OSCR

Portable Ultra-Low Field MRI Deep-Learning Algorithms for White Matter Lesion Segmentation Improve Accuracy and Reflect Clinical Disability in Multiple Sclerosis

Code ↔ Paper

The paper beside its authors' code: matches between them have not been computed for this paper yet.

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

Shell · 46 lines · 1.3 KB · Apache-2.0

  1. #!/usr/bin/env bash
  2. # safe-label.sh — label wrapper with a denylist.
  3. #
  4. # Usage: safe-label.sh <number> <add|remove> <label>
  5. #
  6. # Blocks the "ready-for-fix" label so agent workflows cannot apply it and
  7. # thereby trigger the bug-fix PR workflow. All other labels pass through.
  8. # The denylist is intentionally small; this is the structural boundary that
  9. # makes fix-PR creation a human-only decision.
  10. #
  11. # GITHUB_REPOSITORY is provided automatically by GitHub Actions.
  12. set -euo pipefail
  13. if [[ $# -ne 3 ]]; then
  14. echo "Usage: $0 <number> <add|remove> <label>" >&2
  15. exit 2
  16. fi
  17. NUMBER="$1"
  18. ACTION="$2"
  19. LABEL="$3"
  20. # Deny ADD of the ready-for-fix label. REMOVE is allowed so the fix
  21. # workflow can clear the label after opening its PR.
  22. case "$ACTION:$LABEL" in
  23. add:ready-for-fix)
  24. echo "safe-label.sh: refusing to add label 'ready-for-fix' — reserved for maintainers" >&2
  25. exit 1
  26. ;;
  27. esac
  28. REPO="${GITHUB_REPOSITORY:?GITHUB_REPOSITORY must be set}"
  29. case "$ACTION" in
  30. add)
  31. exec gh issue edit "$NUMBER" --repo "$REPO" --add-label "$LABEL"
  32. ;;
  33. remove)
  34. exec gh issue edit "$NUMBER" --repo "$REPO" --remove-label "$LABEL"
  35. ;;
  36. *)
  37. echo "safe-label.sh: unknown action '$ACTION' (expected add|remove)" >&2
  38. exit 2
  39. ;;
  40. esac

safe-label.sh at commit 1489d74, under Apache-2.0 · at the source

Overview

  1. Neuroimmunology Branch, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA
  2. Sidney Kimmel Medical College, Thomas Jefferson University, Philadelphia, PA, USA
  3. Oxford Centre for Integrative Neuroimaging - University of Oxford, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
  4. Office of Biostatistics, Division of Intramural Research, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA
  5. Oxford Centre for Integrative Neuroimaging, Oxford Centre for Human Brain Activity - University of Oxford, Department of Psychiatry, University of Oxford, Oxford, United Kingdom
  6. qMRI Core Facility, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA
Dates: published online 17 July 2026
Type: Preprint · Language: English
License: CC0
Identifiers: DOI 10.64898/2026.07.15.26357954 · OpenAlex W7169591259
Open access: green, a free copy (OpenAlex)
Status: code verified (how the code is found and verified)
Categories: structural MRI / diffusion (modality), human (organism), multiple sclerosis (population), clinical / translational (subfield)
Methods: Connectivity, Statistics, Machine learning
Keywords: MRI, multiple sclerosis, portable MRI, low-field MRI, white matter lesions, lesion segmentation, machine learning, deep learning
Topic: Multiple Sclerosis Research Studies (Clinical Neurology, Medicine), according to OpenAlex
Funding: National Institute for Health Research (NIHR) (NIHR203316)
Citations: not cited yet (Europe PMC); 36 references in the paper

Abstract

White matter lesion (WML) identification, assessment, and characterization using magnetic resonance imaging (MRI) are fundamental for diagnosis and monitoring of multiple sclerosis (MS). Portable ultra-low field (pULF) MRI at 64 millitesla (mT) has been shown to visualize WML with at least one dimension greater than 4 mm. An automated WML segmentation tool catered to pULF-MRI can provide standardized and accurate quantitative measurements of WML volume. In this study, we sought to investigate and compare the accuracy of machine-learning (ML) and deep-learning (DL) pULF MRI segmentation tools. Same-day paired pULF (64mT) and high-field (HF, 3T) MRI scans from 84 adults with MS or suspected-MS (mean age±SD: 48±13, 62 females) included T2-FLAIR and T1w images. Reference WML segmentations were manually annotated on pULF T2-FLAIR for all scans, with WML confirmed with registered HF T2-FLAIR. HF reference WML segmentations were created. Four automated segmentation methods were applied to pULF scans: Method for Inter-Modal Segmentation Analysis (MIMoSA), an ML algorithm trained on HF WML masks; WMH-SynthSeg, a convolutional neural network model with flexible segmentation capabilities across field strengths and resolution; nnU-Net, a DL algorithm trained on pULF reference WML masks; and Pseudo-Label Assisted nnU-Net (PLAn), a DL algorithm pre-trained on HF reference WML masks and refined with 64mT reference WML masks. Two models were trained with nnU-Net, one using T2-FLAIR images only (nnU-Net-FL) and one using T1w and T2-FLAIR images (nnU-Net-FL/T1). The same was done with PLAn, creating PLAn-FL and PLAn-FL/T1. The six automated WML segmentation outputs were compared to the manual segmentations to determine Dice Similarity Coefficient (DSC) scores. Associations of WML volume estimates with clinical measures were investigated.

DSC scores with pULF reference WML masks from PLAn-FL (DSC mean±SD: 0.50±0.24) outperformed MIMoSA (0.24±0.20, p<0.0001), WMH-SynthSeg (0.30±0.18, p<0.0001), nnU-Net-FL (0.41±0.24, p<0.0001), and nnU-Net-FL/T1 (0.41 ± 0.26, p = 0.0004). Worse Expanded Disability Status Scale (EDSS) and Scripps Neurologic Rating Scale (SNRS) scores were correlated with higher WML volumes in the pULF and HF reference masks. They were also correlated with WML volumes derived from WHM-SynthSeg, nnU-Net-FL, nnU-Net-FL/T1, PLAn-FL, and PLAn-FL/T1, but not MIMoSA. After adjusting for age, WHM-SynthSeg, nnU-Net FL, nnU-Net-FL/T1, PLAn-FL, and PLAn-FL/T1 had significant associations with EDSS and SNRS scores.

nnU-Net and PLAn performed best in segmenting WML on pULF-MRI at 64 mT, providing accurate quantitative estimates of WML burden. Moreover, WML volumes estimated by these algorithms were associated with clinical measures of disability, underscoring their utility for reflecting clinical and radiological disease severity. Given pULF-MRI’s mobility and lower cost, these findings highlight its relevance in clinical trials, particularly in involving more participants who face logistical constraints and barriers.

Reproduced under the paper's license (CC0), from the paper cited above.

Repository

Its files are read in the Code ↔ Paper reader above.

MIC-DKFZ/nnUNet

License: Apache-2.0
State: the link answers, verified on 27 October 2026
Evidence: files inventoried
Commit: 1489d746e084459581ff20382c1241d8cc2eb258, 22 October 2026
Languages: Python (228), Shell (7)
Size: 315 files, 235 scripts
Software Heritage: archived
Found in: the text, “Automated Lesion Segmentation Methods”
Holds: README, license file, environment (pyproject.toml, setup.py), tests, continuous integration, documentation
Not found: CITATION.cff
Tools: nnU-Net (136 files), NumPy (82 files), PyTorch (62 files), SimpleITK (15 files), scikit-image (7 files), SciPy (7 files), NiBabel (5 files), pandas (4 files), tifffile (4 files), Matplotlib (2 files), Pillow (1 file), pydicom (1 file), scikit-learn (1 file), seaborn (1 file)
Availability: 2 checks, the latest on 27 October 2026: the link answers
  • 27 October 2026: the link answers
  • 26 September 2026: the link answers
237 files

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;
  • 235 scripts, each with its path and the digest of its content;
  • no match between paragraphs and code yet;
  • 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

No dataset and no data link were found in the paper.

Availability of data and material

Supplemental data, including deidentified clinical data, deidentified imaging data, and deep-learning models (nnU-Net-FL, nnU-Net-FL/T1w, PLAn-FL, and PLAn-FL/T1w), will be released upon publication.

Reproduced under the paper's license (CC0), 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 2, 28 September 2026

  • Language: n/a → en
  • Authors: added Ashley A. Thommana (0009-0004-1117-8987); Corinne A. Donnay (0009-0006-4856-8422); Gina Norato (0000-0003-1324-0217); María I. Gaitán (0000-0003-4455-5641); Daniel S. Reich (0000-0002-2628-4334); removed Ashley A. Thommana; Corinne A. Donnay; Gina Norato; María I. Gaitán; Daniel S. Reich

Version 1, 27 September 2026: the first record

Recorded: type, journal, dates, 8 authors, 8 keywords, 1 funder, 34 references.

Cite

This paper

Thommana, A. A., Donnay, C. A., Norato, G., Gaitán, M. I., Griffanti, L., Nair, G., Reich, D. S., & Okar, S. V. (2026). Portable Ultra-Low Field MRI Deep-Learning Algorithms for White Matter Lesion Segmentation Improve Accuracy and Reflect Clinical Disability in Multiple Sclerosis. medRxiv (preprint). https://doi.org/10.64898/2026.07.15.26357954

BibTeX

@article{thommana2026portable,
author = {Thommana, Ashley A. and Donnay, Corinne A. and Norato, Gina and Gaitán, María I. and Griffanti, Ludovica and Nair, Govind and Reich, Daniel S. and Okar, Serhat V.},
title = {{Portable Ultra-Low Field MRI Deep-Learning Algorithms for White Matter Lesion Segmentation Improve Accuracy and Reflect Clinical Disability in Multiple Sclerosis}},
journal = {medRxiv (preprint)},
year = {2026},
month = jul,
publisher = {medRxiv},
doi = {10.64898/2026.07.15.26357954},
url = {https://doi.org/10.64898/2026.07.15.26357954}
}

RIS

TY - JOUR
AU - Thommana, Ashley A.
AU - Donnay, Corinne A.
AU - Norato, Gina
AU - Gaitán, María I.
AU - Griffanti, Ludovica
AU - Nair, Govind
AU - Reich, Daniel S.
AU - Okar, Serhat V.
TI - Portable Ultra-Low Field MRI Deep-Learning Algorithms for White Matter Lesion Segmentation Improve Accuracy and Reflect Clinical Disability in Multiple Sclerosis
T2 - medRxiv (preprint)
J2 - medRxiv
PY - 2026
DA - 2026/07/17
PB - medRxiv
DO - 10.64898/2026.07.15.26357954
UR - https://doi.org/10.64898/2026.07.15.26357954
LA - en
ER -

CSL-JSON

{
"id": "10.64898/2026.07.15.26357954",
"type": "article",
"title": "Portable Ultra-Low Field MRI Deep-Learning Algorithms for White Matter Lesion Segmentation Improve Accuracy and Reflect Clinical Disability in Multiple Sclerosis",
"container-title": "medRxiv (preprint)",
"author": [
{
"family": "Thommana",
"given": "Ashley A."
},
{
"family": "Donnay",
"given": "Corinne A."
},
{
"family": "Norato",
"given": "Gina"
},
{
"family": "Gaitán",
"given": "María I."
},
{
"family": "Griffanti",
"given": "Ludovica"
},
{
"family": "Nair",
"given": "Govind"
},
{
"family": "Reich",
"given": "Daniel S."
},
{
"family": "Okar",
"given": "Serhat V."
}
],
"container-title-short": "medRxiv",
"DOI": "10.64898/2026.07.15.26357954",
"publisher": "medRxiv",
"URL": "https://doi.org/10.64898/2026.07.15.26357954",
"language": "en",
"issued": {
"date-parts": [
[
2026,
7,
17
]
]
}
}

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:10.1136/jnnp-2025-335884 [code]
Diffusivity anisotropy signature of slowly expanding lesions predicts progression independent of relapse activity in multiple sclerosis.
Journal: Journal of neurology, neurosurgery, and psychiatry
In common: nnU-Net, pydicom, SimpleITK, 11 other tools, multiple sclerosis, structural MRI / diffusion, clinical / translational, 1 reference
[2] doi:10.3389/fnimg.2023.1252261 [code]
Pseudo-Label Assisted nnU-Net enables automatic segmentation of 7T MRI from a single acquisition.
Journal: Frontiers in neuroimaging
In common: nnU-Net, pydicom, SimpleITK, 11 other tools, multiple sclerosis, structural MRI / diffusion, 1 reference
[3] doi:10.3390/pathogens13110920
Radiological Changes in the Spinal Cord and Brain of Patients with HTLV-1-Associated Myelopathy/Tropical Spastic Paraparesis (HAM/TSP).
Journal: Pathogens (Basel, Switzerland)
In common: multiple sclerosis, structural MRI / diffusion, clinical / translational, 1 reference, 3 authors
[4] doi:10.3389/fmed.2026.1875760 [code]
Adaptive multi-stage domain unlearning for white-matter lesion segmentation.
Journal: Frontiers in medicine
In common: nnU-Net, pydicom, SimpleITK, 11 other tools, structural MRI / diffusion, 1 reference
[5] doi:10.1371/journal.pone.0323398 [code]
Ratio maps of T1w/T2w MRI signal intensity do not improve deep-learning segmentation of pediatric brain tumors.
Journal: PloS one
In common: nnU-Net, pydicom, SimpleITK, 11 other tools, structural MRI / diffusion, 1 reference
[6] doi:10.1016/j.media.2023.102789 [code]
SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining.
Journal: Medical image analysis
In common: nnU-Net, pydicom, SimpleITK, 11 other tools, structural MRI / diffusion, 1 reference
[7] doi:10.3389/fmed.2021.740248 [code]
A Clinically-Compatible Workflow for Computer-Aided Assessment of Brain Disease Activity in Multiple Sclerosis Patients.
Journal: Frontiers in medicine
In common: nnU-Net, pydicom, SimpleITK, 11 other tools, multiple sclerosis, structural MRI / diffusion, clinical / translational
[8] doi:10.1186/s12880-025-01687-0 [code]
The impact of cerebral vessels morphological alteration and white matter hyperintensities burden on the one-year risk of ischemic stroke recurrence.
Journal: BMC medical imaging
In common: nnU-Net, pydicom, SimpleITK, 11 other tools, structural MRI / diffusion, clinical / translational
[9] doi:10.1002/hipo.70124 [code]
Association Between Anterior Hippocampal Gyrification and Episodic Memory Performance in Neurotypical Young Adults.
Journal: Hippocampus
In common: nnU-Net, pydicom, SimpleITK, 11 other tools, structural MRI / diffusion
[10] doi:10.1186/s12880-026-02335-x [code]
Automatic lateral ventricle and choroid plexus segmentation method in infant brain MR images.
Journal: BMC medical imaging
In common: nnU-Net, pydicom, SimpleITK, 11 other tools, structural MRI / diffusion

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.

Add the badge to the code's README

OSCR: the badge of this paper

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 -->
[![OSCR](https://openscicode.org/badge/doi/10.64898/2026.07.15.26357954.svg)](https://openscicode.org/badge/doi/10.64898/2026.07.15.26357954)
<!-- oscr-badge:end -->
reStructuredText
.. oscr-badge:start

.. image:: https://openscicode.org/badge/doi/10.64898/2026.07.15.26357954.svg
   :target: https://openscicode.org/badge/doi/10.64898/2026.07.15.26357954
   :alt: OSCR

.. oscr-badge:end
HTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.64898/2026.07.15.26357954"><img src="https://openscicode.org/badge/doi/10.64898/2026.07.15.26357954.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.