"Nature"},{"key":"2026082715555890700_IMAG.a.1346-b18","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.neuroimage.2014.10.031","article-title":"Mapping the end-tidal CO2 response function in the resting-state BOLD fMRI signal: Spatial specificity, test\u2013retest reliability and effect of fMRI sampling rate","volume":"104","author":"Golestani","year":"2015","journal-title":"NeuroImage"},{"key":"2026082715555890700_IMAG.a.1346-b19","doi-asserted-by":"crossref","first-page":"116874","DOI":"10.1016\/j.neuroimage.2020.116874","article-title":"Controlling for the effect of arterial-CO2 fluctuations in resting-state fMRI: Comparing end-tidal CO2 clamping and retroactive CO2 correction","volume":"216","author":"Golestani","year":"2020","journal-title":"NeuroImage"},{"key":"2026082715555890700_IMAG.a.1346-b20","doi-asserted-by":"crossref","first-page":"1024","DOI":"10.3389\/fnins.2019.01024","article-title":"White matter fMRI activation cannot be treated as a nuisance regressor: Overcoming a historical blind spot","volume":"13","author":"Grajauskas","year":"2019","journal-title":"Frontiers in Neuroscience"},{"key":"2026082715555890700_IMAG.a.1346-b21","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1016\/j.neuroimage.2018.09.060","article-title":"Extending the Human Connectome Project across ages: Imaging protocols for the Lifespan Development and Aging projects","volume":"183","author":"Harms","year":"2018","journal-title":"NeuroImage"},{"issue":"1","key":"2026082715555890700_IMAG.a.1346-b22","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1016\/j.neuroimage.2007.07.053","article-title":"Tract probability maps in stereotaxic spaces: Analyses of white matter anatomy and tract-specific quantification","volume":"39","author":"Hua","year":"2008","journal-title":"Neuroimage"},{"issue":"6735","key":"2026082715555890700_IMAG.a.1346-b23","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1038\/20924","article-title":"Multifractality in human heartbeat dynamics","volume":"399","author":"Ivanov","year":"1999","journal-title":"Nature"},{"key":"2026082715555890700_IMAG.a.1346-b24","doi-asserted-by":"crossref","first-page":"118838","DOI":"10.1016\/j.neuroimage.2021.118838","article-title":"Filtering respiratory motion artifact from resting state fMRI data in infant and toddler populations","volume":"247","author":"Kaplan","year":"2022","journal-title":"NeuroImage"},{"issue":"12","key":"2026082715555890700_IMAG.a.1346-b25","doi-asserted-by":"crossref","first-page":"2641","DOI":"10.1161\/01.STR.29.12.2641","article-title":"Functional magnetic resonance imaging of regional cerebral blood oxygenation changes during breath holding","volume":"29","author":"Kastrup","year":"1998","journal-title":"Stroke"},{"key":"2026082715555890700_IMAG.a.1346-b26","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-6849-3","volume-title":"Applied predictive modeling","author":"Kuhn","year":"2013"},{"issue":"2\u20133","key":"2026082715555890700_IMAG.a.1346-b27","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.schres.2005.11.020","article-title":"Decreased volume of left and total anterior insular lobule in schizophrenia","volume":"83","author":"Makris","year":"2006","journal-title":"Schizophrenia Research"},{"issue":"6","key":"2026082715555890700_IMAG.a.1346-b28","doi-asserted-by":"crossref","first-page":"2765","DOI":"10.1152\/jappl.1994.76.6.2765","article-title":"Ventilatory variability induced by spontaneous variations of PaCO2 in humans","volume":"76","author":"Modarreszadeh","year":"1994","journal-title":"Journal of Applied Physiology (1985)"},{"key":"2026082715555890700_IMAG.a.1346-b29","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/j.neuroimage.2013.04.001","article-title":"Resting-state fMRI confounds and cleanup","volume":"80","author":"Murphy","year":"2013","journal-title":"Neuroimage"},{"issue":"7","key":"2026082715555890700_IMAG.a.1346-b30","doi-asserted-by":"crossref","first-page":"3575","DOI":"10.1093\/cercor\/bhac293","article-title":"Parcellating the human brain using resting-state dynamic functional connectivity","volume":"33","author":"Peng","year":"2023","journal-title":"Cerebral Cortex"},{"key":"2026082715555890700_IMAG.a.1346-b31","doi-asserted-by":"crossref","first-page":"116041","DOI":"10.1016\/j.neuroimage.2019.116041","article-title":"Distinctions among real and apparent respiratory motions in human fMRI data","volume":"201","author":"Power","year":"2019","journal-title":"Neuroimage"},{"key":"2026082715555890700_IMAG.a.1346-b32","doi-asserted-by":"crossref","first-page":"117459","DOI":"10.1016\/j.neuroimage.2020.117459","article-title":"Reconstruction of respiratory variation signals from fMRI data","volume":"225","author":"Salas","year":"2021","journal-title":"NeuroImage"},{"issue":"2","key":"2026082715555890700_IMAG.a.1346-b33","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/j.neuroimage.2007.07.037","article-title":"Low-frequency fluctuations in the cardiac rate as a source of variance in the resting-state fMRI BOLD signal","volume":"38","author":"Shmueli","year":"2007","journal-title":"NeuroImage"},{"issue":"1","key":"2026082715555890700_IMAG.a.1346-b34","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1038\/s41597-022-01231-7","article-title":"Neurocognitive aging data release with behavioral, structural and multi-echo functional MRI measures","volume":"9","author":"Spreng","year":"2022","journal-title":"Scientific Data"},{"issue":"8","key":"2026082715555890700_IMAG.a.1346-b35","doi-asserted-by":"crossref","first-page":"1041","DOI":"10.1164\/ajrccm.165.8.2104100","article-title":"Influence of chemoreflexes on respiratory variability in healthy subjects","volume":"165","author":"Van den Aardweg","year":"2002","journal-title":"American Journal of Respiratory and Critical Care Medicine"},{"key":"2026082715555890700_IMAG.a.1346-b36","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.neuroimage.2013.05.041","article-title":"The WU-Minn human connectome project: An overview","volume":"80","author":"Van Essen","year":"2013","journal-title":"NeuroImage"},{"key":"2026082715555890700_IMAG.a.1346-b37","doi-asserted-by":"crossref","unstructured":"Wang, S., Xu, Z., Lochard, L. M., Li, Y., Fan, J., Chen, J. E., Huo, Y., Mather, M., Bayrak, R. G., & Chang, C. (2025). Reconstructing physiological signals from fMRI across the adult lifespan. Medical Imaging 2025: Image Processing. https:\/\/doi.org\/10.1117\/12.3046980","DOI":"10.1117\/12.3046980"},{"issue":"4","key":"2026082715555890700_IMAG.a.1346-b38","doi-asserted-by":"crossref","first-page":"1652","DOI":"10.1016\/j.neuroimage.2003.11.025","article-title":"Resting fluctuations in arterial carbon dioxide induce significant low frequency variations in BOLD signal","volume":"21","author":"Wise","year":"2004","journal-title":"NeuroImage"},{"key":"2026082715555890700_IMAG.a.1346-b39","doi-asserted-by":"crossref","first-page":"120038","DOI":"10.1016\/j.neuroimage.2023.120038","article-title":"Comparing end-tidal CO2, respiration volume per time (RVT), and average gray matter signal for mapping cerebrovascular reactivity amplitude and delay with breath-hold task BOLD fMRI","volume":"272","author":"Zvolanek","year":"2023","journal-title":"NeuroImage"}],"container-title":["Imaging Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/imag\/article-pdf\/doi\/10.1162\/IMAG.a.1346\/2619993\/imag.a.1346.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/imag\/article-pdf\/doi\/10.1162\/IMAG.a.1346\/2619993\/imag.a.1346.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T19:56:17Z","timestamp":1787860577000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/imag\/article\/doi\/10.1162\/IMAG.a.1346\/138080\/Improving-respiratory-and-heart-rate-variation"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1162\/imag.a.1346","relation":{},"ISSN":["2837-6056"],"issn-type":[{"value":"2837-6056","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2026]]},"article-number":"IMAG.a.1346"}}