Fast surface reconstruction of human brain MRI: benchmarking deep-learning based morphometry tools.
One block of code here has 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 1 match
- [1] § Materials and methods › Processing pipeline with different segmentation/surface reconstruction methods ↔ dldirect/radiomics_extractor.py, lines 1 to 20 · score 0.61 · accumbens, caudate, pallidum, putamen, thalamus, ventral · block
oscr:b:BTTHJXMD6B9WK-B· 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 · 115 lines · 4.4 KB · BSD-3-Clause · 1 match
- import argparse
- import os
- import sys
- import pathlib
- import radiomics
- import SimpleITK as sitk
- import csv
- import pandas as pd
- LABELS_FS = ['Left-Lateral-Ventricle', 'Left-Inf-Lat-Vent', 'Left-Thalamus-Proper', 'Left-Caudate', 'Left-Putamen', 'Left-Pallidum', '3rd-Ventricle',
- '4th-Ventricle', 'Brain-Stem', 'Left-Hippocampus', 'Left-Amygdala', 'Left-Accumbens-area', 'Left-VentralDC', 'Left-choroid-plexus',
- 'Right-Lateral-Ventricle', 'Right-Inf-Lat-Vent', 'Right-Thalamus-Proper', 'Right-Caudate', 'Right-Putamen', 'Right-Pallidum', 'Right-Hippocampus',
- 'Right-Amygdala', 'Right-Accumbens-area', 'Right-VentralDC', 'Right-choroid-plexus', '5th-Ventricle',
- 'CC_Posterior', 'CC_Mid_Posterior', 'CC_Central', 'CC_Mid_Anterior', 'CC_Anterior']
- LABELS_DL = ['Left-Ventricle-all:101', 'Left-Thalamus-Proper', 'Left-Caudate', 'Left-Putamen', 'Left-Pallidum', 'Left-Hippocampus', 'Left-Amygdala',
- 'Left-Accumbens-area', 'Left-VentralDC', 'Right-Ventricle-all:112', 'Right-Thalamus-Proper', 'Right-Caudate', 'Right-Putamen',
- 'Right-Pallidum', 'Right-Hippocampus', 'Right-Amygdala', 'Right-Accumbens-area', 'Right-VentralDC', 'Brain-Stem',
- '3rd-Ventricle', '4th-Ventricle', 'Corpus-Callosum:125']
- def lut_parse():
- lut = pd.read_csv('{}/fs_lut.csv'.format(pathlib.Path(__file__).parent.resolve()))
- lut = dict(zip(lut.Key, lut.Label))
- return lut
- def run_main(subject_dirs, aseg_file, labels, results_csv):
- LUT = lut_parse()
- print(results_csv)
- with open(results_csv, 'w') as out_file:
- writer = csv.writer(out_file, delimiter=',')
- header = None
- for subjects_dir in subject_dirs:
- for subject_name in sorted(os.listdir(subjects_dir)):
- fname = '{}/{}/{}'.format(subjects_dir, subject_name, aseg_file)
- if not os.path.exists(fname):
- print('{}: {} not found. Skipping'.format(subject_name, aseg_file))
- continue
- print(subject_name)
- fields = list()
- values = list()
- img = sitk.ReadImage(fname)
- for label in labels:
- if ':' in label:
- label, label_id = label.split(':')
- else:
- label_id = LUT[label]
- radiomics.setVerbosity(50)
- shape_features = radiomics.shape.RadiomicsShape(img, img, **{'label': int(label_id)})
- shape_features.enableAllFeatures()
- results = shape_features.execute()
- for key in results.keys():
- fields.append('{}.{}'.format(label, key))
- values.append(float(results[key]) if results['VoxelVolume'] > 0 else 'nan')
- if header is None:
- header = fields
- writer.writerow(['Subject'] + header)
- else:
- assert header == fields
- writer.writerow([subject_name] + values)
- def main():
- parser = argparse.ArgumentParser(description='Extract radiomics features from subjects')
- parser.add_argument(
- '--aseg_file',
- type=str,
- default='T1w_norm_seg.nii.gz',
- help='Path (relative to subject dir) of aseg segmentation file.'
- )
- parser.add_argument(
- '--labels',
- type=str,
- nargs='+',
- metavar='label',
- default=['DL'],
- help='List of labels. FreeSurfer ids (from fs_lut) are used per default. '
- 'Can also be: label:id. Example: "Left-Hippocampus:9 Right-Hippocampus:21." '
- 'Use "FS" for all FreeSurfer labels or "DL" for all DL+DiReCT labels'
- )
- parser.add_argument(
- '--results_csv',
- type=str,
- required=True,
- help='CSV-File to store results'
- )
- parser.add_argument(
- 'subject_dirs',
- metavar='dir',
- type=str,
- nargs='+',
- help='Directories with subjects (FreeSurfer or DL+DiReCT results dir)'
- )
- args = parser.parse_args()
- for dir in args.subject_dirs:
- if not os.path.exists(dir):
- print('{} not found'.format(args.dir))
- sys.exit(1)
- labels = LABELS_FS if args.labels[0] == 'FS' else LABELS_DL if args.labels[0] == 'DL' else args.labels
- run_main(args.subject_dirs, args.aseg_file, labels, args.results_csv)
- if __name__ == '__main__':
- sys.exit(main())
radiomics_extractor.py at commit 0cb3d72, under BSD-3-Clause · at the source
Overview
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology University of Bern, Inselspital, Bern University Hospital,Bern, Switzerland
- European Campus Rottal-Inn, Technische Hochschule Deggendorf,Max-Breiherr-Straße 32, 84347 Pfarrkirchen, Germany
Abstract
Time efficient and reliable pipelines for quantitative evaluation of structural brain MRI are essential to utilize the potential of morphometry tools for large scale research projects as well as to pave the path towards future clinical applications. In our work, we have explored this idea by evaluating three deep learning models for brain segmentation and cortex parcellation (DeepSCAN, FastSurferCNN and QuickNAT) as input for an 11-min surface reconstruction pipeline adapted from the well studied open source software package FreeSurfer. Performance was assessed using both, large publicly available human MRI datasets and a synthetic dataset with known metrics and reference surfaces. Evaluation criteria included closeness to the surface reconstruction by FreeSurfer’s full recon-all pipeline, reproducibility within same-session rescans, performance stability across a wide age range, sensitivity to variations of the grey-white contrast in the MRI and accuracy regarding metrics of synthetic surfaces. Metrics derived from the DeepSCAN-based pipeline demonstrated the highest agreement with FreeSurfer in the human data and the greatest fidelity to the expected metrics in the synthetic dataset. Our findings identify the DeepSCAN-based surface reconstruction pipeline as a rapid, yet reliable alternative to established research-grade structural MRI processing. Time expenditure and reliability suggest it is suitable for research applications with high-throughput requirements. This is an essential first step towards necessary subsequent studies aimed at evaluating robustness, pathological variability, and utility in the context of clinical diagnostics.
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 1 match between paragraphs and lines of code.
SCAN-NRAD/DL-DiReCT-V2
0cb3d728b4ef78706e37d12309bc93f12a7c97ef, 22 September 2026Availability: 1 check, the latest on 27 September 2026: the link answers
- 27 September 2026: the link answers
27 files
- dldirect/
DeepSCAN_Anatomy_Newnet_ , Python, 488 linesapply.py - dldirect/
DiReCT.py , Python, 217 lines - dldirect/
__init__.py , Python, 1 line - dldirect/
bet.py , Python, 92 lines - dldirect/
compare_surfaces.py , Python, 211 lines - dldirect/
conform.py , Python, 48 lines - dldirect/
crop.py , Python, 76 lines - dldirect/
direct_cuda.py , Python, 802 lines - dldirect/
dl_wm_surface_parallel_d , Python, 157 linesev.py - dldirect/
extract_morphometrics.py , Python, 255 lines - dldirect/
extract_stats.py , Python, 120 lines - dldirect/
field_pial_optimize.py , Python, 271 lines - dldirect/
field_pial_prototype.py , Python, 2,192 lines - dldirect/
preparedata.py , Python, 195 lines - dldirect/
radiomics2table.py , Python, 48 lines - dldirect/
radiomics_extractor.py , Python, 115 lines, 1 match - dldirect/
run_script.py , Python, 10 lines - dldirect/
scripts/ , Shell, 136 linesbatch-dl+direct.sh - dldirect/
scripts/ , Shell, 56 linesdirect.sh - dldirect/
scripts/ , Shell, 175 linesdl+direct-nofs.sh - dldirect/
scripts/ , Shell, 177 linesdl+direct.sh - dldirect/
scripts/ , Shell, 72 linesfast_surface_reconstruct ion.sh - dldirect/
smooth_pial.py , Python, 156 lines - dldirect/
stats2table.py , Python, 100 lines - dldirect/
surface_frames.py , Python, 181 lines - LICENSE, License, 29 lines
- README.md, Text, 66 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;
- 25 scripts, each with its path and the digest of its content;
- 1 match 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
No dataset and no data link were found in the paper.
Data availability
There is no data release in this paper. All dataset used are public. All scripts necessary to run the fast pipeline reconstruction are 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, 27 September 2026: the first record
Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 8 keywords, 14 MeSH terms, 2 funders, 53 references.
Cite
This paper
Mello, V. B. B., McKinley, R., Wiest, R., & Rummel, C. (2026). Fast surface reconstruction of human brain MRI: benchmarking deep-learning based morphometry tools. Scientific reports, 16(1), 20350. https://
BibTeX
@article{mello2026fast,
author = {Mello, Victor B. B. and McKinley, Richard and Wiest, Roland and Rummel, Christian},
title = {{Fast surface reconstruction of human brain MRI: benchmarking deep-learning based morphometry tools}},
journal = {Scientific reports},
year = {2026},
month = jun,
volume = {16},
number = {1},
pages = {20350},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/
url = {https://
pmid = {42286078},
pmcid = {PMC13328385}
}
RIS
TY - JOUR
AU - Mello, Victor B. B.
AU - McKinley, Richard
AU - Wiest, Roland
AU - Rummel, Christian
TI - Fast surface reconstruction of human brain MRI: benchmarking deep-learning based morphometry tools
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/
VL - 16
IS - 1
SP - 20350
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.1038/
"type": "article-journal",
"title": "Fast surface reconstruction of human brain MRI: benchmarking deep-learning based morphometry tools",
"container-title": "Scientific reports",
"author": [
{
"family": "Mello",
"given": "Victor B. B."
},
{
"family": "McKinley",
"given": "Richard"
},
{
"family": "Wiest",
"given": "Roland"
},
{
"family": "Rummel",
"given": "Christian"
}
],
"container-title-short":
"volume": "16",
"issue": "1",
"page": "20350",
"DOI": "10.1038/
"PMID": "42286078",
"PMCID": "PMC13328385",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
12
]
]
}
}
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.nicl.2024.103624 [code]
- Cortical thickness and grey-matter volume anomaly detection in individual MRI scans: Comparison of two methods.Journal: NeuroImage. ClinicalIn common: PyRadiomics, SimpleITK, ANTs, 7 other tools, structural MRI / diffusion, 14 references
- [2] doi:10.3389/fneur.2022.812432 [code]
- A Quantitative Imaging Biomarker Supporting Radiological Assessment of Hippocampal Sclerosis Derived From Deep Learning-Based Segmentation of T1w-MRI.Journal: Frontiers in neurologyIn common: PyRadiomics, SimpleITK, ANTs, 6 other tools, structural MRI / diffusion, 11 references
- [3] doi:10.1186/s40708-022-00155-7 [code]
- Fast cortical surface reconstruction from MRI using deep learning.Journal: Brain informaticsIn common: Nighres, SimpleITK, ANTs, 5 other tools, methods / tools, structural MRI / diffusion, 9 references
- [4] doi:10.1002/hbm.70560
- Mitigating the Impact of MR Sequence Parameters: Increasing the Robustness of DL-Based Cortical Thickness Estimates.Journal: Human brain mappingIn common: structural MRI / diffusion, 14 references
- [5] doi:10.1093/brain/awae139 [code]
- Transient brain structure changes after high phenylalanine exposure in adults with phenylketonuria.Journal: Brain : a journal of neurologyIn common: PyRadiomics, SimpleITK, ANTs, 6 other tools, structural MRI / diffusion, 6 references
- [6] doi:10.1162/imag.a.997 [code]
- Machine learning-based reconstruction of 2D MRI for quantitative morphometry in epilepsy.Journal: Imaging neuroscience (Cambridge, Mass.)In common: ANTs, FreeSurfer, NiBabel, 1 other tool, structural MRI / diffusion, 10 references
- [7] doi:10.1038/s41592-025-02599-1 [code]
- DeepPrep: an accelerated, scalable and robust pipeline for neuroimaging preprocessing empowered by deep learning.Journal: Nature methodsIn common: Nighres, SimpleITK, ANTs, 7 other tools, methods / tools, structural MRI / diffusion, 4 references
- [8] doi:10.1162/imag_a_00180 [code]
- VINNA for neonates: Orientation independence through latent augmentations.Journal: Imaging neuroscience (Cambridge, Mass.)In common: SimpleITK, scikit-image, NiBabel, 4 other tools, structural MRI / diffusion, 8 references
- [9] doi:10.1002/alz.71649 [code]
- Postmortem brain MRI reveals differential associations of subcortical and limbic volumes with cortical thinning and neurodegenerative pathologies.Journal: Alzheimer's & dementia : the journal of the Alzheimer's AssociationIn common: Nighres, SimpleITK, ANTs, 8 other tools, structural MRI / diffusion, 2 references
- [10] doi:10.1162/imag.a.960 [code]
- GOUHFI: A novel contrast- and resolution-agnostic segmentation tool for ultra-high-field MRI.Journal: Imaging neuroscience (Cambridge, Mass.)In common: SimpleITK, ANTs, scikit-image, 6 other tools, methods / tools, structural MRI / diffusion, 5 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, 25 scripts, and 1 match 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: sha256:698852bc64213bb1…
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/10.1038/s41598-026-55397-w)
<!-- oscr-badge:end -->reStructuredText
.. oscr-badge:start
.. image:: https://openscicode.org/badge/doi/10.1038/s41598-026-55397-w.svg
:target: https://openscicode.org/badge/doi/10.1038/s41598-026-55397-w
:alt: OSCR
.. oscr-badge:endHTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1038/s41598-026-55397-w"><img src="https://openscicode.org/badge/doi/10.1038/s41598-026-55397-w.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.
