Automated home-cage behavioural phenotyping of mice
Creators
-
1.
Massachusetts Institute of Technology
-
2.
California Institute of Technology
-
3.
Brown University
Abstract
Neurobehavioural analysis of mouse phenotypes requires the monitoring of mouse behaviour over long periods of time. In this study, we describe a trainable computer vision system enabling the automated analysis of complex mouse behaviours. We provide software and an extensive manually annotated video database used for training and testing the system. Our system performs on par with human scoring, as measured from ground-truth manual annotations of thousands of clips of freely behaving mice. As a validation of the system, we characterized the home-cage behaviours of two standard inbred and two non-standard mouse strains. From these data, we were able to predict in a blind test the strain identity of individual animals with high accuracy. Our video-based software will complement existing sensor-based automated approaches and enable an adaptable, comprehensive, high-throughput, fine-grained, automated analysis of mouse behaviour.
Additional Information
© 2010 Macmillan Publishers Limited. Received 24 May 2010; Accepted 6 Aug 2010; Published 7 Sep 2010. This project was sponsored by the McGovern Institute for Brain Research. A.D.S., L.Y. and V.K. were funded by the Broad Fellows Program in Brain Circuitry at Caltech. H.J. was founded by the Taiwan National Science Council (TMS-094-1-A032). We thank Jessi Ambrose, Andrea Farbe, Cynthia Hsu, Alexandra Jiang, Grant Kadokura, Xuying Li, Anjali Patel, Kelsey von Tish, Emma Tolley, Ye Yao and Eli T Williams for their efforts in annotating the videos for this project. We are grateful to Susan Lindquist for allowing us to use her facilities and mice to generate much of the training video database and to Walker Jackson for assistance with operating Home Cage Scan. We thank Piotr Dollar for providing source code. The algorithm and software development and its evaluation were conducted at the Center for Biological and Computational Learning, which is in the McGovern Institute for Brain Research at MIT, as well as in the Department of Brain and Cognitive Sciences, and which is affiliated with the Computer Sciences and Artificial Intelligence Laboratory. Author contributions: H.J., T.P., A.D.S. and T.S. designed the research; H.J., E.G., A.D.S. and T.S. conducted the research; H.J., E.G., X.Y., V.K., A.D.S. and T.S analysed data; H.J., T.P., A.D.S. and T.S. wrote the paper.Attached Files
Supplemental Material - ncomms1064-s1.mpg
Supplemental Material - ncomms1064-s2.mpg
Supplemental Material - ncomms1064-s3.mpg
Supplemental Material - ncomms1064-s4.pdf
Supplemental Material - ncomms1064-s5.zip
Files
ncomms1064-s4.pdf
Files
(23.5 MB)
Additional details
Identifiers
- Eprint ID
- 21364
- DOI
- 10.1038/ncomms1064
- Resolver ID
- CaltechAUTHORS:20101214-140307155
Related works
- Describes
- 10.1038/ncomms1064 (DOI)
Funding
- McGovern Institute for Brain Research
- Caltech Brain Circuitry
- National Science Council (Taipei)
- TMS-094-1-A032
Dates
- Created
-
2010-12-14Created from EPrint's datestamp field
- Updated
-
2021-11-09Created from EPrint's last_modified field