High-resolution 3D tracking of social behaviors for deep phenotypic analysis

NIH RePORTER · NIH · R34 · $378,727 · view on reporter.nih.gov ↗

Abstract

Project Summary The aim of this proposal is to plan for and deliver a proof-of-concept solution for an innovative and easy-to-use experimental platform for measuring and quantifying social behaviors in animal models. Efforts during this initial grant period will be restricted to rats and mice, experimental animals with rich social behaviors, but we hope in future iterations of this program to expand also to other model organisms, including birds and monkeys. To capture kinematic details of whole- body movement during social behaviors requires novel solutions for dealing with the inevitable occlusions that results from social interactions. To overcome the limitations of current approaches we will build and validate a novel deep neural network that learns to combine images across multiple synchronized cameras and infer the 3D physical coordinates of multiple animals. Preliminary studies have been very positive and suggest large improvements over current methods both when it comes to the range of social behaviors that can be tracked and the precision with which they can be measured. Importantly, all new technology will be readily shared with the scientific community, thereby leveraging from this single grant the potential for numerous investigators to dramatically improve the efficiency of their research programs requiring rigorous quantitative descriptions of animal behavior.

Key facts

NIH application ID
10786685
Project number
1R34DA059506-01
Recipient
DUKE UNIVERSITY
Principal Investigator
Timothy William Dunn
Activity code
R34
Funding institute
NIH
Fiscal year
2024
Award amount
$378,727
Award type
1
Project period
2024-09-15 → 2026-08-31