OSCR

A dual space MRI radiomic network signature for risk stratification and subtyping of mild cognitive impairment.

Code ↔ Paper

1 match between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

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. [1] § STAR★Methods › Method details › Radiomic feature extraction ↔ Radiomics_R2SN.py, lines 8 to 25 · score 0.58 · Radiomic features, GLCM, GLDM, GLRLM, GLSZM, NGTDM · block oscr:b:GMYHSRCJ9TRWT-Y · 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 · 160 lines · 4.9 KB · no license · 1 match

  1. import argparse
  2. import numpy as np
  3. import pandas as pd
  4. import SimpleITK as sitk
  5. from radiomics import featureextractor
  6. def make_extractor(bin_width=25.0, normalize=False, include_shape=True):
  7. settings = {"binWidth": bin_width}
  8. if normalize:
  9. settings["normalize"] = True
  10. ext = featureextractor.RadiomicsFeatureExtractor(**settings)
  11. ext.disableAllImageTypes()
  12. ext.enableImageTypeByName("Original")
  13. ext.disableAllFeatures()
  14. classes = ["firstorder", "glcm", "glrlm", "glszm", "gldm", "ngtdm"]
  15. if include_shape:
  16. classes.append("shape")
  17. for c in classes:
  18. ext.enableFeatureClassByName(c)
  19. return ext
  20. def clean_features(feats):
  21. out = {}
  22. for k, v in feats.items():
  23. if k.startswith("diagnostics_"):
  24. continue
  25. try:
  26. out[k] = float(v)
  27. except Exception:
  28. pass
  29. return out
  30. def same_space(a, b, tol=1e-6):
  31. return (
  32. a.GetSize() == b.GetSize()
  33. and np.allclose(a.GetSpacing(), b.GetSpacing(), atol=tol)
  34. and np.allclose(a.GetOrigin(), b.GetOrigin(), atol=tol)
  35. and np.allclose(a.GetDirection(), b.GetDirection(), atol=tol)
  36. )
  37. def get_binary_mask_from_label(label_img, label):
  38. mask = sitk.Equal(label_img, int(label))
  39. return sitk.Cast(mask, sitk.sitkUInt8)
  40. def extract_global_radiomics(image, global_mask, out_csv, bin_width=25.0, normalize=False):
  41. ext = make_extractor(bin_width=bin_width, normalize=normalize, include_shape=True)
  42. feats = clean_features(ext.execute(image, global_mask))
  43. df = pd.DataFrame([feats])
  44. df.to_csv(out_csv, index=False)
  45. return df
  46. def extract_regional_features(image, region_mask, bin_width=25.0, normalize=False, include_shape=False):
  47. ext = make_extractor(bin_width=bin_width, normalize=normalize, include_shape=include_shape)
  48. labels = np.unique(sitk.GetArrayViewFromImage(region_mask))
  49. labels = [int(x) for x in labels if x > 0]
  50. rows = []
  51. for label in labels:
  52. roi = get_binary_mask_from_label(region_mask, label)
  53. try:
  54. feats = clean_features(ext.execute(image, roi))
  55. feats["region_id"] = label
  56. rows.append(feats)
  57. except Exception:
  58. continue
  59. if not rows:
  60. raise RuntimeError("No valid regional features were extracted.")
  61. df = pd.DataFrame(rows).set_index("region_id").sort_index()
  62. df = df.apply(pd.to_numeric, errors="coerce")
  63. df = df.dropna(axis=1, how="all")
  64. df = df.fillna(df.median(numeric_only=True))
  65. return df
  66. def build_rrsn(regional_df, out_csv):
  67. x = regional_df.copy()
  68. # Z-score by feature
  69. x = (x - x.mean(axis=0)) / (x.std(axis=0, ddof=0) + 1e-12)
  70. x = x.fillna(0.0)
  71. if len(x) == 1:
  72. net = np.array([[1.0]])
  73. else:
  74. net = np.corrcoef(x.to_numpy(), rowvar=True)
  75. net = np.nan_to_num(net, nan=0.0)
  76. np.fill_diagonal(net, 1.0)
  77. net_df = pd.DataFrame(net, index=x.index, columns=x.index)
  78. net_df.index.name = "region_id"
  79. net_df.to_csv(out_csv)
  80. return net_df
  81. def main():
  82. parser = argparse.ArgumentParser()
  83. parser.add_argument("--image", required=True, help="Input image path")
  84. parser.add_argument("--region_mask", required=True, help="Region label mask path")
  85. parser.add_argument("--global_mask", default=None, help="Global ROI mask path")
  86. parser.add_argument("--out_radiomics", default="radiomics.csv", help="Output radiomics CSV")
  87. parser.add_argument("--out_rrsn", default="rrsn.csv", help="Output RRSN CSV")
  88. parser.add_argument("--bin_width", type=float, default=25.0, help="PyRadiomics binWidth")
  89. parser.add_argument("--normalize", action="store_true", help="Enable intensity normalization")
  90. parser.add_argument(
  91. "--include_shape_in_network",
  92. action="store_true",
  93. help="Include shape features in regional network",
  94. )
  95. args = parser.parse_args()
  96. image = sitk.ReadImage(args.image)
  97. region_mask = sitk.ReadImage(args.region_mask)
  98. if args.global_mask is None:
  99. global_mask = sitk.Cast(region_mask > 0, sitk.sitkUInt8)
  100. else:
  101. global_mask = sitk.ReadImage(args.global_mask)
  102. if not same_space(image, region_mask):
  103. raise ValueError("image and region_mask are not in the same space")
  104. if not same_space(image, global_mask):
  105. raise ValueError("image and global_mask are not in the same space")
  106. extract_global_radiomics(
  107. image=image,
  108. global_mask=global_mask,
  109. out_csv=args.out_radiomics,
  110. bin_width=args.bin_width,
  111. normalize=args.normalize,
  112. )
  113. regional_df = extract_regional_features(
  114. image=image,
  115. region_mask=region_mask,
  116. bin_width=args.bin_width,
  117. normalize=args.normalize,
  118. include_shape=args.include_shape_in_network,
  119. )
  120. build_rrsn(regional_df, args.out_rrsn)
  121. print(f"Saved: {args.out_radiomics}")
  122. print(f"Saved: {args.out_rrsn}")
  123. if __name__ == "__main__":
  124. main()

Radiomics_R2SN.py at commit be306cf, no license · at the source

Overview

Authors: Diaohan Xiong1, Mengjiao Liu1, Jiamei Xie1, Zefeng Liu1, Junping Wang1
ORCID iDs: Junping Wang
  1. Department of Radiology, Tianjin Key Lab of Functional Imaging & Tianjin Institute of Radiology, Tianjin Medical University General Hospital, Tianjin 300052, China
Journal: iScience, volume 29, issue 7, article 116394
Dates: received 14 January 2026; accepted 28 May 2026; published online 12 June 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1016/j.isci.2026.116394 · PMID 42325556 · PMCID PMC13276304 · OpenAlex W7164524996
Open access: gold, a free copy (OpenAlex)
Status: code verified (how the code is found and verified)
Categories: structural MRI / diffusion (modality), human (organism), Alzheimer's / dementia (population)
Methods: Connectivity, Statistics, Machine learning, fMRI & imaging
Keywords: applied sciences, biological sciences, cognitive neuroscience, computer science, health sciences, medical imaging, medical tests, medicine, natural sciences, network, neuroscience
Topic: Radiomics and Machine Learning in Medical Imaging (Radiology, Nuclear Medicine and Imaging, Medicine), according to OpenAlex
Funding: Tianjin Municipal Science and Technology Program (25ZXWZSY00070)
Citations: not cited yet (Europe PMC); 37 references in the paper

Abstract

Mild cognitive impairment (MCI) is a clinically heterogeneous prodromal stage of Alzheimer’s disease (AD) in which accurate risk stratification could support earlier intervention and more efficient trial design. Using baseline T1-weighted MRI from the Alzheimer’s Disease Neuroimaging Initiative and the National Alzheimer’s Coordinating Center cohorts, we developed a dual-space anatomical radiomic-network signature that integrates regional radiomic features and radiomics similarity network metrics extracted in standard and native spaces. The signature improved prediction of MCI-to-AD conversion relative to regional volumetric and clinical models, achieved consistent external validation performance, and separated participants into high- and low-risk groups. The same feature set identified five imaging-defined MCI subtypes with distinct anatomical patterns, conversion risks, and clinical, APOE ε4, and cerebrospinal fluid biomarker profiles; fronto-parietal and parahippocampal-temporal subtypes showed the highest risk. These findings support structural MRI radiomic-network profiling as a complementary framework for individualized prognosis and cohort stratification in AD research.

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.

bearsyep/iscience_R2SN_radiomics

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: be306cf3c3599795f0a9a34a28e695184b86f4a0, 27 March 2026
Languages: Python (1)
Size: 1 file, 1 script
Software Heritage: not archived
Found in: “Data and code availability”
Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: NumPy (1 file), pandas (1 file), PyRadiomics (1 file), SimpleITK (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
1 file

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;
  • 1 script, 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 and code availability

This paper analyzes baseline T1-weighted structural MRI, demographic, clinical, genetic, cognitive, and biomarker data obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the National Alzheimer’s Coordinating Center (NACC). ADNI and NACC data are available to qualified researchers upon application to the respective data repositories and are subject to their data-use agreements and governance requirements. The analysis code used in this study is publicly available at https://github.com/bearsyep/iscience_R2SN_radiomics. Additional information required to reanalyze the data reported in this paper is available from the lead contact upon reasonable request, subject to the restrictions of the source cohorts.

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, 5 authors, 11 keywords, 1 funder, 37 references.

Cite

This paper

Xiong, D., Liu, M., Xie, J., Liu, Z., & Wang, J. (2026). A dual space MRI radiomic network signature for risk stratification and subtyping of mild cognitive impairment. iScience, 29(7), 116394. https://doi.org/10.1016/j.isci.2026.116394

BibTeX

@article{xiong2026dual,
author = {Xiong, Diaohan and Liu, Mengjiao and Xie, Jiamei and Liu, Zefeng and Wang, Junping},
title = {{A dual space MRI radiomic network signature for risk stratification and subtyping of mild cognitive impairment}},
journal = {iScience},
year = {2026},
month = jun,
volume = {29},
number = {7},
pages = {116394},
publisher = {Elsevier},
issn = {2589-0042},
doi = {10.1016/j.isci.2026.116394},
url = {https://doi.org/10.1016/j.isci.2026.116394},
pmid = {42325556},
pmcid = {PMC13276304}
}

RIS

TY - JOUR
AU - Xiong, Diaohan
AU - Liu, Mengjiao
AU - Xie, Jiamei
AU - Liu, Zefeng
AU - Wang, Junping
TI - A dual space MRI radiomic network signature for risk stratification and subtyping of mild cognitive impairment
T2 - iScience
J2 - iScience
PY - 2026
DA - 2026/06/12
VL - 29
IS - 7
SP - 116394
SN - 2589-0042
PB - Elsevier
DO - 10.1016/j.isci.2026.116394
UR - https://doi.org/10.1016/j.isci.2026.116394
LA - en
ER -

CSL-JSON

{
"id": "10.1016/j.isci.2026.116394",
"type": "article-journal",
"title": "A dual space MRI radiomic network signature for risk stratification and subtyping of mild cognitive impairment",
"container-title": "iScience",
"author": [
{
"family": "Xiong",
"given": "Diaohan"
},
{
"family": "Liu",
"given": "Mengjiao"
},
{
"family": "Xie",
"given": "Jiamei"
},
{
"family": "Liu",
"given": "Zefeng"
},
{
"family": "Wang",
"given": "Junping"
}
],
"container-title-short": "iScience",
"volume": "29",
"issue": "7",
"page": "116394",
"DOI": "10.1016/j.isci.2026.116394",
"PMID": "42325556",
"PMCID": "PMC13276304",
"ISSN": "2589-0042",
"publisher": "Elsevier",
"URL": "https://doi.org/10.1016/j.isci.2026.116394",
"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:10.1002/advs.202309889 [code]
Polygenic Score for Conscientiousness Is a Protective Factor for Reversion from Mild Cognitive Impairment to Normal Cognition.
Journal: Advanced science (Weinheim, Baden-Wurttemberg, Germany)
In common: NumPy, Alzheimer's / dementia, 1 reference, author Junping Wang
[2] 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. Clinical
In common: PyRadiomics, SimpleITK, pandas, 1 other tool, Alzheimer's / dementia, structural MRI / diffusion, 1 reference
[3] doi:10.1038/s41467-023-44591-3 [code]
Radiomic tractometry reveals tract-specific imaging biomarkers in white matter.
Journal: Nature communications
In common: PyRadiomics, SimpleITK, pandas, 1 other tool, structural MRI / diffusion, 1 reference
[4] doi:10.1126/sciadv.ado8837 [code]
Macroscale connectome topographical structure reveals the biomechanisms of brain dysfunction in Alzheimer's disease.
Journal: Science advances
In common: PyRadiomics, SimpleITK, pandas, 1 other tool, Alzheimer's / dementia, structural MRI / diffusion, 1 reference
[5] doi:10.3389/fneur.2024.1474461 [code]
Utilizing machine-learning techniques on MRI radiomics to identify primary tumors in brain metastases.
Journal: Frontiers in neurology
In common: PyRadiomics, SimpleITK, pandas, 1 other tool, structural MRI / diffusion, 1 reference
[6] doi:10.1371/journal.pbio.3002710 [code]
The multiscale brain structural re-organization that occurs from childhood to adolescence correlates with cortical morphology maturation and functional specialization.
Journal: PLoS biology
In common: PyRadiomics, SimpleITK, pandas, 1 other tool, structural MRI / diffusion, 1 reference
[7] doi:10.1371/journal.pone.0285683 [code]
Segmenting white matter hyperintensities on isotropic three-dimensional Fluid Attenuated Inversion Recovery magnetic resonance images: Assessing deep learning tools on a Norwegian imaging database.
Journal: PloS one
In common: PyRadiomics, SimpleITK, pandas, 1 other tool, Alzheimer's / dementia, structural MRI / diffusion
[8] doi:10.1038/s41398-024-02939-3 [code]
Bidirectional two-sample Mendelian randomization analyses support causal relationships between structural and diffusion imaging-derived phenotypes and the risk of major neurodegenerative diseases.
Journal: Translational psychiatry
In common: Alzheimer's / dementia, structural MRI / diffusion, author Junping Wang
[9] doi:10.1002/alz.70544 [code]
Change points for dynamic biomarkers in the Alzheimer's disease pathological cascade: A 30-year cohort study.
Journal: Alzheimer's & dementia : the journal of the Alzheimer's Association
In common: SimpleITK, pandas, NumPy, Alzheimer's / dementia, structural MRI / diffusion, 2 references
[10] doi:10.3389/fnagi.2024.1434589 [code]
Machine learning models for diagnosing Alzheimer's disease using brain cortical complexity.
Journal: Frontiers in aging neuroscience
In common: PyRadiomics, SimpleITK, pandas, 1 other tool, Alzheimer's / dementia

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/10.1016/j.isci.2026.116394.svg)](https://openscicode.org/badge/doi/10.1016/j.isci.2026.116394)
<!-- oscr-badge:end -->
reStructuredText
.. oscr-badge:start

.. image:: https://openscicode.org/badge/doi/10.1016/j.isci.2026.116394.svg
   :target: https://openscicode.org/badge/doi/10.1016/j.isci.2026.116394
   :alt: OSCR

.. oscr-badge:end
HTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1016/j.isci.2026.116394"><img src="https://openscicode.org/badge/doi/10.1016/j.isci.2026.116394.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.