The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
SynthMorph: Learning Contrast-Invariant Registration Without Acquired Images
Open accessAbstract
We introduce a strategy for learning image registration without acquired imaging data, producing powerful networks agnostic to contrast introduced by magnetic resonance imaging (MRI). While classical registration methods accurately estimate the spatial correspondence between images, they solve an optimization problem for every new image pair. Learning-based techniques are fast at test time but limited to registering images with contrasts and geometric content similar to those seen during training. We propose to remove this dependency on training data by leveraging a generative strategy for diverse synthetic label maps and images that exposes networks to a wide range of variability, forcing them to learn more invariant features. This approach results in powerful networks that accurately generalize to a broad array of MRI contrasts. We present extensive experiments with a focus on 3D neuroimaging, showing that this strategy enables robust and accurate registration of arbitrary MRI contrasts even if the target contrast is not seen by the networks during training. We demonstrate registration accuracy surpassing the state of the art both within and across contrasts, using a single model. Critically, training on arbitrary shapes synthesized from noise distributions results in competitive performance, removing the dependency on acquired data of any kind. Additionally, since anatomical label maps are often available for the anatomy of interest, we show that synthesizing images from these dramatically boosts performance, while still avoiding the need for real intensity images. Our code is available at doic https://w3id.org/synthmorph.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Sudlow, C., Gallacher, J., Allen, N., Beral, V., Burton, P., Danesh, J., Downey, P., Elliott, P., Green, J., Landray, M., et al. (2015) · PLOS Medicine · doi:10.1371/journal.pmed.1001779 · Cited by 12,728 · cited 5×
“Of these, we source 5000 MPRAGE images with 1 mm isotropic resolution from the UK Biobank (UKBB) [84] and 2000 MEMPRAGE [81] scans with 1.”
MethodInfluentialV-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
Milletari, F., Navab, N., & Ahmadi, S.-A. (2016) · 2016 Fourth International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.79 · Cited by 11,931 · cited 1×
“In our experiments, we use the (soft) Dice metric [67]”
MethodFischl, B. (2012) · NeuroImage · doi:10.1016/j.neuroimage.2012.01.021 · Cited by 9,526
Self-citationFischl, B., Salat, D. H., Busa, E., Albert, M., Dieterich, M., Haselgrove, C., van der Kouwe, A., Killiany, R., Kennedy, D., Klaveness, S., et al. (2002) · Neuron · doi:10.1016/s0896-6273(02)00569-x · Cited by 8,610
Self-citationA fast diffeomorphic image registration algorithm
Ashburner, J. (2007) · NeuroImage · doi:10.1016/j.neuroimage.2007.07.007 · Cited by 8,122
Ashburner, J., & Friston, K. J. (2005) · NeuroImage · doi:10.1016/j.neuroimage.2005.02.018 · Cited by 7,507 · cited 1×
“2) Synthetic Images: From the pair of label maps {sm, s f }, we synthesize gray-scale images {m, f } building on generative models of MR images used for Bayesian segmentation [69]–[72] (Fig.”
Nonrigid registration using free-form deformations: application to breast mr images
Rueckert, D., Sonoda, L. I., Hayes, C., Hill, D. L. G., Leach, M. O., & Hawkes, D. J. (1999) · IEEE Transactions on Medical Imaging · doi:10.1109/42.796284 · Cited by 5,265
Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration
Klein, A., Andersson, J., Ardekani, B. A., Ashburner, J., Avants, B., Chiang, M.-C., Christensen, G. E., Collins, D. L., Gee, J., Hellier, P., et al. (2009) · NeuroImage · doi:10.1016/j.neuroimage.2008.12.037 · Cited by 2,227
A deep learning framework for unsupervised affine and deformable image registration
de Vos, B. D., Berendsen, F. F., Viergever, M. A., Sokooti, H., Staring, M., & Išgum, I. (2019) · Medical Image Analysis · doi:10.1016/j.media.2018.11.010 · Cited by 818 · cited 2×
“First, we plan to extend our framework to incorporate affine registration [47], [54], [55], [97].”
Method
Research works printed but not linked: 84
- rühaak, 2013, A fully parallel algorithm for multimodal image registration using normalized gradient fields, Proc ISBI, 572
- 10.1109/ISBI.2015.7163977 · DOI
- 10.1016/j.media.2012.05.008 · DOI · Paper page
- 10.1007/11866763_89 · DOI · Paper page
- van ginneken, 2019, Medical Image Computing and Computer-Assisted Intervention Curious
- 10.1109/TMI.2019.2935060 · DOI
- könig, 2014, A fast and accurate parallel algorithm for non-linear image registration using normalized gradient fields, Proc ISBI, 580
- 10.1109/TBME.2016.2574816 · DOI · Paper page
- 10.1016/j.media.2011.03.001 · DOI · Paper page
- 10.1016/j.media.2005.01.002 · DOI
- 10.1007/BFb0056301 · DOI · Paper page
- 10.1023/A:1007958904918 · DOI · Paper page
- 10.1007/978-3-642-40811-3_79 · DOI
- li, 2017, Non-rigid image registration using fully convolutional networks with deep self-supervision, arXiv 1709 00799
- 10.1007/978-3-319-66182-7_27 · DOI · Paper page
- 10.1109/TBME.2015.2496253 · DOI · Paper page
- 10.1023/B:VISI.0000043755.93987.aa · DOI · Paper page
- roy, 2014, MR to CT registration of brains using image synthesis, Proc SPIE Med Ima Image Process, 9034
- 10.1016/j.neuroimage.2015.03.050 · DOI
- 10.1007/978-3-030-20351-1_3 · DOI
- lee, 2019, Few labeled atlases are necessary for deep-learning-based segmentation, Proc Mach Learn Health, 1
- 10.1016/j.neunet.2020.01.023 · DOI
- 10.1007/978-3-658-25326-4_69 · DOI
- 10.1109/ISBI.2018.8363756 · DOI
- 10.1016/j.media.2018.07.002 · DOI · Paper page
- 10.1007/978-3-030-20351-1_19 · DOI
- tanner, 2018, Generative adversarial networks for MR-CT deformable image registration, arXiv 1807 07349
- 10.1016/j.patcog.2016.09.026 · DOI
- 10.1201/9781420042474 · doi:10.1201/9781420042474
- 10.1016/j.neuroimage.2016.09.011 · DOI · Paper page
- frackowiak, 2004, Human Brain Function
- 10.1038/s41467-019-13374-0 · DOI
- 10.1016/j.media.2016.10.005 · DOI
- 10.1007/978-3-319-02126-3_3 · DOI
- 10.1002/cne.24946 · DOI
- 10.1109/TMI.2019.2897112 · DOI · Paper page
- 10.1109/TMI.2018.2878316 · DOI · Paper page
- 10.1016/j.media.2015.09.005 · DOI
- 10.1109/ISBI.2017.7950652 · DOI
- 10.1109/TMI.2002.806587 · DOI · Paper page
- 10.1109/42.906424 · DOI · Paper page
- 10.1109/42.511747 · DOI · Paper page
- 10.1109/42.811270 · DOI · Paper page
- abadi, 2016, Tensorflow: A system for large-scale machine learning, Proc USENIX Symp on Operating System Design and Implementation, 265
- kingma, 2014, Adam: A method for stochastic optimization, arXiv 1412 6980
- 10.1016/j.media.2005.09.004 · DOI · Paper page
- 10.1155/IJBI/2006/49515 · DOI · Paper page
- 10.1162/jocn.2007.19.9.1498 · DOI · Paper page
- 10.1016/j.neuroimage.2018.10.009 · DOI · Paper page
- zhao, 2019, Data augmentation using learned transforms for one-shot medical image segmentation, CoRR, abs 1902 9383, 1
- 10.1007/978-3-030-32251-9_44 · doi:10.1007/978-3-030-32251-9_44
- 10.1007/978-3-319-59050-9_47 · DOI · Paper page
- billot, 2020, A learning strategy for contrast-agnostic mri segmentation, Proc PMLR, 121, 75
- 10.1109/ISBI48211.2021.9434113 · DOI
- dalca, 2018, VoxelMorph Learning-Based Image Registration
- 10.1007/11866565_113 · DOI · Paper page
- 10.1016/j.mri.2014.11.004 · doi:10.1016/j.mri.2014.11.004
- 10.1017/9781107706958 · DOI · Paper page
- shi, 2012, A comprehensive cardiac motion estimation framework using both untagged and 3-D tagged MR images based on nonrigid registration, IEEE Trans Med Imag, 31, 1263, 10.1109/TMI.2012.2188104 · DOI
- 10.2307/1932409 · DOI · Paper page
- 10.1109/TMI.2013.2246577 · DOI · Paper page
- pustina, 2017, Anatomy of an Registration Call
- 10.1016/j.neuroimage.2010.07.020 · DOI · Paper page
- 10.1016/j.media.2007.12.003 · DOI · Paper page
- 10.1007/978-3-030-78191-0_1 · DOI
- 10.1109/CVPR.2019.00874 · DOI · Paper page
- 10.1109/TMI.2005.852050 · DOI · Paper page
- chee, 2018, AIRNet: Self-supervised affine registration for 3D medical images using neural networks, arXiv 1810 02583
- 10.1016/j.neuroimage.2013.04.114 · DOI · Paper page
- 10.1016/j.media.2007.06.004 · DOI · Paper page
- 10.1016/j.cmpb.2009.09.002 · DOI · Paper page
- 10.1109/42.929618 · DOI · Paper page
- 10.1016/j.neuroimage.2008.10.040 · DOI · Paper page
- 10.1002/jmri.24542 · DOI · Paper page
- 10.1109/TMI.2019.2897538 · DOI · Paper page
- 10.1016/j.neuroimage.2007.12.025 · DOI · Paper page
- 10.1007/978-3-319-67558-9_24 · DOI · Paper page
- 10.1007/11566489_32 · DOI
- 10.1109/TITB.2008.917893 · DOI
- 10.1016/j.neuroimage.2018.09.060 · DOI · Paper page
- 10.1098/rstb.2001.0916 · DOI
- holmes, 2015, Brain genomics superstruct project initial data release with structural, functional, and behavioral measures, Data Science Journal, 2
- 10.1097/00004728-198701000-00003 · DOI
- 10.1016/j.neuroimage.2009.10.002 · DOI · Paper page
Cited by
UniverSeg: Universal Medical Image Segmentation
Butoi, V. I., Gonzalez Ortiz, J. J., Ma, T., Sabuncu, M. R., Guttag, J., & Dalca, A. V. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01960 · Cited by 195
Self-citationA ready-to-use machine learning tool for symmetric multi-modality registration of brain MRI
Iglesias, J. E. (2023) · Scientific Reports · doi:10.1038/s41598-023-33781-0 · Cited by 64
Self-citationMapping the neural dynamics of locomotion across the Drosophila brain
Brezovec, B. E., Berger, A. B., Hao, Y. A., Chen, F., Druckmann, S., & Clandinin, T. R. (2024) · Current Biology · doi:10.1016/j.cub.2023.12.063 · Cited by 58
Self-Supervised 2D/3D Registration for X-Ray to CT Image Fusion
Jaganathan, S., Kukla, M., Wang, J., Shetty, K., & Maier, A. (2023) · 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv56688.2023.00281 · Cited by 30
Ren, J., An, N., Lin, C., Zhang, Y., Sun, Z., Zhang, W., Li, S., Guo, N., Cui, W., Hu, Q., et al. (2025) · Nature Methods · doi:10.1038/s41592-025-02599-1 · Cited by 29
Metadata
- Authors
- Hoffmann, M., Billot, B., Greve, D. N., Iglesias, J. E., Fischl, B., & Dalca, A. V.
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2022-03
- Volume
- 41
- Issue
- 3
- Pages
- 543-558
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- OpenAlex
- W3204867994
- Cited by
- 201
- References
- 14
- FWCI
- 7.23
- Type
- journal article
- Language
- en
- Open access
- hybrid
- Funders
- Alzheimer’s Research UK (ARUK-IRG2019A-003)
- European Research Council (ERC) under Starting Grant (677697)
- National Institutes of Health (1R01 AG070988-01)
- BRAIN Initiative Grant (1RF1MH123195-01, K99 HD101553, U01 AG052564, R56 AG064027, R01 AG064027, R01 AG016495, U01 MH117023, P41 EB015896, R01 EB023281, R01 EB019956, R01 NS0525851, R21 NS072652, R01 NS083534, U01 NS086625, U24 NS10059103, R01 NS105820, S10 RR023401, S10 RR019307, S10 RR023043)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: SynthMorph: Learning Contrast-Invariant Registration Without Acquired Images. https://app.cochat.ai/papers/10.1109/tmi.2021.3116879
- The paper
- Hoffmann, M., Billot, B., Greve, D. N., Iglesias, J. E., Fischl, B., & Dalca, A. V. (2022). SynthMorph: Learning Contrast-Invariant Registration Without Acquired Images. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2021.3116879
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.