Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 15, 2025

Translational Orthotopic Models of Glioblastoma Multiforme
07:37

Translational Orthotopic Models of Glioblastoma Multiforme

Published on: February 17, 2023

2.7K

Reproducibility of Radiomic Features in Glial Brain Tumors.

Gleb Danilov1, Alexander Shevchenko2, Ramin Afandiev2

  • 1Laboratory of Biomedical Informatics and Artificial Intelligence, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.

Studies in Health Technology and Informatics
|August 23, 2024
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Hairline as a Neurosurgical Landmark.

Cureus·2026
Same author

New Player in the Field of Glioblastoma Therapy: EGFRvIII-Specific Gol1 Aptamer Shows a Great Therapeutic Potential.

Pharmaceutics·2026
Same author

Ancient host-associated microbes obtained from mammoth remains.

Cell·2025
Same author

A low-angle trans-magendie foraminal approach to the fourth ventricle and dorsal brainstem.

Neurosurgical review·2025
Same author

Augmented reality intraoperative tractography for diffuse glioma resection adjacent to the corticospinal tract: a case series with preliminary results.

Neurosurgical review·2025
Same author

Hospital Information Systems: From Trio to Quartet.

Studies in health technology and informatics·2025

This study shows that machine learning (ML) models for classifying glial tumors from MRI are reproducible when using consistent feature selection across different volumes of interest (VOIs). However, radiomic features themselves showed limited reproducibility.

Area of Science:

  • Radiology
  • Oncology
  • Data Science

Background:

  • Magnetic resonance imaging (MRI) is crucial for diagnosing brain tumors.
  • Radiomics and machine learning (ML) offer advanced tools for tumor classification.
  • Standardizing analysis is key for reliable results in neuro-oncology.

Purpose of the Study:

  • To assess the reproducibility of a radiomics and ML approach for classifying glial tumors.
  • To investigate the impact of changing the location of the volume of interest (VOI) on classification accuracy and feature reproducibility.
  • To evaluate the consistency of ML model performance and radiomic features across different VOIs.

Main Methods:

  • Classification of glial tumors into four histological types using MRI, standardized VOI, radiomics, and ML.
Keywords:
MRIartificial intelligencegliomamachine learningneurooncologyradiomics

More Related Videos

Quantitative Immunohistochemistry of the Cellular Microenvironment in Patient Glioblastoma Resections
05:45

Quantitative Immunohistochemistry of the Cellular Microenvironment in Patient Glioblastoma Resections

Published on: July 31, 2017

9.6K
Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
10:17

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

13.2K

Related Experiment Videos

Last Updated: Jun 15, 2025

Translational Orthotopic Models of Glioblastoma Multiforme
07:37

Translational Orthotopic Models of Glioblastoma Multiforme

Published on: February 17, 2023

2.7K
Quantitative Immunohistochemistry of the Cellular Microenvironment in Patient Glioblastoma Resections
05:45

Quantitative Immunohistochemistry of the Cellular Microenvironment in Patient Glioblastoma Resections

Published on: July 31, 2017

9.6K
Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
10:17

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

13.2K
  • Comparison of ML results and radiomic feature reproducibility when VOI locations were altered.
  • Analysis of a dataset of 85 glial tumor cases.

    • Main Results:

    • High reproducibility of ML classification results was achieved when the same feature selection methodology was applied across different VOIs.
    • Radiomic features and their associated sets demonstrated limited reproducibility across various VOIs.
    • The sample size of 85 cases was insufficient to ensure feature reproducibility with changing VOIs.

    Conclusions:

    • ML-based classification of glial tumors using MRI is feasible and reproducible under consistent feature selection, even with varied VOIs.
    • The inherent variability of radiomic features across different VOIs necessitates careful consideration in study design and interpretation.
    • Future research should focus on methods to improve radiomic feature stability for more robust glial tumor analysis.