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 Experiment Video

Updated: Jan 15, 2026

A Porcine Model of Acute Autologous Pulmonary Embolism
07:44

A Porcine Model of Acute Autologous Pulmonary Embolism

Published on: September 6, 2024

762

Comparing computer vision models for detecting chronic pleurisy in pigs.

Daniel Hjorth Lund1, Lis Alban2, Matt Denwood3

  • 1Section of Animal Welfare, Danish Technological Institute, Taastrup, Denmark.

Preventive Veterinary Medicine
|October 7, 2025
PubMed
Summary

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

A systems thinking approach to identify barriers and strategies to improve antimicrobial stewardship using a bottom-up approach among Danish pig veterinarians.

Preventive veterinary medicine·2026
Same author

Management practices and biosecurity in hobby and companion pig holdings: A cross-sectional study in Denmark.

Preventive veterinary medicine·2026
Same author

Analytical and clinical performance of in-house and commercial real-time PCR assays for diagnosing <i>L. infantum</i> visceral leishmaniasis: a study from a hub center in Northern Italy.

Journal of clinical microbiology·2026
Same author

A field observational study evaluating antemortem inspection as a predictive tool for postmortem lesion findings at a Portuguese pig abattoir.

Research in veterinary science·2026
Same author

Risk assessment for Brucella suis biovar 2 in Danish pigs.

Porcine health management·2025
Same author

Challenging the Distance-Morbidity Paradigm Following Liver Transplantation: A Single Center Experience.

The Journal of surgical research·2025

Computer vision systems (CVS) show high accuracy in detecting chronic pleurisy in pigs, outperforming traditional meat inspection in sensitivity. This technology offers precise, uniform registration for quality assurance in meat inspection frameworks.

Area of Science:

  • Veterinary diagnostics
  • Artificial intelligence in agriculture
  • Food safety technology

Background:

  • Chronic pleurisy negatively impacts pig productivity and is relevant for abattoir quality assurance.
  • Official registration of chronic pleurisy is no longer a priority for Danish authorities.
  • Accurate detection of chronic pleurisy is crucial for understanding its prevalence and economic impact.

Purpose of the Study:

  • To evaluate the diagnostic performance of three convolutional neural network (CNN) models in a computer vision system (CVS) for detecting chronic pleurisy in pig carcasses.
  • To compare the CVS diagnostic performance against official meat inspection methods.
  • To assess the potential of CVS technology for risk-based meat inspection.

Main Methods:

  • Analysis of data from 85,413 pig carcasses across 15 slaughter days.
Keywords:
Carcass evaluationLatent class modellingMachine visionMeat safety assurance

More Related Videos

Author Spotlight: Exploring Venous Waveforms for Non&#45;Invasive Respiratory Monitoring in Pigs
04:10

Author Spotlight: Exploring Venous Waveforms for Non-Invasive Respiratory Monitoring in Pigs

Published on: March 8, 2024

1.8K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.4K

Related Experiment Videos

Last Updated: Jan 15, 2026

A Porcine Model of Acute Autologous Pulmonary Embolism
07:44

A Porcine Model of Acute Autologous Pulmonary Embolism

Published on: September 6, 2024

762
Author Spotlight: Exploring Venous Waveforms for Non&#45;Invasive Respiratory Monitoring in Pigs
04:10

Author Spotlight: Exploring Venous Waveforms for Non-Invasive Respiratory Monitoring in Pigs

Published on: March 8, 2024

1.8K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.4K
  • Evaluation using traditional agreement statistics and Bayesian latent class modeling, independent of a gold standard.
  • Comparison of sensitivity and specificity between CVS models and human meat inspectors using Cohen's kappa and prevalence- and bias-adjusted kappa.

    • Main Results:

    • CVS models demonstrated moderate to near-perfect agreement with meat inspectors (kappa values 0.72-0.89).
    • CVS models exhibited superior sensitivity (84.7-90.3%) compared to meat inspectors (79.4-83.0%).
    • Meat inspectors maintained slightly higher specificity (99.7-99.9%) than CVS models (97.6-98.8%).
    • The ResNeXt-101 architecture (CVS-Complex-HighRes) performed best; consensus from multiple models improved specificity.
    • No significant associations were found between CVS detection and other meat inspection findings, except minor defects.

    Conclusions:

    • Computer vision systems offer precise and uniform detection of chronic pleurisy, complementing traditional meat inspection.
    • CVS technology shows promise for implementation in risk-based meat inspection frameworks.
    • Further work is needed to establish performance thresholds and address regulatory aspects for commercial adoption.