Head and gaze tracking of unrestrained marmosets

New technologies for manipulating and recording the nervous system allow us to perform unprecedented experiments. However, the influence of our experimental manipulations on psychological processes must be inferred from their effects on behavior. Today, quantifying behavior has become the bottleneck for large-scale, high-throughput, experiments. The method presented here addresses this issue by using deep learning algorithms for video-based animal tracking. Here we describe a reliable automatic method for tracking head position and orientation from simple video recordings of the common marmoset (Callithrix jacchus). This method for measuring marmoset behavior allows for the estimation of gaze within foveal error, and can easily be adapted to a wide variety of similar tasks in biomedical research. In particular, the method has great potential for the simultaneous tracking of multiple marmosets to quantify social behaviors.

[1]  H. Okano,et al.  Common marmoset as a new model animal for neuroscience research and genome editing technology , 2014, Development, growth & differentiation.

[2]  Hans Knutsson,et al.  Signal processing for computer vision , 1994 .

[3]  Aaron S. Andalman,et al.  Structural and molecular interrogation of intact biological systems , 2013, Nature.

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  S. Tardif,et al.  The marmoset as a model of aging and age-related diseases. , 2011, ILAR journal.

[6]  P. Lusso,et al.  Recent developments in animal models for human herpesvirus 6A and 6B. , 2014, Current opinion in virology.

[7]  Pietro Perona,et al.  High-throughput Ethomics in Large Groups of Drosophila , 2009, Nature Methods.

[8]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[9]  Samuel G. Solomon,et al.  A simpler primate brain: the visual system of the marmoset monkey , 2014, Front. Neural Circuits..

[10]  Brian Litt,et al.  Flexible, Foldable, Actively Multiplexed, High-Density Electrode Array for Mapping Brain Activity in vivo , 2011, Nature Neuroscience.

[11]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[12]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[13]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[14]  K. Deisseroth,et al.  Millisecond-timescale, genetically targeted optical control of neural activity , 2005, Nature Neuroscience.

[15]  Pablo M. Blazquez,et al.  Behavioral responses of trained squirrel and rhesus monkeys during oculomotor tasks , 2011, Experimental Brain Research.

[16]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[17]  Christopher J Machado,et al.  Eye‐tracking with nonhuman primates is now more accessible than ever before , 2011, American journal of primatology.

[18]  Richard G. M. Morris,et al.  Morris water maze , 2008, Scholarpedia.

[19]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[20]  Gregor Rainer,et al.  A MATLAB-based eye tracking control system using non-invasive helmet head restraint in the macaque , 2014, Journal of Neuroscience Methods.

[21]  Martin J. Wainwright,et al.  Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions , 2011, ICML.

[22]  Hjalmar K. Turesson,et al.  Can vocal conditioning trigger a semiotic ratchet in marmosets? , 2015, Front. Psychol..

[23]  Thomas Serre,et al.  Automated home-cage behavioural phenotyping of mice. , 2010, Nature communications.

[24]  John H. Reynolds,et al.  Active Vision in Marmosets: A Model System for Visual Neuroscience , 2014, The Journal of Neuroscience.

[25]  K. Gannon,et al.  A system for studying the microstructure of ingestive behavior in mice , 1992, Physiology & Behavior.

[26]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Helen Shen,et al.  Precision gene editing paves way for transgenic monkeys , 2013, Nature.

[28]  G. Townsend,et al.  Craniofacial growth in young marmosets (Callithrix jacchus) , 1983, Laboratory animals.

[29]  E. Nestler,et al.  Neurobehavioral assessment in the information age , 2004, Nature Neuroscience.

[30]  Roy D. Patterson,et al.  Vocal-Tract Resonances as Indexical Cues in Rhesus Monkeys , 2007, Current Biology.

[31]  Adam Claridge‐Chang,et al.  The surveillance state of behavioral automation , 2012, Current Opinion in Neurobiology.

[32]  D. Paré,et al.  Altered responsiveness of BNST and amygdala neurons in trauma-induced anxiety , 2016, Translational psychiatry.

[33]  R. Colwill,et al.  A novel high-throughput imaging system for automated analyses of avoidance behavior in zebrafish larvae , 2011, Behavioural Brain Research.

[34]  Neville E. Sanjana,et al.  High-throughput functional genomics using CRISPR–Cas9 , 2015, Nature Reviews Genetics.

[35]  J. Flynn,et al.  Modeling tuberculosis in nonhuman primates. , 2014, Cold Spring Harbor perspectives in medicine.

[36]  David Troilo,et al.  Visual optics and retinal cone topography in the common marmoset (Callithrix jacchus) , 1993, Vision Research.

[37]  Tapan P. Patel,et al.  An open-source toolbox for automated phenotyping of mice in behavioral tasks , 2014, Front. Behav. Neurosci..

[38]  Gordon M. Burghardt,et al.  Perspectives – Minimizing Observer Bias in Behavioral Studies: A Review and Recommendations , 2012 .

[39]  B. '. ’t Hart,et al.  The primate autoimmune encephalomyelitis model; a bridge between mouse and man , 2015, Annals of clinical and translational neurology.

[40]  Ryan P. Adams,et al.  Mapping Sub-Second Structure in Mouse Behavior , 2015, Neuron.

[41]  B. Roth.  DREADDs for Neuroscientists , 2016, Neuron.

[42]  Thomas F. Quatieri,et al.  A multimodal sensor system for automated marmoset behavioral analysis , 2016, 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[43]  Michael H. Dickinson,et al.  Multi-camera real-time three-dimensional tracking of multiple flying animals , 2010, Journal of The Royal Society Interface.

[44]  Sidarta Ribeiro,et al.  Machine Learning Algorithms for Automatic Classification of Marmoset Vocalizations , 2016, PloS one.

[45]  John D. Hunter,et al.  Matplotlib: A 2D Graphics Environment , 2007, Computing in Science & Engineering.

[46]  Jeremy I Borjon,et al.  Arousal dynamics drive vocal production in marmoset monkeys. , 2016, Journal of neurophysiology.

[47]  A. Rylands,et al.  Marmosets and tamarins : systematics, behaviour, and ecology , 1993 .

[48]  Judith M Burkart,et al.  Geometrical gaze following in common marmosets (Callithrix jacchus). , 2006, Journal of comparative psychology.

[49]  J. Takahashi,et al.  A robust automated system elucidates mouse home cage behavioral structure , 2008, Proceedings of the National Academy of Sciences.

[50]  M. Dickinson,et al.  Visual Control of Altitude in Flying Drosophila , 2010, Current Biology.

[51]  Eric Nestler,et al.  In need of high-throughput behavioral systems. , 2002, Drug discovery today.

[52]  P. Perona,et al.  utomated multi-day tracking of marked mice for the analysis of ocial behaviour , 2013 .

[53]  Erika Sasaki,et al.  Prospects for genetically modified non-human primate models, including the common marmoset , 2015, Neuroscience Research.

[54]  Ulrich Stern,et al.  Analyzing animal behavior via classifying each video frame using convolutional neural networks , 2015, Scientific Reports.

[55]  S. Haggarty,et al.  Zebrafish Behavioral Profiling Links Drugs to Biological Targets and Rest/Wake Regulation , 2010, Science.

[56]  Jean L Patterson,et al.  An animal model that reflects human disease: the common marmoset (Callithrix jacchus) , 2012, Current Opinion in Virology.

[57]  Byeong-Cheol Kang,et al.  Modeling Parkinson's disease in the common marmoset (Callithrix jacchus): overview of models, methods, and animal care , 2015, Laboratory animal research.

[58]  G. Buzsáki,et al.  Tools for probing local circuits: high-density silicon probes combined with optogenetics , 2015, Neuron.

[59]  Richard F. Kay,et al.  The Evolution of High Visual Acuity in the Anthropoidea , 2004 .

[60]  Robert A McCrea,et al.  Firing behaviour of squirrel monkey eye movement‐related vestibular nucleus neurons during gaze saccades , 2003, The Journal of physiology.

[61]  David A. Leopold,et al.  Brains, Genes, and Primates , 2015, Neuron.

[62]  Guoping Feng,et al.  Modeling psychiatric disorders for developing effective treatments , 2015, Nature Medicine.

[63]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[64]  A. Iriki,et al.  The common marmoset as a novel animal model system for biomedical and neuroscience research applications. , 2012, Seminars in fetal & neonatal medicine.

[65]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[66]  J. DiCarlo,et al.  Using goal-driven deep learning models to understand sensory cortex , 2016, Nature Neuroscience.