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: May 31, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Quantitative prediction of acute ischemic tissue fate using support vector machine.

Shiliang Huang1, Qiang Shen, Timothy Q Duong

  • 1Research Imaging Institute, University of Texas Health Science Center, San Antonio, TX 78229, USA.

Brain Research
|July 12, 2011
PubMed
Summary

Support vector machine (SVM) accurately predicts stroke infarcts using acute MRI data. This method aids clinical decisions by quantifying tissue fate in acute stroke patients.

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

Effects of Various Drying Parameters on the Volatile and Non-Volatile Compositions of 'Qiancha 1' White Tea.

Foods (Basel, Switzerland)·2025
Same author

CircATP2C1 Drives Prostate Cancer Progression Through miR-654-3p-Mediated SLC7A11 Upregulation and Ferroptosis Suppression.

Cancers·2025
Same author

A multiplex RPA-CRISPR/Cas12a platform for rapid and accurate toxinotyping of Clostridium perfringens.

Talanta·2025
Same author

Fixing Background Misclassification in Few-Shot Object Detection via Product of Experts.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Oxidized LDL-induced FOXS1 mediates cholesterol transport dysfunction and inflammasome activation to drive aortic valve calcification.

Cardiovascular research·2025
Same author

A novel mouse model for <i>LAMA2</i>-related muscular dystrophy with analysis of molecular pathogenesis and clinical phenotype.

eLife·2025

Area of Science:

  • Biomedical Engineering
  • Neuroscience
  • Medical Imaging

Background:

  • Accurate prediction of ischemic tissue fate is crucial for acute stroke treatment decisions.
  • Current methods may lack the quantitative precision needed for optimal clinical management.

Purpose of the Study:

  • To evaluate the efficacy of a novel Support Vector Machine (SVM) model for pixel-by-pixel infarct prediction.
  • To utilize acute cerebral blood flow (CBF) and apparent diffusion coefficient (ADC) MRI data for infarct prediction.

Main Methods:

  • Developed and tested an SVM prediction model on rat models of middle cerebral artery occlusion (MCAO) at 30-min, 60-min, and permanent occlusion.
  • Acquired CBF, ADC, and T2 MRI data during the acute phase (up to 3h) and at 24h.
  • Quantified prediction accuracy using Receiver Operating Characteristic (ROC) analysis.

Related Experiment Videos

Last Updated: May 31, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Main Results:

  • SVM models using ADC+CBF achieved high prediction accuracy (86-93% Area Under the Curve) across stroke groups.
  • Incorporating neighboring pixel information and spatial infarction incidence further improved accuracy (88-97% AUC).
  • SVM performance favorably compared to a previously published Artificial Neural Network (ANN) algorithm.

Conclusions:

  • SVM offers a robust and quantitative framework for predicting infarct extent in acute stroke.
  • This approach has the potential to significantly aid clinical decision-making in stroke treatment.
  • The model demonstrates high accuracy and comparability to existing advanced algorithms.