OSCR

Evaluating the impact of segmentation strategies on radiomic feature stability for paediatric brain tumour diagnosis using diffusion weighted imaging.

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.

The 1 match
  1. [1] § 2 Materials and methods › 2.1 Data › 2.1.5 Feature extraction. ↔ FeatureExtraction.py, lines 60–139 · score 0.72 · bin width, PyRadiomics, resampling, ROIs, ADC, eroded

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

Python · 144 lines · 5.4 KB · no license · 1 match

  1. # -*- coding: utf-8 -*-
  2. """
  3. @author: mulvanyt
  4. """
  6. import os
  7. import numpy as np
  8. import pandas as pd
  9. import nibabel as nib
  10. import cv2
  11. from radiomics import featureextractor
  13. def calculate_adc(b0_path, b1000_path, out_adc_path):
  14. """Calculates the ADC map from b0 and b1000 images using nibabel."""
  15. b0_img = nib.load(b0_path)
  16. b1000_img = nib.load(b1000_path)
  18. # Get image arrays and converts to float
  19. b0_arr = b0_img.get_fdata().astype(np.float32)
  20. b1000_arr = b1000_img.get_fdata().astype(np.float32)
  22. # Calculate ADC and truncate
  23. adc_arr = -(np.log(b1000_arr / b0_arr)) / 1000.0
  24. adc_arr = np.clip(adc_arr, a_min=0, a_max=0.004)
  26. # Create new Nifti image using the affine and header from b0
  27. adc_img = nib.Nifti1Image(adc_arr, b0_img.affine, b0_img.header)
  28. nib.save(adc_img, out_adc_path)
  30. return out_adc_path
  32. def apply_morphology(roi_path, iterations, operation, out_path):
  33. """Applies in-plane 3x3 erosion/dilation directly to input image (paths)"""
  34. roi_img = nib.load(roi_path)
  35. roi_arr = np.round(roi_img.get_fdata(), decimals=0).astype(np.uint8)
  37. kernel = np.ones((3, 3), np.uint8)
  39. if operation == 'erode':
  40. new_roi_arr = cv2.erode(roi_arr, kernel, iterations=iterations)
  41. elif operation == 'dilate':
  42. new_roi_arr = cv2.dilate(roi_arr, kernel, iterations=iterations)
  44. if out_path is None:
  45. return new_roi_arr
  46. else:
  47. new_roi_img = nib.Nifti1Image(new_roi_arr, roi_img.affine, roi_img.header)
  48. nib.save(new_roi_img, out_path)
  49. return out_path
  51. def extract_features(extractor, image_path, mask_path):
  52. """Extracts features from file paths and filters to 19 first-order features."""
  54. result = extractor.execute(image_path, mask_path)
  55. first_order = {k.replace('original_firstorder_', ''): v
  56. for k, v in result.items() if 'original_firstorder_' in k}
  57. first_order['StandardDeviation'] = first_order['Variance'] ** 0.5
  58. return first_order
  60. def main():
  62. data_dir = "./"
  63. patient_info_path = os.path.join(data_dir, "patient_info.csv")
  65. df_info = pd.read_csv(patient_info_path)
  66. patient_ids = df_info.iloc[:, 0].astype(str).tolist()
  68. # Configure PyRadiomics
  69. settings = {
  70. 'binWidth': 25e-6,
  71. 'interpolator': 'sitkBSpline',
  72. 'resampledPixelSpacing': [1, 1, 1]
  73. }
  74. extractor = featureextractor.RadiomicsFeatureExtractor(**settings)
  75. extractor.disableAllFeatures()
  76. extractor.enableFeatureClassByName('firstorder')
  78. results_original = []
  79. results_eroded = {1: [], 2: [], 3: []}
  80. results_dilated = {1: [], 2: [], 3: []}
  82. for pid in patient_ids:
  83. print(f"Processing Patient ID: {pid}")
  85. b0_path = os.path.join(data_dir, f"{pid}_b0.nii.gz")
  86. b1000_path = os.path.join(data_dir, f"{pid}_b1000.nii.gz")
  87. roi_path = os.path.join(data_dir, f"{pid}_roi.nii")
  88. adc_path = os.path.join(data_dir, f"{pid}_adc.nii.gz")
  90. #Generate and Save ADC
  91. adc_path = calculate_adc(b0_path, b1000_path, adc_path)
  93. #Original Features
  94. print(" Calculating original features...")
  95. feats_orig = extract_features(extractor, adc_path, roi_path)
  96. if feats_orig:
  97. feats_orig['Patient_ID'] = pid
  98. results_original.append(feats_orig)
  100. #Generate Eroded/Dilated ROIs and Calculate Features
  101. for iterations in [1, 2, 3]:
  102. # Erosion
  103. print(f" Calculating eroded features (iter={iterations})...")
  104. eroded_roi_path = os.path.join(data_dir, f"{pid}_roi_eroded_{iterations}.nii.gz")
  105. apply_morphology(roi_path, iterations, 'erode', eroded_roi_path)
  107. # Dilation
  108. print(f" Calculating dilated features (iter={iterations})...")
  109. dilated_roi_path = os.path.join(data_dir, f"{pid}_roi_dilated_{iterations}.nii.gz")
  110. apply_morphology(roi_path, iterations, 'dilate', dilated_roi_path)
  113. #Eroded Feature Calculation
  114. feats_erode = extract_features(extractor, adc_path, eroded_roi_path)
  115. if feats_erode:
  116. feats_erode['Patient_ID'] = pid
  117. results_eroded[iterations].append(feats_erode)
  119. #Dilated Feature Calculation
  120. feats_dilate = extract_features(extractor, adc_path, dilated_roi_path)
  121. if feats_dilate:
  122. feats_dilate['Patient_ID'] = pid
  123. results_dilated[iterations].append(feats_dilate)
  125. # Save DataFrames with Patient_ID as the first column
  126. def save_df(result_list, filename):
  127. if not result_list:
  128. return
  129. df = pd.DataFrame(result_list)
  130. cols = ['Patient_ID'] + [c for c in df.columns if c != 'Patient_ID']
  131. df = df[cols]
  132. df.to_csv(filename, index=False)
  133. print(f"Saved: {filename}")
  135. # Save all outputs
  136. save_df(results_original, os.path.join(data_dir, "original_data.csv"))
  137. for i in [1, 2, 3]:
  138. save_df(results_eroded[i], os.path.join(data_dir, f"eroded_{i}_features.csv"))
  139. save_df(results_dilated[i], os.path.join(data_dir, f"dilated_{i}_features.csv"))
  141. if __name__ == "__main__":
  142. main()

FeatureExtraction.py at commit 94ab7c2, no license · at the source

Overview

Authors: Timothy Mulvany1, Daniel Griffiths-King1, Lara Worthington2, Katherine Crombie3, Heather E. L. Rose4,5, Andrew Peet2,3, John Apps2,3, Jan Novak1
ORCID iDs: Timothy Mulvany, Daniel Griffiths-King, Katherine Crombie, Heather E. L. Rose, Jan Novak
  1. Aston Institute of Health and Neurodevelopment, Aston University, Birmingham, United Kingdom
  2. Department of Oncology, Birmingham Women’s and Children’s Hospital NHS Foundation Trust, Birmingham, United Kingdom
  3. Institute of Cancer & Genomics Science, University of Birmingham, Birmingham, United Kingdom
  4. Medical Physics Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom
  5. School of Medicine, University of Nottingham, Nottingham, United Kingdom
Institutions: Aston University (United Kingdom); Birmingham Women’s and Children’s NHS Foundation Trust (United Kingdom); University of Birmingham (United Kingdom); Nottingham University Hospitals NHS Trust (United Kingdom); University of Nottingham (United Kingdom)
Journal: PloS one, volume 21, issue 8, article e0356382
Dates: received 18 May 2026; accepted 3 August 2026; published online 18 August 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1371/journal.pone.0356382 · PMID 42611869 · PMCID PMC13484970 · OpenAlex W7203683879
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: structural MRI / diffusion (modality), human (organism), other condition (population), clinical / translational (subfield)
Methods: Connectivity, Statistics, Machine learning, fMRI & imaging
MeSH: Brain Neoplasms*, Diffusion Magnetic Resonance Imaging*, Adolescent, Child, Child, Preschool, Female, Humans, Image Processing, Computer-Assisted, Machine Learning, Male, Radiomics, Retrospective Studies (* major topic)
Journal subjects: Medicine and Health Sciences, Oncology, Cancers and Neoplasms, Diagnostic Medicine, Cancer Detection and Diagnosis, Pediatrics, Diagnostic Radiology, Magnetic Resonance Imaging, Research and Analysis Methods, Imaging Techniques, Radiology and Imaging, Engineering and Technology, Signal Processing, Image Processing, Biology and Life Sciences, Neuroscience, Brain Mapping, Brain Morphometry, Diffusion Weighted Imaging, Neuroimaging, Blastoma, Medulloblastoma
Topic: Glioma Diagnosis and Treatment (Genetics, Medicine), according to OpenAlex
Funding: National Institute for Health and Care Research
Citations: not cited yet (Europe PMC); 31 references in the paper

Abstract

Objectives: This research aims to comprehensively assess the impact of both conservatively and extensively delineated Regions of Interest (ROI) on subsequent quantitative in-vivo characterisation of paediatric brain tumours using diffusion-weighted MRI.

Methods: Utilising a retrospective cohort of 106 paediatric brain tumour patients, ground truth (GT) ROIs delineating tumour boundaries were eroded or dilated, simulating conservative and extensive ROI drawing strategies respectively. Stability was evaluated for 19 first-order radiomic features extracted from Apparent Diffusion Coefficient (ADC) maps within each ROI. Further, these features were used to train a series of machine learning models to evaluate the impact of ROI boundaries on downstream diagnostic classification.

Results: For 18/19 first-order features, ROI dilation introduced significantly (p < 0.01) greater feature variability than erosion, with large effect size (d > 0.8) for 11 features. This relationship was variable between diagnoses, and strongest amongst pilocytic astrocytomas. Diagnostic models trained using features from GT ROIs were negatively impacted with classification accuracy reduced by 3.8 ± 0.8% and 5.6 ± 0.9% for low-level erosion and dilation respectively. Inclusion of eroded/dilated ROI features into the training dataset combined with stable-feature selection partially mitigated the impact of erosion/dilation on model accuracy with 1.4 ± 0.7% and 2.9 ± 0.3% accuracy drop compared model accuracy on features extracted from GT ROIs.

Conclusion: The consistently reduced impact of conservative boundaries over extensive ones suggests that, in terms of segmentation strategies, exclusion of ambiguous boundary regions may be preferable over their inclusion. Additionally, diagnostic models exhibited improved robustness to variable ROI drawing strategies through training augmentation and selection of stable features.

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.

tmulvanyAC/ADC_Radiomic_Stability

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 94ab7c2d94f32e3376eed08da900b4aa92837c57, 20 July 2026
Languages: Python (2)
Size: 7 files, 2 scripts
Software Heritage: not archived
Found in: “Data Availability”
Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: NumPy (2 files), pandas (2 files), NiBabel (1 file), OpenCV (1 file), Pingouin (1 file), PyRadiomics (1 file), scikit-learn (1 file), SciPy (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
2 files
At the source: github.com/tmulvanyAC/ADC_Radiomic_Stability

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;
  • 2 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

Due to the sensitive nature of the data used in this study, which involves child patient data, the full raw datasets cannot be shared publicly. Access to the data is restricted in accordance with ethical guidelines and study protocol. Therefore, the data for this publication cannot be made available. For more information about data availability, contact Sara Burling at . Specific sections of code covering the image processing and machine learning/statistical analyses developed for the current study have been made available at https://github.com/tmulvanyAC/ADC_Radiomic_Stability. Additionally, this publicly accessible repository provides extensive result tables providing the raw values used to build figures and to calculate summative statistics such as averages/distributions used in this paper.

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 2, 28 September 2026

  • Funding: added National Institute for Health and Care Research

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 8 authors, 12 MeSH terms, 29 references.

Cite

This paper

Mulvany, T., Griffiths-King, D., Worthington, L., Crombie, K., Rose, H. E. L., Peet, A., Apps, J., & Novak, J. (2026). Evaluating the impact of segmentation strategies on radiomic feature stability for paediatric brain tumour diagnosis using diffusion weighted imaging. PloS one, 21(8), e0356382. https://doi.org/10.1371/journal.pone.0356382

BibTeX

@article{mulvany2026evaluating,
author = {Mulvany, Timothy and Griffiths-King, Daniel and Worthington, Lara and Crombie, Katherine and Rose, Heather E. L. and Peet, Andrew and Apps, John and Novak, Jan},
title = {{Evaluating the impact of segmentation strategies on radiomic feature stability for paediatric brain tumour diagnosis using diffusion weighted imaging}},
journal = {PloS one},
year = {2026},
month = aug,
volume = {21},
number = {8},
pages = {e0356382},
publisher = {PLOS},
issn = {1932-6203},
doi = {10.1371/journal.pone.0356382},
url = {https://doi.org/10.1371/journal.pone.0356382},
pmid = {42611869},
pmcid = {PMC13484970}
}

RIS

TY - JOUR
AU - Mulvany, Timothy
AU - Griffiths-King, Daniel
AU - Worthington, Lara
AU - Crombie, Katherine
AU - Rose, Heather E. L.
AU - Peet, Andrew
AU - Apps, John
AU - Novak, Jan
TI - Evaluating the impact of segmentation strategies on radiomic feature stability for paediatric brain tumour diagnosis using diffusion weighted imaging
T2 - PloS one
J2 - PLoS One
PY - 2026
DA - 2026/08/18
VL - 21
IS - 8
SP - e0356382
SN - 1932-6203
PB - PLOS
DO - 10.1371/journal.pone.0356382
UR - https://doi.org/10.1371/journal.pone.0356382
LA - en
ER -

CSL-JSON

{
"id": "10.1371/journal.pone.0356382",
"type": "article-journal",
"title": "Evaluating the impact of segmentation strategies on radiomic feature stability for paediatric brain tumour diagnosis using diffusion weighted imaging",
"container-title": "PloS one",
"author": [
{
"family": "Mulvany",
"given": "Timothy"
},
{
"family": "Griffiths-King",
"given": "Daniel"
},
{
"family": "Worthington",
"given": "Lara"
},
{
"family": "Crombie",
"given": "Katherine"
},
{
"family": "Rose",
"given": "Heather E. L."
},
{
"family": "Peet",
"given": "Andrew"
},
{
"family": "Apps",
"given": "John"
},
{
"family": "Novak",
"given": "Jan"
}
],
"container-title-short": "PLoS One",
"volume": "21",
"issue": "8",
"page": "e0356382",
"DOI": "10.1371/journal.pone.0356382",
"PMID": "42611869",
"PMCID": "PMC13484970",
"ISSN": "1932-6203",
"publisher": "PLOS",
"URL": "https://doi.org/10.1371/journal.pone.0356382",
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
18
]
]
}
}

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:10.1093/braincomms/fcag317 [code]
Deep learning segmentation of paediatric brain tumours using diffusion-weighted MRI: towards an early, &lt;i&gt;in vivo&lt;/i&gt; classification pipeline.
Journal: Brain communications
In common: NiBabel, pandas, NumPy, structural MRI / diffusion, other condition, 6 references, 3 authors
[2] doi:10.1038/s41598-026-56688-y [code]
On the value of radiomics in addition to clinical measures in emotional conflict fMRI for predicting sertraline response in major depressive disorder.
Journal: Scientific reports
In common: PyRadiomics, NiBabel, scikit-learn, 3 other tools, 3 references
[3] doi:10.1038/s41598-026-47942-4 [code]
CT-based radiomic markers to predict late-onset seizures after traumatic brain injury.
Journal: Scientific reports
In common: PyRadiomics, NiBabel, scikit-learn, 3 other tools, clinical / translational, other condition, 1 reference
[4] 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 Association
In common: Pingouin, OpenCV, NiBabel, 4 other tools, structural MRI / diffusion, other condition
[5] doi:10.3390/cancers18162636 [code]
Exploring the Impact of T2-Weighted MRI Fat Saturation on Radiomics Stability for Brain Radionecrosis Prediction After Skull-Base Proton Therapy: A Pilot Study.
Journal: Cancers
In common: PyRadiomics, scikit-learn, pandas, 2 other tools, structural MRI / diffusion, clinical / translational, 1 reference
[6] doi:10.1186/s13244-026-02296-3 [code]
A pre-trained foundation model framework for multiplanar MRI classification of extramural vascular invasion and mesorectal fascia invasion in rectal cancer.
Journal: Insights into imaging
In common: OpenCV, NiBabel, scikit-learn, 3 other tools, structural MRI / diffusion, other condition, 1 reference
[7] doi:10.1186/s13244-026-02365-7 [code]
Super-resolution MRI and 2.5D deep learning for intratumoral-peritumoral radiomics in preoperative prediction of rectal cancer perineural invasion.
Journal: Insights into imaging
In common: PyRadiomics, NiBabel, scikit-learn, 3 other tools, structural MRI / diffusion, other condition
[8] doi:10.21203/rs.3.rs-9914920/v1 [code]
Prediction of cognitive performance by demographics, sleep, and brain morphometry: machine learning findings from ENIGMA-Sleep Working Group
Journal: Research Square (preprint)
In common: Pingouin, NiBabel, scikit-learn, 3 other tools, structural MRI / diffusion, 1 reference
[9] doi:10.3389/fonc.2026.1816015 [code]
Modality-level attribution and redundancy-aware radiomics for MRI-based differentiation of melanoma and NSCLC brain metastases.
Journal: Frontiers in oncology
In common: PyRadiomics, NiBabel, scikit-learn, 3 other tools, structural MRI / diffusion, other condition
[10] doi:10.1038/s41593-026-02228-w [code]
Circuit response to neuromodulation characterized with simultaneous deep brain stimulation and precision neuroimaging in humans.
Journal: Nature neuroscience
In common: Pingouin, OpenCV, NiBabel, 4 other tools

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.