RT Journal Article
SR Electronic
T1 Deep learning based behavioral analysis enables high precision rodent tracking and is capable of outperforming commercial solutions
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2020.01.21.913624
DO 10.1101/2020.01.21.913624
A1 Oliver Sturman
A1 Lukas von Ziegler
A1 Christa Schläppi
A1 Furkan Akyol
A1 Benjamin Grewe
A1 Johannes Bohacek
YR 2020
UL http://biorxiv.org/content/early/2020/01/21/2020.01.21.913624.abstract
AB To study brain function, preclinical research relies heavily on animal monitoring and the subsequent analyses of behavior. Commercial platforms have enabled semi high-throughput behavioral analyses by providing accurate tracking of animals, yet they often struggle with the analysis of ethologically relevant behaviors and lack the flexibility to adapt to variable testing environments. In the last couple of years, substantial advances in deep learning and machine vision have given researchers the ability to take behavioral analysis entirely into their own hands. Here, we directly compare the performance of commercially available platforms (Ethovision XT14, Noldus; TSE Multi Conditioning System, TSE Systems) to cross-verified human annotation. To this end, we provide a set of videos - carefully annotated by several human raters - of three widely used behavioral tests (open field, elevated plus maze, forced swim test). Using these data, we show that by combining deep learning-based motion tracking (DeepLabCut) with simple post-analysis, we can track animals in a range of classic behavioral tests at similar or even greater accuracy than commercial behavioral solutions. In addition, we integrate the tracking data from DeepLabCut with post analysis supervised machine learning approaches. This combination allows us to score ethologically relevant behaviors with similar accuracy to humans, the current gold standard, thus outperforming commercial solutions. Moreover, the resulting machine learning approach eliminates variation both within and between human annotators. In summary, our approach helps to improve the quality and accuracy of behavioral data, outperforming commercial systems at a fraction of the cost.