Application of a novel automated behaviour monitoring system for studying dietary-induced cognitive decline in mouse models

The typical Western diet, rich in saturated fat and refined sugar, has been shown to increase cognitive decline with aging and Alzheimer’s disease, and to affect cognitive functions that are dependent on the hippocampus, including memory processes and reversal learning. There is consensus among researchers that onset of diabetes/obesity/metabolic syndrome is a driver of neurodegeneration in the elderly. Behaviour analysis of laboratory animals is a useful tool to assess therapeutic efficacy.

The entire process consists of animal tracking and motion categorisation. Despite efforts made within the research community, there is no system which can perform automated recognition of complex animal behaviours and interactions. Within QUB we have developed a fully automated and trainable computer vision system to monitor and analyse complex mouse behaviours and interactions using video data recorded by calibrated cameras. Funded by the EPSRC this system is capable of conducting interaction analysis on multiple mice simultaneously. The system is currently being tested for monitoring movement disorders associated with Parkinson’s disease (see: http://gow.epsrc.ac.uk/NGBOViewGrant.aspx?GrantRef=EP/N011074/1).

Research aims
The overall objective is to adapt and extend the use of the developed system to analyse complex behaviours and interactions in well-established mouse models of diet-induced obesity (DIO). We will: 1. automatically identify home-cage microbehaviours (e.g. grooming, hanging, jumping etc.) within videos; 2. detect abnormal behaviours in DIO mice, develop specific algorithms to discriminate them and apply them to recognising behaviours; and 3. demonstrate specific drug and dietary strategies which restore normal abnormal behaviours.