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

Imaging the hallmarks of cancer.

Nature reviews. Cancer·2026
Same author

Cardiopulmonary transit time measured on dynamic rubidium cardiac PET/CT is a predictor for pulmonary hypertension.

EJNMMI research·2026
Same author

Estimation of Future Patient Populations Eligible for Radioligand Therapies in the EU and the UK: A Modelling Study.

The Lancet regional health. Europe·2026
Same author

Impact of DOI Capability on Detector Performance: A Comparative Study of DOI and Non-DOI Detectors for High-Resolution and Sensitivity Organ-Specific PET Inserts.

IEEE transactions on radiation and plasma medical sciences·2026
Same author

German Society of Nuclear Medicine procedure guideline for brain perfusion SPECT using 99mTc-labelled radiopharmaceuticals (09/2025).

Nuklearmedizin. Nuclear medicine·2026
Same author

The PET tracer [<sup>11</sup>C]MODAG-005 targets alpha-synuclein aggregates in the brain.

Science translational medicine·2026

Related Experiment Video

Updated: Nov 21, 2025

Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research
07:34

Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research

Published on: December 15, 2023

2.8K

Machine learning identifies stroke features between species.

Salvador Castaneda-Vega1,2, Prateek Katiyar1,3, Francesca Russo4

  • 1Werner Siemens Imaging Center, Department of Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tuebingen, Tuebingen, Germany.

Theranostics
|January 18, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a new AI framework for segmenting ischemic stroke lesions using MRI data. The model accurately predicts final stroke volume and lesion location, bridging preclinical and clinical research.

Keywords:
Ischemic strokeMachine learningStroke segmentation NeuroimagingTranslational medicine

More Related Videos

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

8.5K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.1K

Related Experiment Videos

Last Updated: Nov 21, 2025

Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research
07:34

Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research

Published on: December 15, 2023

2.8K
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

8.5K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.1K

Area of Science:

  • Biomedical Imaging
  • Neurology
  • Artificial Intelligence in Medicine

Background:

  • Accurate ischemic stroke (IS) lesion segmentation is crucial for diagnosis, severity assessment, and treatment evaluation in both clinical and preclinical settings.
  • Manual segmentation is time-consuming, subjective, and lacks histological validation, while automated methods often lack accuracy or interpretability.
  • Current automated approaches struggle with multi-center datasets and require extensive training data, limiting their widespread application.

Purpose of the Study:

  • To develop and validate an automated framework for accurate ischemic stroke lesion segmentation using MRI.
  • To assess the framework's ability to predict final stroke volume and lesion location from early MRI scans.
  • To evaluate the translatability of the segmentation model between preclinical (rat) and clinical (human) data.

Main Methods:

  • Developed a segmentation framework using a Gaussian mixture model and random forest classifier on apparent diffusion coefficient (ADC) and T2-weighted (T2W) MRI data from rats.
  • Validated the framework against manual delineations, thresholding methods, and histological data at 24 hours and 1 week post-stroke.
  • Tested the trained model on a human stroke dataset with similar onset timing.

Main Results:

  • The framework significantly outperformed traditional thresholding methods in rat models, achieving high accuracy in predicting final stroke region localization (Dice similarity coefficient of 0.86).
  • Predicted stroke volumes strongly correlated with histological outcomes (Pearson correlation = 0.88), demonstrating predictive capability.
  • The model successfully identified stroke lesions in human brains, outperforming thresholding approaches in stroke volume prediction.

Conclusions:

  • The developed AI framework provides accurate and predictive segmentation of ischemic stroke lesions from early MRI scans.
  • This approach demonstrates the first successful direct translation of stroke imaging features between species, enabling co-analysis of preclinical and clinical data.
  • The findings offer a novel method to enhance biological insights into human stroke and improve the design of preclinical models.