OSCR

Volumetric reference data of the orbit: a deep learning MRI analysis in the German national cohort.

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, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Markdown · 83 lines · 2.1 KB · no license

  1. # Welcome
  3. This repository contains the model parameters of the deep learning eye segmentation model used in our paper
  5. **Volumetric Reference Data of the Orbit: A Deep Learning MRI Analysis in the German National Cohort**
  7. Authors: Moises Felipe Molina-Fuentes; Kevin Wornath; Marco Reisert; Susanne Rospleszcz; J.E. Rod; Daniel Boehringer; Thomas Kroencke; Thoralf Niendorf; Tobias Pischon; Henry Voelzke; Steffen Ringhof; Thomas Reinhard; Fabian Bamberg; Wolf Alexander Lagreze; Christopher L. Schlett; Navid Farassat
  10. ## Install patchwork and download model
  12. To install patchwork do the following
  14. ```bash
  15. pip install git+https://[email hidden]/reisert/patchwork.git
  16. ```
  18. this should install all necessary packages, including tensorflow and numpy.
  20. Now get the model weights
  22. ```bash
  23. git clone https://[email hidden]/reisert/eye_model.git
  24. ```
  26. This creates a folder `eye_model` in your current folder. The model definition is stored in `model_patchwork.json`; the weights are stored in the `model_patchwork.weights` folder.
  29. ## Apply network
  31. The network expects the orbital MRI image as nifti.
  33. Here's an example of applying the network
  35. ```python
  36. import tensorflow as tf
  37. import patchwork.model as patchwork
  39. out = "someresult.nii"
  40. modeljson = "path/to/eye_model/model_patchwork.json" # this path depends on the download location of the weights
  42. inputnii = "orbita.nii"
  44. model = patchwork.PatchWorkModel.load(modeljson)
  46. res, r = model.apply_on_nifti(
  47. [inputnii],
  48. out,
  49. generate_type='random',
  50. repetitions=16,
  51. num_chunks=20,
  52. out_typ='atls',
  53. level='mix',
  54. sparse_suppression=1,
  55. label_names=[
  56. 'Orbita',
  57. 'Bulbusrest',
  58. 'Vitreous',
  59. 'Lens',
  60. 'MOI',
  61. 'MOS',
  62. 'MRI',
  63. 'MRL',
  64. 'MRM',
  65. 'MRS',
  66. 'Opticus',
  67. 'VK',
  68. 'SSS',
  69. ],
  70. scale_to_original=True,
  71. branch_factor=4,
  72. lazyEval={
  73. 'fraction': 0.5,
  74. 'reduceFun': tf.reduce_mean,
  75. 'attentionFun': tf.math.exp,
  76. },
  77. )
  78. ```
  80. The output `someresult.nii` contains the resulting atlas label image.
  83. Have fun!

README.md at commit ed5ef2a, no license · at the source

Overview

Authors: Navid Farassat1, Marco Reisert2, Susanne Rospleszcz3, J. E. Rod4, Daniel Böhringer1, Thomas Kroencke5,6, Thoralf Niendorf7, Tobias Pischon8,9,10, Henry Völzke11, Steffen Ringhof3, Thomas Reinhard1, Fabian Bamberg3, Wolf Alexander Lagrèze1, Christopher L. Schlett3, Kevin Wornath3, Moises Felipe Molina-Fuentes3,12
ORCID iDs: Navid Farassat
  1. Eye Center, Faculty of Medicine, Medical Center - University of Freiburg, University of Freiburg,Freiburg im Breisgau, Germany
  2. Medical Physics, Department of Diagnostic and Interventional Radiology, Faculty of Medicine, Medical Center - University of Freiburg, University of Freiburg,Freiburg im Breisgau, Germany
  3. Department of Diagnostic and Interventional Radiology, Faculty of Medicine, Medical Center - University of Freiburg, University of Freiburg,Freiburg im Breisgau, Germany
  4. Division of Health Sciences, Department of Public Health, Universidad del Norte,Barranquilla, Colombia
  5. Department of Diagnostic and Interventional Radiology, University Hospital Augsburg,Augsburg, Germany
  6. Centre for Advanced Analytics and Predictive Sciences, University of Augsburg,Augsburg, Germany
  7. Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrueck Center for Molecular Medicine in the Helmholtz Association,Berlin, Germany
  8. Molecular Epidemiology Research Group, Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC),Berlin, Germany
  9. Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC), Biobank Technology Platform,Berlin, Germany
  10. Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin,Berlin, Germany
  11. Institute for Community Medicine, University Medicine Greifswald,Greifswald, Germany
  12. Department of Neuroradiology, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich,Zurich, Switzerland
Institutions: University of Freiburg (Germany); Universidad del Norte (Colombia); University Hospital Augsburg (Germany); University of Augsburg (Germany); Max Delbrück Center (Germany); Humboldt-Universität zu Berlin (Germany); Universitätsmedizin Greifswald (Germany); University Hospital Zurich (Switzerland)
Journal: Scientific reports, volume 16, issue 1, article 27113
Dates: received 18 May 2026; accepted 20 August 2026; published online 29 August 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1038/s41598-026-68393-x · PMID 42668292 · PMCID PMC13526028 · OpenAlex W7204635485
Open access: gold, a free copy (OpenAlex)
Status: empty repository
Categories: structural MRI / diffusion (modality), human (organism)
Methods: Statistics, Connectivity, Graphs, Machine learning
Keywords: Orbit, Morphometry, Reference data, NAKO, MRI, Germany, Anatomy, Computational biology and bioinformatics, Diseases, Health care, Medical research
MeSH: Deep Learning*, Magnetic Resonance Imaging*, Orbit*, Adult, Aged, Cohort Studies, Female, Germany, Humans, Image Processing, Computer-Assisted, Male, Middle Aged, Reference Values (* major topic)
Topic: Ocular Disorders and Treatments (Genetics, Biochemistry, Genetics and Molecular Biology), according to OpenAlex
Funding: Universitätsklinikum Freiburg (8975)
Citations: not cited yet (Europe PMC); 33 references in the paper

Abstract

Manual segmentation of orbital magnetic resonance imaging (MRI) is labor-intensive, hindering large-scale morphometric studies. To overcome this, we developed a fully automated deep learning pipeline to segment orbital MRIs and establish age- and sex-stratified normative reference data. We analyzed T1-weighted brain MRIs from 30,868 participants in the population-based German National Cohort (NAKO). After quality control, 28,779 participants (mean age 48.1 years; 44.1% female) were included. The model, validated against expert manual segmentations, accurately extracted 34 volumetric and geometric parameters across 15 orbital structures (Dice Similarity Coefficients: vitreous 0.97, lens 0.89, optic nerve 0.85). Mean [SD] axial length was 23.5 [1.2] mm. Mean [SD] volumes were 34.4 [3.9] cm³ for total orbital contents, 6.3 [0.8] cm³ for the vitreous, and 0.17 [0.03] cm³ for the lens. Males exhibited significantly larger dimensions across all parameters (p < 0.001). Age-stratified percentile curves revealed continuous age-dependent lens growth (Spearman’s ρ = 0.57 in men, 0.51 in women) alongside modest volume increases in the orbit, optic nerve, and extraocular muscles. This deep learning tool effectively resolved the bottleneck of manual segmentation, providing comprehensive orbital reference data for the German population. This foundation enables future high-throughput epidemiological research into the associations between orbital anatomy, systemic health, and disease.

Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1038/s41598-026-68393-x.

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

Repository

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

reisert/eye_model

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: ed5ef2a87787235ac8091bd8c5564d04653d9436, 16 July 2026
Size: 4 files, 0 scripts
Software Heritage: not archived
Found in: “Data availability”
Holds: README
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
1 file
At the source: bitbucket.org/reisert/eye_model/src/main/

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;
  • 0 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.

Data availability

Due to strict data protection regulations and the informed consent framework of the NAKO study, the data used in this study cannot be made publicly available. However, access to and use of NAKO (German National Cohort) data and biospecimens can be obtained via an electronic application portal (https://transfer.nako.de/transfer/index). To facilitate reproducibility, the trained deep learning model has been deposited in a public repository and can be accessed at (https://bitbucket.org/reisert/eye_model/src/main/). The custom MATLAB scripts used for post-processing and morphometric analysis are available upon reasonable request.

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, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 16 authors, 11 keywords, 13 MeSH terms, 1 funder, 33 references.

Cite

This paper

Farassat, N., Reisert, M., Rospleszcz, S., Rod, J. E., Böhringer, D., Kroencke, T., Niendorf, T., Pischon, T., Völzke, H., Ringhof, S., Reinhard, T., Bamberg, F., Lagrèze, W. A., Schlett, C. L., Wornath, K., & Molina-Fuentes, M. F. (2026). Volumetric reference data of the orbit: a deep learning MRI analysis in the German national cohort. Scientific reports, 16(1), 27113. https://doi.org/10.1038/s41598-026-68393-x

BibTeX

@article{farassat2026volumetric,
author = {Farassat, Navid and Reisert, Marco and Rospleszcz, Susanne and Rod, J. E. and Böhringer, Daniel and Kroencke, Thomas and Niendorf, Thoralf and Pischon, Tobias and Völzke, Henry and Ringhof, Steffen and Reinhard, Thomas and Bamberg, Fabian and Lagrèze, Wolf Alexander and Schlett, Christopher L. and Wornath, Kevin and Molina-Fuentes, Moises Felipe},
title = {{Volumetric reference data of the orbit: a deep learning MRI analysis in the German national cohort}},
journal = {Scientific reports},
year = {2026},
month = aug,
volume = {16},
number = {1},
pages = {27113},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/s41598-026-68393-x},
url = {https://doi.org/10.1038/s41598-026-68393-x},
pmid = {42668292},
pmcid = {PMC13526028}
}

RIS

TY - JOUR
AU - Farassat, Navid
AU - Reisert, Marco
AU - Rospleszcz, Susanne
AU - Rod, J. E.
AU - Böhringer, Daniel
AU - Kroencke, Thomas
AU - Niendorf, Thoralf
AU - Pischon, Tobias
AU - Völzke, Henry
AU - Ringhof, Steffen
AU - Reinhard, Thomas
AU - Bamberg, Fabian
AU - Lagrèze, Wolf Alexander
AU - Schlett, Christopher L.
AU - Wornath, Kevin
AU - Molina-Fuentes, Moises Felipe
TI - Volumetric reference data of the orbit: a deep learning MRI analysis in the German national cohort
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/08/29
VL - 16
IS - 1
SP - 27113
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/s41598-026-68393-x
UR - https://doi.org/10.1038/s41598-026-68393-x
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41598-026-68393-x",
"type": "article-journal",
"title": "Volumetric reference data of the orbit: a deep learning MRI analysis in the German national cohort",
"container-title": "Scientific reports",
"author": [
{
"family": "Farassat",
"given": "Navid"
},
{
"family": "Reisert",
"given": "Marco"
},
{
"family": "Rospleszcz",
"given": "Susanne"
},
{
"family": "Rod",
"given": "J. E."
},
{
"family": "Böhringer",
"given": "Daniel"
},
{
"family": "Kroencke",
"given": "Thomas"
},
{
"family": "Niendorf",
"given": "Thoralf"
},
{
"family": "Pischon",
"given": "Tobias"
},
{
"family": "Völzke",
"given": "Henry"
},
{
"family": "Ringhof",
"given": "Steffen"
},
{
"family": "Reinhard",
"given": "Thomas"
},
{
"family": "Bamberg",
"given": "Fabian"
},
{
"family": "Lagrèze",
"given": "Wolf Alexander"
},
{
"family": "Schlett",
"given": "Christopher L."
},
{
"family": "Wornath",
"given": "Kevin"
},
{
"family": "Molina-Fuentes",
"given": "Moises Felipe"
}
],
"container-title-short": "Sci Rep",
"volume": "16",
"issue": "1",
"page": "27113",
"DOI": "10.1038/s41598-026-68393-x",
"PMID": "42668292",
"PMCID": "PMC13526028",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41598-026-68393-x",
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
29
]
]
}
}

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:10.1038/s41398-026-04131-1 [code]
Multimodal phenotypic classification of generalized anxiety and panic using structural MRI data and psychosocial factors: machine learning results from the German National Cohort (NAKO) study.
Journal: Translational psychiatry
In common: structural MRI / diffusion, 3 references
[2] doi:10.1038/s41593-026-02359-0 [code]
The cross-site reproducibility of MRI morphometric phenotypes in psychiatric disorders.
Journal: Nature neuroscience
In common: structural MRI / diffusion, 1 reference
[3] doi:10.1038/s41380-026-03691-4 [code]
Breaking the norm: population-scale deviations of brain structure in depression and anxiety.
Journal: Molecular psychiatry
In common: structural MRI / diffusion, 1 reference
[4] doi:10.1002/alz.71822 [code]
SynthPET: A 3D generative AI approach for FDG-PET image synthesis from T1-weighted MRI and ASL CBF in Alzheimer's disease.
Journal: Alzheimer's & dementia : the journal of the Alzheimer's Association
In common: structural MRI / diffusion, 1 reference
[5] doi:10.3390/diagnostics16121791
An Explainable Multi-Scale Deep Learning Framework for Multi-Class Brain MRI Classification.
Journal: Diagnostics (Basel, Switzerland)
In common: structural MRI / diffusion, 1 reference
[6] doi:10.1162/imag.a.1303
Composite reaction time and variability correlate with whole-brain white-matter characteristics.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: structural MRI / diffusion, 1 reference
[7] doi:10.1016/j.neuroimage.2026.121921 [code]
A hierarchical brain MRI atlas of the coppery titi monkey (Plecturocebus cupreus).
Journal: NeuroImage
In common: structural MRI / diffusion, 1 reference
[8] doi:10.1038/s43856-026-01722-3 [code]
Local and global patterns support medical imaging as a biomarker of ageing.
Journal: Communications medicine
In common: 1 reference
[9] doi:10.1038/s41746-026-02651-0 [code]
AI Augmented Confocal Laser Endomicroscopy for Rapid Intraoperative Diagnosis of Brain Tumors.
Journal: NPJ digital medicine
In common: 1 reference

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.

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: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.