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

Revisiting the Lipid-Cancer Axis: PCSK9, ANGPTL3, and CETP as Emerging Biomarkers and Therapeutic Targets in Oncology.

Biomolecules·2026
Same author

Influence of the Adsorption Time on the Growth of Bovine Serum Albumin-Chondroitin Sulfate Multilayer Films: A Surface Plasmon Resonance Spectroscopy Study.

Biopolymers·2026
Same author

Metabolomics in Motion: Translating Molecular Signatures into Clinical Impact.

Metabolites·2026
Same author

Effective waste management towards promoting circular economy.

Environmental science and pollution research international·2026
Same author

Cardioprotective therapies for ST-elevation myocardial infarction: the emerging role of thyroid hormone: a narrative review.

Frontiers in endocrinology·2025
Same author

Efficient and Scalable Point Cloud Generation With Sparse Point-Voxel Diffusion Models.

IEEE transactions on neural networks and learning systems·2025

Related Experiment Video

Updated: Oct 2, 2025

A Versatile Murine Model of Subcortical White Matter Stroke for the Study of Axonal Degeneration and White Matter Neurobiology
08:36

A Versatile Murine Model of Subcortical White Matter Stroke for the Study of Axonal Degeneration and White Matter Neurobiology

Published on: March 17, 2016

8.2K

Machine learning based analysis of stroke lesions on mouse tissue sections.

Gerasimos Damigos1,2, Evangelia I Zacharaki2, Nefeli Zerva1

  • 1Department of Pharmacology, Medical School of Athens, National and Kapodistrian University of Athens, Athens, Greece.

Journal of Cerebral Blood Flow and Metabolism : Official Journal of the International Society of Cerebral Blood Flow and Metabolism
|February 25, 2022
PubMed
Summary

A new automated method, StrokeAnalyst, accurately analyzes brain lesions after ischemic stroke in mice. This machine learning tool improves reliability and reduces errors compared to manual or semi-automated techniques.

Keywords:
Mouse strokeTTC brain atlasautomated infarct volumetrylesion analysismachine learningneuroanatomical mapping

More Related Videos

Modeling Stroke in Mice: Focal Cortical Lesions by Photothrombosis
06:07

Modeling Stroke in Mice: Focal Cortical Lesions by Photothrombosis

Published on: May 6, 2021

6.8K
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

2.5K

Related Experiment Videos

Last Updated: Oct 2, 2025

A Versatile Murine Model of Subcortical White Matter Stroke for the Study of Axonal Degeneration and White Matter Neurobiology
08:36

A Versatile Murine Model of Subcortical White Matter Stroke for the Study of Axonal Degeneration and White Matter Neurobiology

Published on: March 17, 2016

8.2K
Modeling Stroke in Mice: Focal Cortical Lesions by Photothrombosis
06:07

Modeling Stroke in Mice: Focal Cortical Lesions by Photothrombosis

Published on: May 6, 2021

6.8K
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

2.5K

Area of Science:

  • Neuroscience
  • Medical Imaging
  • Computational Biology

Background:

  • Manual and semi-automated methods for analyzing ischemic stroke brain lesions are laborious, prone to human error, and yield inaccurate results.
  • Existing threshold-based approaches often produce significant false-positive and false-negative data, compromising reliability.
  • There is a critical need for an unbiased, automated, and dependable method for stroke lesion analysis in preclinical research.

Purpose of the Study:

  • To develop and validate "StrokeAnalyst", a novel machine learning-based, atlas-guided method for fully automated analysis of brain lesions in mouse stroke models.
  • To provide a user-friendly, reliable, and reproducible tool for infarct volumetry and neuroanatomical characterization.
  • To overcome the limitations of existing manual and semi-automated methods in terms of accuracy, bias, and efficiency.

Main Methods:

  • Developed "StrokeAnalyst", a machine learning (Random-Forest) and atlas-based approach for analyzing 2% Triphenyltetrazolium-chloride (2% TTC) stained mouse brain slices.
  • Images are registered to a novel mouse TTC brain atlas, and pixel-based intensity statistics (z-scores) are calculated.
  • Outlier detection and machine learning models are employed to enhance lesion detection accuracy and provide detailed neuroanatomical information.

Main Results:

  • StrokeAnalyst demonstrated rater-independent and reproducible detection of stroke lesions in validation studies using the filament stroke model.
  • The method accurately determined hemispheric volumes, even in the presence of post-stroke edema.
  • Significantly minimized false-positive errors compared to threshold-based methods, with a false-positive rate of 1.2-2.3% (p < 0.05).

Conclusions:

  • StrokeAnalyst represents a significant advancement over previous TTC-volumetry techniques for preclinical stroke research.
  • The automated, machine learning-driven approach enhances the quality, reproducibility, and reliability of stroke lesion detection.
  • This tool can process various image types, including those from scanners, smartphones, and PDFs, increasing its accessibility and utility.