Document Type

Article

Publication Date

3-29-2019

Keywords

JMG

JAX Source

Commun Biol 2019 Mar 29; 2:124

Volume

2

First Page

124

Last Page

124

ISSN

2399-3642

PMID

30937403

DOI

https://doi.org/10.1038/s42003-019-0362-1

Grant

DA041668,OD023222,Brain and Behavioral Foundation Young Investigator Award,The Jackson Laboratory, Director’s Innovation Fund

Abstract

The ability to track animals accurately is critical for behavioral experiments. For video-based assays, this is often accomplished by manipulating environmental conditions to increase contrast between the animal and the background in order to achieve proper foreground/background detection (segmentation). Modifying environmental conditions for experimental scalability opposes ethological relevance. The biobehavioral research community needs methods to monitor behaviors over long periods of time, under dynamic environmental conditions, and in animals that are genetically and behaviorally heterogeneous. To address this need, we applied a state-of-the-art neural network-based tracker for single mice. We compare three different neural network architectures across visually diverse mice and different environmental conditions. We find that an encoder-decoder segmentation neural network achieves high accuracy and speed with minimal training data. Furthermore, we provide a labeling interface, labeled training data, tuned hyperparameters, and a pretrained network for the behavior and neuroscience communities.

Comments

We thank the members of the Kumar laboratory for suggestions and editing of the manuscript. We thank JAX Information Technology team members Edwardo Zaborowski, Shane Sanders, Rich Brey, David McKenzie, and Jason Macklin for infrastructure support, and we thank KOMP2 behavioral testers James Clark, Pamelia Fraungruber, Rose Presby, Zachery Seavey, and Catherine Witmeyer.

This open access article is licensed under a Creative Commons Attribution 4.0 International License

Download

Share

COinS