An effective deep learning algorithm for medical image registration.
4 blocks of code here have a permanent identifier (oscr:b:…), listed with the matches below: citable for good, with a page of its own. Select a match and press Cite to copy it. What a block identifier is.
The 4 matches
- [1] § Experiment › Implementation ↔ voxelmorph/__init__.py, lines 1 to 31 · score 0.63 · PyTorch, deep learning framework, loss function, Python · block
oscr:b:XPE9M4QCSFEKK-8· Report a mismatch - [2] § Methodology › Dual multiscale feature extractor ↔ voxelmorph/nn/models.py, lines 60 to 124 · score 0.59 · ReLU, activation function, layers, channel, dimensions, Transformers · block
oscr:b:6S9CE0ZNT4HE3-X· Report a mismatch - [3] § Methodology › Similarity loss ↔ voxelmorph/nn/losses.py, lines 14 to 27 · score 0.57 · Normalized Cross Correlation, NCC, loss · block
oscr:b:2S9X08SN55FC0-L· Report a mismatch - [4] § Experiment › Implementation ↔ scripts/train.py, lines 167 to 250 · score 0.54 · loss weights, setup, GPU, CPU, PyTorch, batch · block
oscr:b:VD9VX7Y5G8H14-O· Report a mismatch
Paper
Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC
The paper is loaded when this pane is shown.
The authors' code
Python · 53 lines · 1.6 KB · Apache-2.0 · 1 match
- """
- Deep learning tools for deformable medical image registration. This package
- offers reference implementations of core registration networks, loss
- functions, and utilities, with PyTorch and TensorFlow backends.
- ## Subpackages (overview)
- - **nn**: Torch-based neural network components for Voxelmorph.
- - **py**: Python utilities for Voxelmorph.
- ???+ quote "Citation"
- === "APA"
- Balakrishnan, G., Zhao, A., Sabuncu, M. R., Guttag, J., & Dalca,
- A. V. (2018). VoxelMorph: A Learning Framework for Deformable
- Medical Image Registration. *arXiv:1809.05231*.
- <https://arxiv.org/abs/1809.05231>
- === "BibTeX"
- ```bibtex
- @article{balakrishnan2018voxelmorph,
- title = {VoxelMorph: A Learning Framework for Deformable Medical
- Image Registration},
- author = {Balakrishnan, Guha and Zhao, Amy and Sabuncu, Mert R and
- Guttag, John and Dalca, Adrian V},
- journal = {arXiv preprint arXiv:1809.05231},
- year = {2018},
- url = {https://arxiv.org/abs/1809.05231}
- }
- ```
- """
- # set version
- __version__ = '0.3.3'
- # Third-party imports
- from packaging import version
- import neurite
- # ensure valid neurite version is available
- minv = '0.3'
- curv = getattr(neurite, '__version__', None)
- if curv is None or version.parse(curv) < version.parse(minv):
- raise ImportError(f'voxelmorph requires neurite version {minv} or greater, '
- f'but found version {curv}')
- # Local imports
- from . import nn
- from . import py
- from .functional import *
- __all__ = ['nn', 'py']
__init__.py at commit c4155e1, under Apache-2.0 · at the source
Overview
- School of Mathematics and Computational Science, Xiangtan University, Xiangtan, China
- Department of Mathematics and Statistics, University of Strathclyde, Glasgow, United Kingdom
- Radiology Department of Xiangtan Central Hospital, Xiangtan, China
- Schools of Health Sciences and Computer Science, University of Manchester, Manchester, United Kingdom
Abstract
Image registration is crucial for many medical imaging applications, including longitudinal monitoring and multimodal information fusion. A key challenge is to achieve accurate alignment while strictly preserving topology and invertibility. To address the limitations of traditional penalty-based regularization, which may still permit local folding, this study proposes DTC-Reg, a dynamically learned registration framework that more explicitly enforces diffeomorphic deformation. The framework integrates a homotopy-based control–increment formulation with explicit multiscale geometric constraints. Two parameter-sharing U-Nets first extract multiscale feature pyramids from the input images, after which a symmetric registration module with a sequential temporal cascade network progressively refines the forward and inverse multiscale deformation fields. To further enhance diffeomorphic consistency, this study introduces a Multiscale Folding-aware Deformation Correction (MFDC) module that explicitly detects and geometrically rectifies folding points in the predicted deformation fields. Beyond its integration within DTC-Reg, MFDC can also be readily incorporated into several state-of-the-art registration networks, significantly reducing folding and improving deformation regularity. Extensive experiments on three 3D brain MRI registration tasks demonstrate that the proposed method consistently achieves superior performance over existing approaches in both quantitative and qualitative evaluations.
Reproduced under the paper's license (CC BY), from the paper cited above.
Repository
Its files are read in the Code ↔ Paper reader above, with 4 matches between paragraphs and lines of code.
voxelmorph/voxelmorph
c4155e1baf04bc8f1774775b23a6027b58b37e00, 11 September 2026Availability: 1 check, the latest on 29 September 2026: the link answers
- 29 September 2026: the link answers
58 files
- docs/
site/ , JavaScript, 16 linesassets/ javascripts/ bundle.92b07e13.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.ar.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.da.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.de.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.du.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.el.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.es.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.fi.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.fr.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.he.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.hi.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.hu.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.hy.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.it.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.ja.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.jp.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.kn.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.ko.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.multi.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.nl.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.no.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.pt.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.ro.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.ru.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.sa.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.stemmer.support.min .js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.sv.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.ta.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.te.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.th.min.js - docs/
site/ , JavaScript, 18 linesassets/ javascripts/ lunr/ min/ lunr.tr.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.vi.min.js - docs/
site/ , JavaScript, 1 lineassets/ javascripts/ lunr/ min/ lunr.zh.min.js - docs/
site/ , JavaScript, 206 linesassets/ javascripts/ lunr/ tinyseg.js - docs/
site/ , JavaScript, 186 linesassets/ javascripts/ lunr/ wordcut.js - docs/
site/ , JavaScript, 42 linesassets/ javascripts/ workers/ search.973d3a69.min.js - scripts/
register.py , Python, 97 lines - scripts/
train.py , Python, 254 lines, 1 match - setup.py, Python, 41 lines
- tests/
test_functional.py , Python, 1,402 lines - tests/
test_imports.py , Python, 1 line - tests/
test_integrate_disp.py , Python, 62 lines - tests/
test_integration_compati , Python, 183 linesbility.py - tests/
test_models.py , Python, 245 lines - tests/
test_modules.py , Python, 444 lines - tests/
test_neurite_integration , Python, 180 lines.py - voxelmorph/
__init__.py , Python, 53 lines, 1 match - voxelmorph/
functional.py , Python, 1,344 lines - voxelmorph/
nn/ , Python, 29 lines__init__.py - voxelmorph/
nn/ , Python, 880 linesfunctional.py - voxelmorph/
nn/ , Python, 83 lines, 1 matchlosses.py - voxelmorph/
nn/ , Python, 280 lines, 1 matchmodels.py - voxelmorph/
nn/ , Python, 283 linesmodules.py - voxelmorph/
py/ , Python, 15 lines__init__.py - voxelmorph/
py/ , Python, 469 linesgenerators.py - voxelmorph/
py/ , Python, 535 linesutils.py - LICENSE.md, License, 201 lines
- README.md, Text, 217 lines
The paper's code and data availability statement is in the Data section.
Tracing map
Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.
What the map holds:
- 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
- 56 scripts, each with its path and the digest of its content;
- 4 matches between paragraphs of the paper and lines of the code (method lexical-v1);
- neither the text of the paper nor the code itself.
Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.
Data
Datasets cited
- github.com/
adalca/ , at github.com; found in “Data Availability”medical-datasets
Data Availability
All datasets used in this study are publicly available third-party data. The authors had no special access privileges to these datasets which others would not have. The specific data sources are as follows: 1. OASIS-v1 Dataset: The original data is available at https://
Reproduced under the paper's license (CC BY), from the paper cited above.
Versions
The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.
Version 1, 29 September 2026: the first record
Recorded: type, language, journal, volume, issue, pages, dates, 6 authors, 5 funders, 50 references.
Cite
This paper
Deng, J., Chen, K., Li, M., Zuo, Z., Frangi, A. F., & Zhang, J. (2026). An effective deep learning algorithm for medical image registration. PLOS digital health, 5(4), e0001339. https://
BibTeX
@article{deng2026effecti
author = {Deng, Jinqiu and Chen, Ke and Li, Mingke and Zuo, Zhichao and Frangi, Alejandro F and Zhang, Jianping},
title = {{An effective deep learning algorithm for medical image registration}},
journal = {PLOS digital health},
year = {2026},
month = apr,
volume = {5},
number = {4},
pages = {e0001339},
publisher = {PLOS},
issn = {2767-3170},
doi = {10.1371/
url = {https://
pmid = {41990030},
pmcid = {PMC13086356}
}
RIS
TY - JOUR
AU - Deng, Jinqiu
AU - Chen, Ke
AU - Li, Mingke
AU - Zuo, Zhichao
AU - Frangi, Alejandro F
AU - Zhang, Jianping
TI - An effective deep learning algorithm for medical image registration
T2 - PLOS digital health
J2 - PLOS Digit Health
PY - 2026
DA - 2026/
VL - 5
IS - 4
SP - e0001339
SN - 2767-3170
PB - PLOS
DO - 10.1371/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.1371/
"type": "article-journal",
"title": "An effective deep learning algorithm for medical image registration",
"container-title": "PLOS digital health",
"author": [
{
"family": "Deng",
"given": "Jinqiu"
},
{
"family": "Chen",
"given": "Ke"
},
{
"family": "Li",
"given": "Mingke"
},
{
"family": "Zuo",
"given": "Zhichao"
},
{
"family": "Frangi",
"given": "Alejandro F"
},
{
"family": "Zhang",
"given": "Jianping"
}
],
"container-title-short":
"volume": "5",
"issue": "4",
"page": "e0001339",
"DOI": "10.1371/
"PMID": "41990030",
"PMCID": "PMC13086356",
"ISSN": "2767-3170",
"publisher": "PLOS",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
16
]
]
}
}
The tracing map gets a citation of its own once an author has validated it and it has a DOI.
Similar papers
The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.
- [1] doi:10.1016/j.isci.2024.111734 [code]
- Enhancing unsupervised learning in medical image registration through scale-aware context aggregation.Journal: iScienceIn common: scikit-image, PyTorch, SciPy, 1 other tool, 12 references
- [2] doi:10.3390/jimaging12070276 [code]
- Hyperelastic Regularization for Near-Diffeomorphic Transformer-Based Brain MRI Registration.Journal: Journal of imagingIn common: scikit-image, NiBabel, PyTorch, 2 other tools, 10 references
- [3] doi:10.3390/jimaging12080384 [code]
- Understanding Trade-Offs in Continuous Neural Representations for Diffeomorphic Image Registration: A Comparative Study of Implicit Neural Representations and Neural Ordinary Differential Equations.Journal: Journal of imagingIn common: NiBabel, PyTorch, SciPy, 1 other tool, 9 references
- [4] doi:10.1002/hbm.26165 [code]
- Fast three-dimensional image generation for healthy brain aging using diffeomorphic registration.Journal: Human brain mappingIn common: scikit-image, h5py, NiBabel, 3 other tools, 6 references
- [5] doi:10.1162/imag_a_00197 [code]
- Anatomy-aware and acquisition-agnostic joint registration with SynthMorph.Journal: Imaging neuroscience (Cambridge, Mass.)In common: 10 references
- [6] doi:10.1038/s41598-023-44517-5 [code]
- Exploring the performance of implicit neural representations for brain image registration.Journal: Scientific reportsIn common: NiBabel, PyTorch, SciPy, 1 other tool, 7 references
- [7] doi:10.1016/j.neuroimage.2024.120981 [code]
- RegBoost: Enhancing mouse brain image registration using geometric priors and Laplacian interpolation.Journal: NeuroImageIn common: scikit-image, h5py, NiBabel, 3 other tools, 5 references
- [8] doi:10.1038/s41598-025-00403-w
- Hybrid transformer and convolution iteratively optimized pyramid network for brain large deformation image registration.Journal: Scientific reportsIn common: 9 references
- [9] doi:10.1038/s41467-024-47883-4 [code]
- Cross-modality mapping using image varifolds to align tissue-scale atlases to molecular-scale measures with application to 2D brain sections.Journal: Nature communicationsIn common: scikit-image, h5py, NiBabel, 3 other tools, 4 references
- [10] doi:10.1016/j.media.2023.102789 [code]
- SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining.Journal: Medical image analysisIn common: scikit-image, h5py, NiBabel, 3 other tools, 3 references
Contribute
The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.
Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Validate its tracing map
You validate the map as this page shows it: 1 repository of the authors' code, each at its verified commit and with its license, 56 scripts, and 4 matches between paragraphs and code (see the Code and Map sections). It then receives a DOI on Zenodo, with you (your ORCID iD) and OSCR as its creators; the code itself is not deposited.
The map's fingerprint: sha256:520e37773766776f…
Add the badge to the code's README
If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.
Markdown
<!-- oscr-badge:start -->
[](https://openscicode.org/badge/doi/10.1371/journal.pdig.0001339)
<!-- oscr-badge:end -->reStructuredText
.. oscr-badge:start
.. image:: https://openscicode.org/badge/doi/10.1371/journal.pdig.0001339.svg
:target: https://openscicode.org/badge/doi/10.1371/journal.pdig.0001339
:alt: OSCR
.. oscr-badge:endHTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1371/journal.pdig.0001339"><img src="https://openscicode.org/badge/doi/10.1371/journal.pdig.0001339.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".
If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge page.
Request its removal
To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).
Discussion, reproductions, activity
Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.
Report a mismatch between the code and the paper · Report a code error (signed in)
Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.
Report a reproduction failure (signed in)
Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
