Artificial Intelligence Offers Opportunity to Improve Animal Welfare

Researchers are assessing the value of artificial intelligence to track and improve animal welfare.The Western College of Veterinary Medicine and the University of Saskatchewan's Department of Computer engineering, in partnership with 14 industry partners with support from the Natural Sciences and Engineering Research Council are developing new tools to document and analyze animal-based indicators of on farm welfare, such as skin or tail lesions detected on swine carcasses at slaughter.

Dr. Martyna Lagoda, a Post-doctoral Fellow Swine Behavior and Welfare with the Western College of Veterinary Medicine says a full working computer system is in place to detect and document lesions and the artificial intelligence system is being trained for the detection of specific lesions.

Quote-Dr. Martyna Lagoda-Western College of Veterinary Medicine:

We do have several milestones reached for the carcass automation portion of the project.For instance, the computer engineering team has a fully working computer model that can detect and track the same pig carcass and it can also identify the dorsal and the lateral sides as well as specific body regions of the pig.

For example, the tail, the shoulder or the ear, which are of important parts for animal welfare.The model is currently being trained for the detection of lesions on carcasses, both in terms of their quantity but also quality.

The advancements that we've made so far to successfully develop the computer vision to automate the detection and scanning of pig carcasses for welfare indictors is a very important step.Success in this area confirms that we can scale this technology up for commercial adoption because it supports objective and quantifiable data collection on animal welfare assessment.

This increases the relevance of the project to producers and also the swine industry at large by making it more applicable to them.

Dr. Lagoda says on farm data is currently being analyzed and results are expected by April, 2024.