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

Application of support vector machines for modeling dosimetric uncertainty in radiotherapy planning.

Radiological physics and technology·2026
Same author

Heart failure etiology and lipoprotein subfractions: Insight from the SMARTEX-HF study.

International journal of cardiology. Heart & vasculature·2026
Same author

GOUHFI 2.0: A Next-Generation Toolbox for Brain Segmentation and Cortex Parcellation at Ultra-High Field MRI.

ArXiv·2026
Same author

Prospective validation of an AI software for detecting clinically significant prostate cancer on biparametric MRI.

Insights into imaging·2026
Same author

Ready for Routine: Homogeneous, High-Resolution, and Multicontrast Whole-Brain MRI at 7 Tesla in Short Scan Time With "plug-and-Play" pTx Sequences.

Investigative radiology·2025
Same author

Brain Pulsation Imaging Using Non-Balanced Steady-State Free Precession With 3D-EPI Readout.

Magnetic resonance in medicine·2025

Related Experiment Video

Updated: Feb 20, 2026

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

23.3K

Support vector machine for breast cancer classification using diffusion-weighted MRI histogram features: Preliminary

Igor Vidić1, Liv Egnell1,2, Neil P Jerome2,3

  • 1Department of Physics, NTNU - Norwegian University of Science and Technology, Trondheim, Norway.

Journal of Magnetic Resonance Imaging : JMRI
|October 19, 2017
PubMed
Summary

Support vector machine (SVM) analysis of diffusion-weighted MRI (DWI) histogram properties accurately differentiates benign from malignant breast tumors. Machine learning models using combined diffusion features show promise for breast cancer subtyping.

Keywords:
breast MRdiffusion weighted MRIintravoxel incoherent motionprognostic factorssupport vector machinetumor heterogeneity

More Related Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.7K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.6K

Related Experiment Videos

Last Updated: Feb 20, 2026

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

23.3K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.7K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.6K

Area of Science:

  • Radiology and Medical Imaging
  • Oncology
  • Machine Learning in Medicine

Background:

  • Diffusion-weighted MRI (DWI) is a rapidly advancing MRI technique in oncology.
  • Histogram properties derived from DWI model fitting offer valuable features for lesion differentiation.
  • Machine learning can potentially enhance the classification accuracy of DWI-derived features.

Purpose of the Study:

  • To evaluate the efficacy of support vector machine (SVM) for classifying malignant and benign breast tumors.
  • To assess SVM's capability in differentiating breast cancer subtypes.

Main Methods:

  • Prospective study involving 51 patients with breast tumors (23 benign, 28 malignant).
  • DW-MRI (3T) imaging was performed, followed by calculation of apparent diffusion coefficient (ADC), relative enhanced diffusivity (RED), and intravoxel incoherent motion (IVIM) parameters.
  • Histogram properties (median, mean, standard deviation, skewness, kurtosis) were extracted and used as features in a 10-fold cross-validation SVM model.

Main Results:

  • Univariate analysis identified 11 significant histogram properties for differentiating benign from malignant tumors.
  • SVM achieved high accuracy (0.96) using a single feature (mean RED) or combinations of IVIM/ADC features.
  • Perfect classification was obtained by combining features from all diffusion models.
  • While no single feature predicted HER2 status in ER+ tumors, SVM combining several features (including higher-order statistics) achieved 0.90 accuracy, highlighting the importance of heterogeneity analysis.

Conclusions:

  • SVM analysis utilizing combined diffusion model features significantly improves the prediction accuracy for differentiating benign from malignant breast tumors.
  • This approach may also aid in the subtyping of breast cancer, particularly when accounting for tumor heterogeneity through higher-order statistics.