{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T09:21:20Z","timestamp":1785403280625,"version":"3.56.0"},"posted":{"date-parts":[[2026,2,14]]},"group-title":"Neuroscience","reference-count":48,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T00:00:00Z","timestamp":1771027200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"award":["R21-NS145048"],"award-info":[{"award-number":["R21-NS145048"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,2,13]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:p>Portable low-field MRI offers an affordable and mobile alternative to conventional high-field scanners, enabling imaging in point-of-care and resource-limited settings. However, its lower signal-to-noise ratio, reduced resolution, and acquisition artifacts raise concerns about the accuracy of standard image registration methods. Reliable registration is critical for a wide range of emerging applications, including frequent brain monitoring, assessment of neurodegenerative disease progression, and evaluation of treatment effects such as those of Alzheimer\u2019s therapeutics. In this work, we systematically evaluated state-of-the-art registration approaches on simulated low-field scans (obtained by downsampling high-field images) and on real low-field brain MRI data. We compared three representative approaches: classical optimization (NiftyReg), learning-based registration (SynthMorph), and synthesis-based registration (SynthSR+NiftyReg). Using downsampled high-field scans, all methods performed well, achieving high Dice scores and smooth deformation fields, indicating that reduced resolution alone does not hinder registration. In contrast, real low-field data exhibited lower accuracy, primarily due to geometric distortion and other acquisition-specific artifacts. Among the tested approaches, the synthesis-based pipeline achieved the most robust performance across subjects and modalities. Overall, existing algorithms can accommodate resolution limitations, however, future methods could further enhance coregistration by explicitly addressing the distortions present in low-field MRI scans.<\/jats:p>","DOI":"10.64898\/2026.02.11.705413","type":"posted-content","created":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T10:25:20Z","timestamp":1771064720000},"source":"Crossref","is-referenced-by-count":1,"title":["On the accuracy of image registration in portable low-field 3D brain MRI"],"prefix":"10.64898","author":[{"given":"J. Eugenio","family":"Iglesias","sequence":"first","affiliation":[{"name":"Martinos Center for Biomedical Imaging, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ian P.","family":"Johnson","sequence":"additional","affiliation":[{"name":"Center for Brain and Mind Health, Yale School of Medicine, Departments of Neurology and Neurosurgery, New Haven, CT 06510, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Williams-Ramirez","sequence":"additional","affiliation":[{"name":"Martinos Center for Biomedical Imaging, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dina","family":"Zemlyanker","sequence":"additional","affiliation":[{"name":"Martinos Center for Biomedical Imaging, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Tian","sequence":"additional","affiliation":[{"name":"Martinos Center for Biomedical Imaging, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karthik","family":"Gopinath","sequence":"additional","affiliation":[{"name":"Martinos Center for Biomedical Imaging, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Olchanyi","sequence":"additional","affiliation":[{"name":"Picower Institute, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"},{"name":"Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"},{"name":"Center for Neurotechnology and Neurorecovery, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ava D.","family":"Farnan","sequence":"additional","affiliation":[{"name":"Department of Neurology, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Center for Genomic Medicine, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amelia","family":"Demopoulos","sequence":"additional","affiliation":[{"name":"Department of Neurology, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Center for Genomic Medicine, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew S.","family":"Rosen","sequence":"additional","affiliation":[{"name":"Martinos Center for Biomedical Imaging, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin N.","family":"Sheth","sequence":"additional","affiliation":[{"name":"Center for Brain and Mind Health, Yale School of Medicine, Departments of Neurology and Neurosurgery, New Haven, CT 06510, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"de Havenon","sequence":"additional","affiliation":[{"name":"Center for Brain and Mind Health, Yale School of Medicine, Departments of Neurology and Neurosurgery, New Haven, CT 06510, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"W. Taylor","family":"Kimberly","sequence":"additional","affiliation":[{"name":"Department of Neurology, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Center for Genomic Medicine, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annabel","family":"Sorby-Adams","sequence":"additional","affiliation":[{"name":"Department of Neurology, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Center for Genomic Medicine, Massachusets General Hospital and Harvard Medical School, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI)","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026021609251073000_2026.02.11.705413v1.1","first-page":"694","article-title":"Predicting error in rigid-body point-based registration","volume":"17","year":"2002","journal-title":"IEEE transactions on medical imaging"},{"key":"2026021609251073000_2026.02.11.705413v1.2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2003.815867"},{"key":"2026021609251073000_2026.02.11.705413v1.3","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1016\/j.media.2011.02.005","article-title":"Nonlinear registration of longitudinal images and measurement of change in regions of interest","volume":"15","year":"2011","journal-title":"Med. image analysis"},{"key":"2026021609251073000_2026.02.11.705413v1.4","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/j.inffus.2013.12.002","article-title":"Medical image fusion: A survey of the state of the art","volume":"19","year":"2014","journal-title":"Inf. fusion"},{"key":"2026021609251073000_2026.02.11.705413v1.5","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/j.media.2015.06.012","article-title":"Multi-atlas segmentation of biomedical images: a survey","volume":"24","year":"2015","journal-title":"Med. image analysis"},{"key":"2026021609251073000_2026.02.11.705413v1.6","doi-asserted-by":"crossref","unstructured":"Chen, M. , Tustison, N. J. , Jena, R. & Gee, J. C. Image registration: Fundamentals and recent advances based on deep learning. Mach. Learn. for Brain Disord. 435\u2013458 (2023).","DOI":"10.1007\/978-1-0716-3195-9_14"},{"key":"2026021609251073000_2026.02.11.705413v1.7","doi-asserted-by":"publisher","DOI":"10.1016\/S1053-8119(09)70884-5"},{"key":"2026021609251073000_2026.02.11.705413v1.8","doi-asserted-by":"publisher","DOI":"10.1006\/nimg.2000.0582"},{"key":"2026021609251073000_2026.02.11.705413v1.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2008.12.037"},{"key":"2026021609251073000_2026.02.11.705413v1.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.01.024"},{"key":"2026021609251073000_2026.02.11.705413v1.11","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/S1361-8415(98)80022-4","article-title":"Image matching as a diffusion process: an analogy with Maxwell\u2019s demons","volume":"2","year":"1998","journal-title":"Med. image analysis"},{"key":"2026021609251073000_2026.02.11.705413v1.12","doi-asserted-by":"publisher","DOI":"10.1109\/42.796284"},{"key":"2026021609251073000_2026.02.11.705413v1.13","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.media.2007.06.004","article-title":"Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain","volume":"12","year":"2008","journal-title":"Med. image analysis"},{"key":"2026021609251073000_2026.02.11.705413v1.14","doi-asserted-by":"crossref","unstructured":"Viergever, M. A. et al. A survey of medical image registration\u2013under review (2016).","DOI":"10.1016\/j.media.2016.06.030"},{"key":"2026021609251073000_2026.02.11.705413v1.15","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2013.2265603"},{"key":"2026021609251073000_2026.02.11.705413v1.16","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.cmpb.2009.09.002","article-title":"Fast free-form deformation using graphics processing units","volume":"98","year":"2010","journal-title":"Comput. methods programs biomedicine"},{"key":"2026021609251073000_2026.02.11.705413v1.17","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2035616"},{"key":"2026021609251073000_2026.02.11.705413v1.18","first-page":"e21","article-title":"Non-linear registration, aka spatial normalisation FMRIB technical report TR07JA2","volume":"2","year":"2007","journal-title":"FMRIB Analysis Group Univ. Oxf"},{"key":"2026021609251073000_2026.02.11.705413v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2007.07.007"},{"key":"2026021609251073000_2026.02.11.705413v1.20","doi-asserted-by":"publisher","DOI":"10.1016\/J.NEUROIMAGE.2017.10.034"},{"key":"2026021609251073000_2026.02.11.705413v1.21","first-page":"2278","article-title":"Gradient-based learning applied to document recognition","volume":"86","year":"2002","journal-title":"Proc. IEEE"},{"key":"2026021609251073000_2026.02.11.705413v1.22","unstructured":"Vaswani, A. et al. Attention is all you need. Adv. neural information processing systems 30 (2017)."},{"key":"2026021609251073000_2026.02.11.705413v1.23","doi-asserted-by":"crossref","unstructured":"Sokooti, H. et al. Nonrigid image registration using multi-scale 3D convolutional neural networks. In International conference on medical image computing and computer-assisted intervention, 232\u2013239 (Springer, 2017).","DOI":"10.1007\/978-3-319-66182-7_27"},{"key":"2026021609251073000_2026.02.11.705413v1.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.07.008"},{"key":"2026021609251073000_2026.02.11.705413v1.25","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2897538"},{"key":"2026021609251073000_2026.02.11.705413v1.26","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.media.2018.11.010","article-title":"A deep learning framework for unsupervised affine and deformable image registration","volume":"52","year":"2019","journal-title":"Med. image analysis"},{"key":"2026021609251073000_2026.02.11.705413v1.27","doi-asserted-by":"crossref","first-page":"20TR01","DOI":"10.1088\/1361-6560\/ab843e","article-title":"Deep learning in medical image registration: a review","volume":"65","year":"2020","journal-title":"Phys. Medicine & Biol"},{"key":"2026021609251073000_2026.02.11.705413v1.28","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1007\/s00138-020-01060-x","article-title":"Deep learning in medical image registration: a survey","volume":"31","year":"2020","journal-title":"Mach. Vis. Appl"},{"key":"2026021609251073000_2026.02.11.705413v1.29","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.media.2019.07.006","article-title":"Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces","volume":"57","year":"2019","journal-title":"Med. image analysis"},{"key":"2026021609251073000_2026.02.11.705413v1.30","doi-asserted-by":"crossref","first-page":"015011","DOI":"10.1088\/1361-6560\/ab5da0","article-title":"A multi-scale framework with unsupervised joint training of convolutional neural networks for pulmonary deformable image registration","volume":"65","year":"2020","journal-title":"Phys. Medicine & Biol"},{"key":"2026021609251073000_2026.02.11.705413v1.31","doi-asserted-by":"crossref","first-page":"102615","DOI":"10.1016\/j.media.2022.102615","article-title":"Transmorph: Transformer for unsupervised medical image registration","volume":"82","year":"2022","journal-title":"Med. image analysis"},{"key":"2026021609251073000_2026.02.11.705413v1.32","doi-asserted-by":"crossref","unstructured":"Kim, B. , Han, I. & Ye, J. C. Diffusemorph: Unsupervised deformable image registration using diffusion model. In European conference on computer vision, 347\u2013364 (Springer, 2022).","DOI":"10.1007\/978-3-031-19821-2_20"},{"key":"2026021609251073000_2026.02.11.705413v1.33","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","year":"2020","journal-title":"Adv. neural information processing systems"},{"key":"2026021609251073000_2026.02.11.705413v1.34","doi-asserted-by":"crossref","unstructured":"Tian, L. et al. uniGradICON: A foundation model for medical image registration. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 749\u2013760 (Springer, 2024).","DOI":"10.1007\/978-3-031-72069-7_70"},{"key":"2026021609251073000_2026.02.11.705413v1.35","first-page":"e0306","article-title":"Portable magnetic resonance imaging for ICU patients","volume":"2","year":"2020","journal-title":"Critical Care Explor"},{"key":"2026021609251073000_2026.02.11.705413v1.36","doi-asserted-by":"crossref","first-page":"eabm3952","DOI":"10.1126\/sciadv.abm3952","article-title":"Portable, low-field magnetic resonance imaging enables highly accessible and dynamic bedside evaluation of ischemic stroke","volume":"8","year":"2022","journal-title":"Sci. advances"},{"key":"2026021609251073000_2026.02.11.705413v1.37","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1038\/s44222-023-00086-w","article-title":"Brain imaging with portable low-field MRI","volume":"1","year":"2023","journal-title":"Nat. reviews bioengineering"},{"key":"2026021609251073000_2026.02.11.705413v1.38","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1002\/mrm.28992","article-title":"External dynamic interference estimation and removal (EDITER) for low field MRI","volume":"87","year":"2022","journal-title":"Magn. resonance medicine"},{"key":"2026021609251073000_2026.02.11.705413v1.39","doi-asserted-by":"crossref","first-page":"10488","DOI":"10.1038\/s41467-024-54972-x","article-title":"Portable, low-field magnetic resonance imaging for evaluation of Alzheimer\u2019s disease","volume":"15","year":"2024","journal-title":"Nat. Commun"},{"key":"2026021609251073000_2026.02.11.705413v1.40","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/S1361-8415(01)80004-9","article-title":"Multi-modal volume registration by maximization of mutual information","volume":"1","year":"1996","journal-title":"Med. image analysis"},{"key":"2026021609251073000_2026.02.11.705413v1.41","first-page":"543","article-title":"SynthMorph: learning contrast-invariant registration without acquired images","volume":"41","year":"2021","journal-title":"IEEE transactions on medical imaging"},{"key":"2026021609251073000_2026.02.11.705413v1.42","doi-asserted-by":"crossref","first-page":"eadd3607","DOI":"10.1126\/sciadv.add3607","article-title":"SynthSR: A public AI tool to turn heterogeneous clinical brain scans into high-resolution T1-weighted images for 3D morphometry","volume":"9","year":"2023","journal-title":"Sci. advances"},{"key":"2026021609251073000_2026.02.11.705413v1.43","doi-asserted-by":"crossref","unstructured":"Szeliski, R. Computer vision: algorithms and applications (Springer Nature, 2022).","DOI":"10.1007\/978-3-030-34372-9"},{"key":"2026021609251073000_2026.02.11.705413v1.44","doi-asserted-by":"crossref","unstructured":"Iglesias, J. E. et al. Is synthesizing MRI contrast useful for inter-modality analysis? In International Conference on Medical Image Computing and Computer-Assisted Intervention, 631\u2013638 (Springer, 2013).","DOI":"10.1007\/978-3-642-40811-3_79"},{"key":"2026021609251073000_2026.02.11.705413v1.45","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102789"},{"key":"2026021609251073000_2026.02.11.705413v1.46","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2050897"},{"key":"2026021609251073000_2026.02.11.705413v1.47","doi-asserted-by":"crossref","unstructured":"Casamitjana, A. et al. USLR: An open-source tool for unbiased and smooth longitudinal registration of brain MRI. Med. Image Analysis 103662 (2025).","DOI":"10.1016\/j.media.2025.103662"},{"key":"2026021609251073000_2026.02.11.705413v1.48","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2216399120"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.02.11.705413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:25:24Z","timestamp":1771262724000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.02.11.705413"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,14]]},"references-count":48,"URL":"https:\/\/doi.org\/10.64898\/2026.02.11.705413","relation":{},"subject":[],"published":{"date-parts":[[2026,2,14]]},"subtype":"preprint"}}