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

Mendelian Randomization and Transcriptome Analysis Identify Ischemic Stroke Biomarkers With Putative Relevance to Cerebrospinal Fluid.

BioMed research international·2026
Same author

TRPML1 positions lysosomes and regulates actin-membrane linkers in astrocyte processes.

bioRxiv : the preprint server for biology·2026
Same author

Dexterous single sniffs for ethological active olfaction.

Science advances·2026
Same author

Distinct involvements of the subthalamic nucleus subpopulations in reward-biased decision-making in monkeys.

eLife·2026
Same author

Comparative Analysis of Meat Quality and Muscle Transcriptome between Landrace and Jeju Native Pig.

Food science of animal resources·2026
Same author

An olfactory-prefrontal cortical circuit supports social recognition.

Research square·2026

Related Experiment Video

Updated: Aug 18, 2025

Cheek Injection Model for Simultaneous Measurement of Pain and Itch-related Behaviors
04:59

Cheek Injection Model for Simultaneous Measurement of Pain and Itch-related Behaviors

Published on: September 27, 2019

12.3K

Scratch-AID, a deep learning-based system for automatic detection of mouse scratching behavior with high accuracy.

Huasheng Yu1, Jingwei Xiong2, Adam Yongxin Ye3

  • 1Department of Neuroscience, Perelman School of Medicine, University of Pennsylvania, Philadelphia, United States.

Elife
|December 8, 2022
PubMed
Summary

Researchers developed Scratch-AID, an automated system for quantifying mouse scratching behavior. This deep learning tool enhances itch research and drug screening by providing accurate, high-throughput analysis, replacing manual methods.

Keywords:
automatic quantificationdeep learningitchmousemouse behaviorneurosciencescratching

More Related Videos

A System for Tracking the Dynamics of Social Preference Behavior in Small Rodents
08:38

A System for Tracking the Dynamics of Social Preference Behavior in Small Rodents

Published on: November 21, 2019

7.7K
A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents
06:25

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

Published on: May 16, 2025

379

Related Experiment Videos

Last Updated: Aug 18, 2025

Cheek Injection Model for Simultaneous Measurement of Pain and Itch-related Behaviors
04:59

Cheek Injection Model for Simultaneous Measurement of Pain and Itch-related Behaviors

Published on: September 27, 2019

12.3K
A System for Tracking the Dynamics of Social Preference Behavior in Small Rodents
08:38

A System for Tracking the Dynamics of Social Preference Behavior in Small Rodents

Published on: November 21, 2019

7.7K
A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents
06:25

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

Published on: May 16, 2025

379

Area of Science:

  • Neuroscience
  • Pharmacology
  • Bioengineering

Background:

  • Mice are crucial models for itch research and anti-itch drug development.
  • Manual quantification of mouse scratching behavior is labor-intensive and limits large-scale studies.
  • There is a need for automated, accurate methods to assess itch intensity in mice.

Purpose of the Study:

  • To develop and validate an automated system, Scratch-AID, for quantifying mouse scratching behavior.
  • To assess the accuracy and generalizability of Scratch-AID across different itch models.
  • To demonstrate the utility of Scratch-AID in drug screening.

Main Methods:

  • Developed Scratch-AID, incorporating a custom videotaping box and a convolutional recurrent neural network.
  • Trained the neural network using frame-labeled mouse scratching behavior videos induced by chloroquine.
  • Validated Scratch-AID on independent test videos and across various mouse itch models.

Main Results:

  • The best-trained Scratch-AID network achieved high accuracy (97.6% recall, 96.9% precision).
  • Scratch-AID reliably identified scratching behavior in acute, histaminergic, and chronic itch models.
  • The system detected significant differences in scratching between control and drug-treated mice.

Conclusions:

  • Scratch-AID is a novel, deep learning-based system for automated mouse scratching quantification.
  • This system can replace manual methods, enabling efficient large-scale genetic and drug screenings.
  • Scratch-AID offers a reliable tool for diverse itch research applications.