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

Human umbilical cord-derived mesenchymal stem cells ameliorate muscle dysfunction and metabolic dysregulation in the CuZnSOD null mouse model of sarcopenia.

Experimental gerontology·2026
Same author

Impact of Exposure Parameters on Deep Learning Models in Chest Radiography and Implications for Deployment.

Radiology. Artificial intelligence·2026
Same author

Discriminating HFrEF vs HFpEF from chest radiographs: Mitigating demographic performance gaps via augmentation and multimodal fusion.

PLOS digital health·2026
Same author

Impact frequency and interval modulate brain network outcomes in a rat model of repetitive mild traumatic brain injury.

Scientific reports·2026
Same author

<i>SHORTKIT-ML</i>: A UNIFIED MULTI-PERSPECTIVE FRAMEWORK FOR DETECTING SHORTCUT LEARNING IN MEDICAL IMAGING EMBEDDINGS.

medRxiv : the preprint server for health sciences·2026
Same author

3D-printed dictamni-calcium silicate scaffolds modulate the osteoimmune microenvironment and enhance macrophage-derived exosomal miR-21 signaling in vascularized bone regeneration.

Journal of nanobiotechnology·2026

Related Experiment Video

Updated: Dec 14, 2025

A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia
09:59

A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia

Published on: September 16, 2017

14.5K

Machine learning-based segmentation of ischemic penumbra by using diffusion tensor metrics in a rat model.

Duen-Pang Kuo1,2, Po-Chih Kuo3, Yung-Chieh Chen1

  • 1Department of Medical Imaging, Taipei Medical University Hospital, No.250, Wu-Hsing St, Taipei, 11031, Taiwan.

Journal of Biomedical Science
|July 16, 2020
PubMed
Summary

Machine learning accurately differentiates ischemic penumbra from infarct core using diffusion tensor imaging. This approach aids in rapid stroke assessment and treatment decisions.

Keywords:
Diffusion tensor imagingInfarct coreIschemic penumbraMachine learning

More Related Videos

Middle Cerebral Artery Occlusion Allowing Reperfusion via Common Carotid Artery Repair in Mice
06:59

Middle Cerebral Artery Occlusion Allowing Reperfusion via Common Carotid Artery Repair in Mice

Published on: January 23, 2019

18.3K
Focal Cerebral Ischemia Model by Endovascular Suture Occlusion of the Middle Cerebral Artery in the Rat
13:50

Focal Cerebral Ischemia Model by Endovascular Suture Occlusion of the Middle Cerebral Artery in the Rat

Published on: February 5, 2011

80.7K

Related Experiment Videos

Last Updated: Dec 14, 2025

A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia
09:59

A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia

Published on: September 16, 2017

14.5K
Middle Cerebral Artery Occlusion Allowing Reperfusion via Common Carotid Artery Repair in Mice
06:59

Middle Cerebral Artery Occlusion Allowing Reperfusion via Common Carotid Artery Repair in Mice

Published on: January 23, 2019

18.3K
Focal Cerebral Ischemia Model by Endovascular Suture Occlusion of the Middle Cerebral Artery in the Rat
13:50

Focal Cerebral Ischemia Model by Endovascular Suture Occlusion of the Middle Cerebral Artery in the Rat

Published on: February 5, 2011

80.7K

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Stroke Research

Background:

  • Intra-arterial thrombectomy shows promise in acute stroke treatment.
  • Rapid identification of salvageable brain tissue is crucial for stroke management.
  • Diffusion tensor imaging (DTI) metrics offer potential for tissue characterization.

Purpose of the Study:

  • To evaluate machine learning (ML) feasibility for differentiating ischemic penumbra (IP) from infarct core (IC) using DTI.
  • To develop and validate an ML-based classifier for stroke tissue characterization.

Main Methods:

  • Fourteen male rats underwent permanent middle cerebral artery occlusion (pMCAO).
  • DTI metrics were acquired using 7T MRI.
  • A 2-level ML classifier was trained using DTI metrics to categorize stroke hemispheres into IP, IC, and normal tissue (NT).
  • Classification performance was assessed via leave-one-out cross-validation.

Main Results:

  • The classifier accurately segmented infarct core (IC) and non-infarct core (non-IC) with high AUC and accuracy.
  • Non-IC tissue was further classified into IP and normal tissue (NT) with good performance.
  • Overall classification accuracy for the three tissue subtypes (IP, IC, NT) was 88.1% ± 6.7%.

Conclusions:

  • A single DTI sequence combined with ML algorithms can effectively differentiate between IC and IP.
  • This ML approach shows comparable results to conventional perfusion-diffusion mismatch methods.
  • The findings suggest a potential for rapid, non-invasive stroke tissue characterization.