High-throughput markerless pose estimation and home-cage activity analysis of tree shrew using deep learning

Abstract

Background: Quantifying the rich home-cage activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models. However, due to the lack of effective behavioral methods, most efforts on tree shrew behavior are limited to simple measures, resulting in the loss of much behavioral information.

Methods: To address this issue, we present a deep learning (DL) approach to achieve markerless pose estimation and recognize multiple spontaneous behaviors of tree shrews, including drinking, eating, resting, and staying in the dark house, etc.

Results: This high-throughput approach can monitor the home-cage activities of 16 tree shrews simultaneously over an extended period. Additionally, we demonstrated an innovative system with reliable apparatus, paradigms, and analysis methods for investigating food grasping behavior. The median duration for each bout of grasping was 0.20 s.

Conclusion: This study provides an efficient tool for quantifying and understand tree shrews' natural behaviors

Keywords

deep learning / food grasping / home-cage activity / pose estimation / tree shrew

References

[1] Fan Y, Huang ZY, Cao CC, et al. Genome of the Chinese tree shrew. Nat Commun. 2013; 4(1): 1426.

[2] Fan Y, Yu D, Yao YG. Tree shrew database (TreeshrewDB): a genomic knowledge base for the Chinese tree shrew. Sci Rep. 2014; 4(1): 7145.

[3] Savier E, Sedigh-Sarvestani M, Wimmer R, Fitzpatrick D. A bright future for the tree shrew in neuroscience research: summary from the inaugural tree shrew users meeting. Zool Res. 2021; 42(4): 478-481.

[4] Zhao YQ, Liu YQ, Yuan JF, et al. Regeneration of islet β-cells in tree shrews and rats. Anim Models and Exp Med. 2018; 1(2): 152-161.

[5] Yao YG. Creating animal models, why not use the Chinese tree shrew (Tupaia belangeri chinensis)? Zool Res. 2017; 38(3): 118-126.

[6] Ma XT, Li FL, Jiang HJ, Li WH, Zhang Y, Du TY. Detection and comparison of physiological indexes in the wild and laboratory tree shrew. Zool Res. 2011; 32(1): 4-10.

[7] Feng Y, Xia W, Ji K, et al. Hemogram study of an artificially feeding tree shrew (Tupaia belangeri chinensis). Exp Anim. 2020; 69(1): 80-91.

[8] Li B, Zhang RP, Li JT, et al. Measurement and analysis of anatomical parameter values in tree shrews. Zool Res. 2013; 34(2): 132-138.

[9] Ni RJ, Huang ZH, Luo PH, Ma XH, Li T, Zhou JN. The tree shrew cerebellum atlas: systematic nomenclature, neurochemical characterization, and afferent projections. J Comp Neurol. 2018; 526(17): 2744-2775.

[10] Ni RJ, Shu YM, Li T, Zhou JN. Whole-brain afferent inputs to the caudate nucleus, putamen, and Accumbens nucleus in the tree shrew striatum. Front Neuroanat. 2021; 15: 763298.

[11] Ni RJ, Luo PH, Shu YM, Chen JT, Zhou JN. Whole-brain mapping of afferent projections to the bed nucleus of the stria terminalis in tree shrews. Neuroscience. 2016; 333: 162-180.

[12] Ni RJ, Shu YM, Luo PH, Zhou JN. Whole-brain mapping of afferent projections to the suprachiasmatic nucleus of the tree shrew. Tissue Cell. 2021; 73: 101620.

[13] Huang J, Yang G, Li Z, et al. Involvement of dopamine D3 receptor and dopamine transporter in methamphetamine-induced behavioral sensitization in tree shrews. Brain Behav. 2020; 10(2): e01533.

[14] Khani A, Rainer G. Recognition memory in tree shrew (Tupaia belangeri) after repeated familiarization sessions. Behav Process. 2012; 90(3): 364-371.

[15] Ni R-J, Tian Y, Dai X-Y, et al. Social avoidance behavior in male tree shrews and prosocial behavior in male mice toward unfamiliar conspecifics in the laboratory. Zool Res. 2020; 41(3): 258-272.

[16] Zhi-cheng ZH, Qing-kai SO, Xiao-hui LI, et al. Behavior detection method of MPTP induced tree shrew Parkinson's disease models. Lab Anim Comp Med. 2019; 39(1): 9-14.

[17] Li C, McHaney KM, Sederberg PB, Cang J. Tree shrews as an animal model for studying perceptual decision-making reveal a critical role of stimulus-independent processes in guiding behavior. eNeuro. 2022; 9(6): ENEURO.0419-22.2022.

[18] Neff EP. Home sweet home cage. Lab Anim. 2018; 47(10): 261-264.

[19] Le Bras A. Light and activity in the home cage. Lab Anim. 2022; 51(3): 76.

[20] Mill J, Galsworthy MJ, Paya-Cano JL, et al. Home-cage activity in heterogeneous stock (HS) mice as a model of baseline activity. Genes Brain Behav. 2002; 1(3): 166-173.

[21] Tang X, Orchard SM, Sanford LD. Home cage activity and behavioral performance in inbred and hybrid mice. Behav Brain Res. 2002; 136(2): 555-569.

[22] Pernold K, Rullman E, Ulfhake B. Major oscillations in spontaneous home-cage activity in C57BL/6 mice housed under constant conditions. Sci Rep. 2021; 11(1): 4961.

[23] Ganea K, Liebl C, Sterlemann V, Müller MB, Schmidt MV. Pharmacological validation of a novel home cage activity counter in mice. J Neurosci Methods. 2007; 162(1-2): 180-186.

[24] de Visser L, van den Bos R, Spruijt BM. Automated home cage observations as a tool to measure the effects of wheel running on cage floor locomotion. Behav Brain Res. 2005; 160(2): 382-388.

[25] Mnih V, Kavukcuoglu K, Silver D, et al. Human-level control through deep reinforcement learning. Nature. 2015; 518(7540): 529-533.

[26] Rosé CP. Artificial intelligence: a social spin on language analysis. Nature. 2017; 545(7653): 166-167.

[27] Silver D, Huang A, Maddison CJ, et al. Mastering the game of go with deep neural networks and tree search. Nature. 2016; 529(7587): 484-489.

[28] Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare. Nat Med. 2019; 25(1): 24-29.

[29] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Jordan MI, LeCun Y, Solla SA, eds. Advances in Neural Information Processing Systems (NIPS). The MIT Press; 2012: 1097-1105.

[30] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). IEEE; 2016: 770-778.

[31] Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint 2014.

[32] Romero-Ferrero F, Bergomi MG, Hinz RC, Heras FJH, de Polavieja GG. Idtracker.Ai: tracking all individuals in small or large collectives of unmarked animals. Nat Methods. 2019; 16(2): 179-182.

[33] Mathis A, Mamidanna P, Cury KM, et al. DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. Nat Neurosci. 2018; 21(9): 1281-1289.

[34] Pereira TD, Tabris N, Matsliah A, et al. SLEAP: a deep learning system for multi-animal pose tracking. Nat Methods. 2022; 19(4): 486-495.

[35] Su F, Wang Y, Wei M, et al. Noninvasive tracking of every individual in unmarked mouse groups using multi-camera fusion and deep learning. Neurosci Bull. 2023; 39(6): 893-910.

[36] Pereira TD, Aldarondo DE, Willmore L, et al. Fast animal pose estimation using deep neural networks. Nat Methods. 2019; 16(1): 117-125.

[37] Marshall JD, Aldarondo DE, Dunn TW, Wang WL, Berman GJ, Ölveczky BP. Continuous whole-body 3D kinematic recordings across the rodent behavioral repertoire. Neuron. 2021; 109(3): 420-437.

[38] Bala PC, Eisenreich BR, Yoo SBM, Hayden BY, Park HS, Zimmermann J. Automated markerless pose estimation in freely moving macaques with OpenMonkeyStudio. Nat Commun. 2020; 11(1): 4560.

[39] Ren W, Wei P, Yu S, Zhang YQ. Left-right asymmetry and attractor-like dynamics of dog's tail wagging during dog-human interactions. iScience. 2022; 25(8): 104747.

[40] Li D, Chen Y, Zhang K, Li Z. Mounting behaviour recognition for pigs based on deep learning. Sensors. 2019; 19(22): 4924.

[41] MacArthur Clark JA, Sun D. Guidelines for the ethical review of laboratory animal welfare People's Republic of China National Standard GB/T 35892-2018 [issued 6 February 2018 effective from 1 September 2018]. Anim Models and Exp Med. 2020; 3(1): 103-113.

[42] Peng Y, Ye Z, Zhou R, Wang Y, Ma Y, Shi L. Tree Shrew Biology. (Chinese Edition). Yunnan Science and Technology Press; 1991.

[43] Zhen Y, Yao Y, Xu L. Tree Shrew Basic Biology and Disease Models. (Chinese Edition). Yunnan Science and Technology Press; 2014.

[44] Peckre LR, Lowie A, Brewer D, et al. Food mobility and the evolution of grasping behaviour: a case study in strepsirrhine primates. J Exp Biol. 2019; 222(Pt 20): jeb207688.

[45] Rogers LJ. Manual bias, behavior, and cognition in common marmosets and other primates. Prog Brain Res. 2018; 238: 91-113.

[46] Spinozzi G, Truppa V, Laganà T. Grasping behavior in tufted capuchin monkeys (Cebus apella): grip types and manual laterality for picking up a small food item. Am J Phys Anthropol. 2004; 125(1): 30-41.

[47] Wang Z, Gerstein M, Snyder M. RNA-seq: a revolutionary tool for transcriptomics. Nat Rev Genet. 2009; 10(1): 57-63.

[48] Spira ME, Hai A. Multi-electrode array technologies for neuroscience and cardiology. Nat Nanotechnol. 2013; 8(2): 83-94.

[49] Lewis CM, Bosman CA, Fries P. Recording of brain activity across spatial scales. Curr Opin Neurobiol. 2015; 32: 68-77.

[50] Tian Y, Yang C, Cui Y, et al. An excitatory neural assembly encodes short-term memory in the prefrontal cortex. Cell Rep. 2018; 22(7): 1734-1744.

[51] Su F, Tian Y. Non-rigid registration for two-photon imaging using triangulation and piecewise affine transformation. Neuroscience. 2022; 491: 1-12.

[52] Wang Y, Su F, Wang S, et al. Efficient implementation of convolutional neural networks in the data processing of two-photon in vivo imaging. Bioinformatics. 2019; 35(17): 3208-3210.

[53] De Luna P, Veit J, Rainer G. Basal forebrain activation enhances between-trial reliability of low-frequency local field potentials (LFP) and spiking activity in tree shrew primary visual cortex (V1). Brain Struct Funct. 2017; 222(9): 4239-4252.

[54] Schumacher JW, McCann MK, Maximov KJ, Fitzpatrick D. Selective enhancement of neural coding in V1 underlies fine-discrimination learning in tree shrew. Curr Biol. 2022; 32(15): 3245-3260.

[55] Luo PH, Shu YM, Ni RJ, Liu YJ, Zhou JN. A characteristic expression pattern of Core circadian genes in the diurnal tree shrew. Neuroscience. 2020; 437: 145-160.

[56] Fan Y, Luo R, Su LY, et al. Does the genetic feature of the Chinese tree shrew (Tupaia belangeri chinensis) support its potential as a viable model for Alzheimer's disease research? J Alzheimers Dis. 2018; 61(3): 1015-1028.

RIGHTS & PERMISSIONS

2025 The Author(s). Animal Models and Experimental Medicine published by John Wiley & Sons Australia, Ltd on behalf of The Chinese Association for Laboratory Animal Sciences.