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

Shared and disease-specific human brain vascular signatures in Alzheimer's disease, frontotemporal dementia, and Huntington's disease.

bioRxiv : the preprint server for biology·2026
Same author

Developmental molecular signatures define de novo cortico-brainstem circuit for skilled forelimb movement.

Nature communications·2026
Same author

Disruption of the SYNGAP1 PDZ ligand motif accelerates differentiation of human iPSC-derived GABAergic neurons.

bioRxiv : the preprint server for biology·2026
Same author

The dynamics of coastal macroalgal assemblages after the Fundão dam disaster: challenges and lessons from impact assessment.

Environmental monitoring and assessment·2026
Same author

"Time Is Brain" - for Cell Therapies.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025
Same author

Advancing Evidence-Based Nursing: The Updated German Expert Standard on Continence Promotion.

Healthcare (Basel, Switzerland)·2025

Related Experiment Video

Updated: Aug 25, 2025

Gathering Self-Initiated Rat Behavioral Data to Characterize Post-Stroke Deficits
05:08

Gathering Self-Initiated Rat Behavioral Data to Characterize Post-Stroke Deficits

Published on: March 15, 2024

1.2K

Deep learning-based behavioral profiling of rodent stroke recovery.

Rebecca Z Weber1,2, Geertje Mulders3, Julia Kaiser4

  • 1Institute for Regenerative Medicine (IREM), University of Zurich, Campus Schlieren, Wagistrasse 12, 8952, Schlieren, Switzerland.

BMC Biology
|October 15, 2022
PubMed
Summary

Deep learning-based 3D gait analysis offers a reproducible and sensitive method for studying rodent behavior after stroke. This approach enhances the understanding of motor recovery and treatment efficacy in neurological injury research.

Keywords:
Automated behavior analysisBehavioral testsBrain injuryDeep learningDeepLabCutIschemic strokeLocomotor profileMousePhotothrombotic stroke

More Related Videos

A Preclinical Model to Assess Brain Recovery After Acute Stroke in Rats
10:15

A Preclinical Model to Assess Brain Recovery After Acute Stroke in Rats

Published on: November 6, 2019

8.4K
Compensatory Limb Use and Behavioral Assessment of Motor Skill Learning Following Sensorimotor Cortex Injury in a Mouse Model of Ischemic Stroke
08:01

Compensatory Limb Use and Behavioral Assessment of Motor Skill Learning Following Sensorimotor Cortex Injury in a Mouse Model of Ischemic Stroke

Published on: July 10, 2014

11.6K

Related Experiment Videos

Last Updated: Aug 25, 2025

Gathering Self-Initiated Rat Behavioral Data to Characterize Post-Stroke Deficits
05:08

Gathering Self-Initiated Rat Behavioral Data to Characterize Post-Stroke Deficits

Published on: March 15, 2024

1.2K
A Preclinical Model to Assess Brain Recovery After Acute Stroke in Rats
10:15

A Preclinical Model to Assess Brain Recovery After Acute Stroke in Rats

Published on: November 6, 2019

8.4K
Compensatory Limb Use and Behavioral Assessment of Motor Skill Learning Following Sensorimotor Cortex Injury in a Mouse Model of Ischemic Stroke
08:01

Compensatory Limb Use and Behavioral Assessment of Motor Skill Learning Following Sensorimotor Cortex Injury in a Mouse Model of Ischemic Stroke

Published on: July 10, 2014

11.6K

Area of Science:

  • Neuroscience
  • Behavioral Science
  • Biomedical Engineering

Background:

  • Stroke research frequently uses rodent models to evaluate disease mechanisms and therapeutic interventions.
  • Current behavioral tests for motor recovery in rodents often lack reproducibility and struggle to capture complex post-injury behaviors.

Purpose of the Study:

  • To develop and validate a high-precision 3D gait analysis system for rodents using deep learning.
  • To assess the sensitivity, accuracy, and efficiency of this new method compared to conventional behavioral tests.

Main Methods:

  • Utilized DeepLabCut (DLC), a deep learning software, for precise 3D tracking of 10 body parts in mice.
  • Performed comprehensive post-analysis of motion tracking data, generating over 100 locomotor parameters.
  • Refined the ladder rung test using DLC and benchmarked it against traditional neurological scoring, rotarod, cylinder test, and single-pellet grasping tests.

Main Results:

  • Achieved high-precision 3D tracking of mouse locomotion across different strains.
  • Identified significant, biologically relevant differences in locomotor profiles post-stroke over three weeks.
  • Demonstrated superior sensitivity and accuracy of DLC-assisted gait analysis compared to conventional methods.

Conclusions:

  • Deep learning-based motion tracking provides accurate and sensitive data for characterizing complex rodent recovery after stroke.
  • The developed methodology can be applied to study other neurological injuries affecting locomotion.