Deep learning from videography as a tool for measuring E. coli infection in poultry
Authors:
- Neil ScheidwasserNSNeil Scheidwasser
- Louise Ladefoged PoulsenLPLouise Ladefoged Poulsen
- Prince Ravi LeowPLPrince Ravi Leow
- Mark Poulsen KhuranaMKMark Poulsen Khurana
- Maider Iglesias-CarrascoMIMaider Iglesias-Carrasco
- Daniel Joseph LaydonDLDaniel Joseph Laydon
- Christl Ann DonnellyCDChristl Ann Donnelly
- Anders Miki BojesenAnders Miki Bojesen
- Samir BhattSBSamir Bhatt
- David Alejandro DuchêneDDDavid Alejandro Duchêne
Open Access
- 8 October 2025
- journal article
- Published by The Royal Society in Royal Society Open Science
- Vol. 12 (10)
Abstract
Poultry farming is threatened by regular outbreaks of Escherichia coli ( E. coli ) that lead to significant economic losses and public health risks. However, traditional surveillance methods often lack sensitivity and scalability. Early detection of infected poultry using minimally invasive procedures is thus essential for preventing epidemics. To that end, we leverage recent advancements in computer vision, employing deep learning-based tracking to detect behavioural changes associated with E. coli infection in a case–control trial comprising two groups of 20 broiler chickens: (i) a healthy control group and (ii) a group infected with a pathogenic E. coli field strain from the poultry industry. More specifically, kinematic features derived from deep learning-based tracking data revealed markedly reduced activity in the challenged group compared with the negative control. These findings were validated by lower mean optical flow in the infected flock, suggesting reduced movement and activity, and post-mortem physiological markers of inflammation that confirmed the severity of infection in the challenged group. Overall, this study demonstrates that deep learning-based tracking offers a promising solution for real-time monitoring and early infection detection in poultry farming, with the potential to help reduce economic losses and mitigate public health risks associated with infectious disease outbreaks in poultry.Keywords
All Related Versions
Funding Information
- Novo Nordisk Fonden
- Danmarks Grundforskningsfond
- Vaccine Impact Modelling Consortium
- Danish Poultry Levy Foundation
- National Institute for Health Research Health Protection Research Unit
- Medical Research Council
- Schmidt Family Foundation
- Innovationsfonden
This publication has 51 references indexed in Scilit:
- Spread of avian pathogenic Escherichia coli ST117 O78:H4 in Nordic broiler productionBMC Genomics, 2017
- Diversity of Escherichia coli strains involved in vertebral osteomyelitis and arthritis in broilers in BrazilBMC Veterinary Research, 2016
- Monitoring chicken flock behaviour provides early warning of infection by human pathogen CampylobacterProceedings Of The Royal Society B-Biological Sciences, 2016
- Deep learningNature, 2015
- Variations in virulence of avian pathogenic Escherichia coli demonstrated by the use of a new in vivo infection modelVeterinary Microbiology, 2014
- The contribution of systemicEscherichia coliinfection to the early mortalities of commercial broiler chickensAvian Pathology, 2013
- Prediction of welfare outcomes for broiler chickens using Bayesian regression on continuous optical flow dataJournal of The Royal Society Interface, 2012
- Influence of Escherichia coli Shiga Toxin on the Mammalian Central Nervous System2010
- Chicken welfare is influenced more by housing conditions than by stocking densityNature, 2004
- Prevalence of leg weakness in broiler chickens and its relationship with genotypeVeterinary Record, 1992