Mice are routinely used as preclinical models to study the mechanisms of human diseases. In psychiatry, assessing the social behaviour of these animals under normal or pathological conditions is critical for understanding which neural systems are involved in disease. However, such behaviours are complex and challenging to investigate.
Researchers at the Institut Pasteur and the IBPS led by Philippe Faure, Thomas Bourgeron and Jean-Christophe Olivo-Marin have now developed a new method, which they have called Live Mouse Tracker (LMT), to automatically track and identify mice and characterize their behaviour. The model can track and label up to four mice in an enriched environment over long periods of time. This solution makes use of a random-forest machine learning process, RFID sensors and an infrared-depth RGB-D camera and extracts a list of behavioural traits of both individuals and the groups of mice, providing a phenotypic profile for each animal.
“We used the method to study the impact of Shank2 and Shank3 gene mutations – mutations that are associated with autism – on mouse behaviour,” explain the researchers.
The teams involved in this study are:
Read the research paper: Real-time analysis of the behaviour of groups of mice via a depth-sensing camera and machine learning, Fabrice de Chaumont et al., Nature Biomedical Engineering 10.1038/s41551-019-0396-1