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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Radar-Based Fall Detection Using Micro-Doppler Signatures: A Comparative Analysis of YOLO Architectures.

Sensors (Basel, Switzerland)·2026
Same author

A New Breakpoint to Classify 3D Voxels in MRI: A Space Transform Strategy with 3t2FTS-v2 and Its Application for ResNet50-Based Categorization of Brain Tumors.

Bioengineering (Basel, Switzerland)·2023
Same author

Classification of Coronavirus (COVID-19) from X-ray and CT images using shrunken features.

International journal of imaging systems and technology·2020
See all related articles

Related Experiment Video

Updated: Sep 10, 2025

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.2K

An effective flowchart for multimodal brain tumor binary classification with ranked 3D texture features.

Mücahid Barstuğan1

  • 1Department of Electrical and Electronics Engineering, Faculty of Engineering and Natural Sciences, Konya Technical University, Konya, Turkey. mbarstugan@ktun.edu.tr.

Scientific Reports
|August 20, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a 3D feature extraction method for improved brain tumor classification. The novel approach enhances accuracy in differentiating high-grade and low-grade gliomas using machine learning.

Keywords:
3D feature extractionBinary classificationBrain tumorFeature ranking

More Related Videos

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.3K
A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.4K

Related Experiment Videos

Last Updated: Sep 10, 2025

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.2K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.3K
A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.4K

Area of Science:

  • Medical Imaging
  • Machine Learning
  • Computational Biology

Background:

  • Brain tumor classification is complex due to variations in shape, density, and size.
  • Classical 2D texture features offer limited accuracy for brain tumor analysis.
  • 3D magnetic resonance imaging (MRI) provides richer data for tumor characterization.

Purpose of the Study:

  • To develop and evaluate a novel 3D feature extraction and ranking framework for accurate brain tumor classification.
  • To compare the performance of various feature sets and ranking methods in differentiating high-grade and low-grade gliomas.
  • To assess the efficacy of machine learning classifiers, including Support Vector Machines (SVM), in brain tumor diagnosis.

Main Methods:

  • Utilized 3D MRI data from the BraTS 2017 dataset for high-grade and low-grade glioma classification.
  • Extracted 3D texture features from FLAIR, T1, T1-contrast enhanced (T1c), and T2 MRI phases using a 3D gray level co-occurrence matrix.
  • Applied feature ranking methods (Bhattacharyya, entropy, ROC, t-test, Wilcoxon) and classified features using gradient boosting, SVM, and random forest algorithms.
  • Evaluated performance using sensitivity, specificity, accuracy, precision, and F-score via cross-validation (2-fold, 5-fold, 10-fold).

Main Results:

  • The combination of all four MRI phases (FLAIR+T1+T1c+T2) with the entropy feature-ranking method and 2-fold cross-validation yielded the most effective classification scheme.
  • The proposed machine learning framework achieved high performance metrics: 100% sensitivity, 97.29% specificity, 99.30% accuracy, 99.07% precision, and 99.53% F-score for glioma classification using SVM.
  • The 3D feature extraction approach significantly outperformed traditional 2D methods.

Conclusions:

  • 3D feature extraction and ranking methods overcome the limitations of 2D texture analysis for brain tumor classification.
  • The developed machine learning-based framework offers a robust and highly accurate system for glioma grading.
  • This novel approach demonstrates competitive performance compared to existing state-of-the-art methods in brain tumor classification.