Papers › VoxelMorph: A Learning Framework for Deformable Medical Image Registration

VoxelMorph: A Learning Framework for Deformable Medical Image Registration

14 Sep 2018arXiv:1809.05231archive 2025-07-28

Guha Balakrishnan, Amy Zhao, Mert R. Sabuncu, John Guttag, Adrian V. Dalca

We present VoxelMorph, a fast learning-based framework for deformable, pairwise medical image registration. Traditional registration methods optimize an objective function for each pair of images, which can be time-consuming for large datasets or rich deformation models. In contrast to this approach, and building on recent learning-based methods, we formulate registration as a function that maps an input image pair to a deformation field that aligns these images. We parameterize the function via a convolutional neural network (CNN), and optimize the parameters of the neural network on a set of images. Given a new pair of scans, VoxelMorph rapidly computes a deformation field by directly evaluating the function. In this work, we explore two different training strategies. In the first (unsupervised) setting, we train the model to maximize standard image matching objective functions that are based on the image intensities. In the second setting, we leverage auxiliary segmentations available in the training data. We demonstrate that the unsupervised model's accuracy is comparable to state-of-the-art methods, while operating orders of magnitude faster. We also show that VoxelMorph trained with auxiliary data improves registration accuracy at test time, and evaluate the effect of training set size on registration. Our method promises to speed up medical image analysis and processing pipelines, while facilitating novel directions in learning-based registration and its applications. Our code is freely available at voxelmorph.csail.mit.edu.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

voxelmorph/voxelmorph officialmentioned on GitHubtf report
CIG-UCL/eddeep mentioned on GitHubtfNOASSERTION report
CIG-UCL/polaffini mentioned on GitHubtfNOASSERTION report
acasamitjana/3dhirest mentioned on GitHubpytorch report
jw4hv/geo-sic mentioned on GitHubpytorchMIT report
winterpan2017/adlreg mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Deformable Medical Image RegistrationDiffeomorphic Medical Image RegistrationImage RegistrationMedical Image AnalysisMedical Image Registration

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Diffeomorphic Medical Image Registration Automatic Cardiac Diagnosis Challenge (ACDC) VoxelMorph Grad Det-Jac 9.2 #3 of 3 Archive leaderboard report
Diffeomorphic Medical Image Registration OASIS+ADIBE+ADHD200+MCIC+PPMI+HABS+HarvardGSP VoxelMorph (CC) CPU (sec) 57.0 #3 of 6 Archive leaderboard report
Diffeomorphic Medical Image Registration OASIS+ADIBE+ADHD200+MCIC+PPMI+HABS+HarvardGSP VoxelMorph (CC) Dice (Average) 0.753 #3 of 6 Archive leaderboard report
Diffeomorphic Medical Image Registration OASIS+ADIBE+ADHD200+MCIC+PPMI+HABS+HarvardGSP VoxelMorph (CC) GPU sec 0.45 #3 of 6 Archive leaderboard report
Diffeomorphic Medical Image Registration OASIS+ADIBE+ADHD200+MCIC+PPMI+HABS+HarvardGSP VoxelMorph Instance Dice 0.79 #6 of 6 Archive leaderboard report
Medical Image Registration IXI VoxelMorph DSC 0.714 #8 of 8 Archive leaderboard report
Medical Image Registration OASIS VoxelMorph DSC 0.788 #6 of 8 Archive leaderboard report
Medical Image Registration OASIS VoxelMorph val dsc 84.7 #6 of 8 Archive leaderboard report
Medical Image Registration OASIS+ADIBE+ADHD200+MCIC+PPMI+HABS+HarvardGSP VoxelMorph Dice Score 76.3 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections