A machine-vision approach for automated pain measurement at millisecond timescales

Objective and automatic measurement of pain in mice remains a barrier for discovery in both basic and translational neuroscience. Here we capture rapid paw kinematics during pain behavior in mice with high-speed videography and automated paw tracking with machine and deep learning approaches. Our statistical software platform, PAWS (Pain Assessment at Withdrawal Speeds), uses a univariate projection of paw position over time to automatically quantify fast paw dynamics at the onset of paw withdrawal and also lingering pain-related behaviors such as paw guarding and shaking. Applied to innocuous and noxious stimuli across six inbred mouse strains, a linear discriminant analysis reveals a two-dimensional subspace that separates painful from non-painful stimuli on one axis, and further distinguishes the severity of pain on the second axis. Automated paw tracking combined with PAWS reveals behaviorally-divergent mouse strains that display hypo- and hyper-sensitivity to mechanical stimuli. To demonstrate the efficacy of PAWS for detecting hypersensitivity to noxious stimuli, we chemogenetically activated pain-aversion neurons in the amygdala, which further separated the behavioral representation of pain-related behaviors along a low-dimensional path. Taken together, this automated pain quantification approach should increase the ease and objectivity of collecting rigorous behavioral data, and it is compatible with other neural circuit dissection tools for determining the mouse pain state.

[1]  Jacob M. Graving,et al.  DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning , 2019, bioRxiv.

[2]  Scott W. Linderman,et al.  The Striatum Organizes 3D Behavior via Moment-to-Moment Action Selection , 2018, Cell.

[3]  Blair H. Smith,et al.  The Genetics of Neuropathic Pain from Model Organisms to Clinical Application , 2019, Neuron.

[4]  Ronald Melzack,et al.  The short-form McGill pain questionnaire , 1987, Pain.

[5]  William Bialek,et al.  Mapping the stereotyped behaviour of freely moving fruit flies , 2013, Journal of The Royal Society Interface.

[6]  R. Full,et al.  Tail-assisted pitch control in lizards, robots and dinosaurs , 2012, Nature.

[7]  Nathan T. Fried,et al.  Development of a Mouse Pain Scale Using Sub-second Behavioral Mapping and Statistical Modeling , 2019, Cell reports.

[8]  R. D'Hooge,et al.  Differences in nociceptive behavioral performance between C57BL/6J, 129S6/SvEv, B6 129 F1 and NMRI mice , 2008, Behavioural Brain Research.

[9]  E. Chesler,et al.  Transgenic studies of pain and analgesia: mutation or background genotype? , 2001, The Journal of pharmacology and experimental therapeutics.

[10]  C. Woolf,et al.  Toward a Mechanism-Based Approach to Pain Diagnosis. , 2016, The journal of pain : official journal of the American Pain Society.

[11]  Kristin Branson,et al.  JAABA: interactive machine learning for automatic annotation of animal behavior , 2013, Nature Methods.

[12]  G. Elmer,et al.  Aggression modulates genetic influences on morphine analgesia as assessed using a classical mendelian cross analysis , 2005, Psychopharmacology.

[13]  K. Craig,et al.  Coding of facial expressions of pain in the laboratory mouse , 2010, Nature Methods.

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

[15]  Muriel T. Davisson,et al.  Genetic variation among 129 substrains and its importance for targeted mutagenesis in mice , 1997, Nature Genetics.

[16]  David P. Roberson,et al.  Time-Resolved Fast Mammalian Behavior Reveals the Complexity of Protective Pain Responses. , 2017, Cell reports.

[17]  C. Woolf,et al.  Overcoming obstacles to developing new analgesics , 2010, Nature Medicine.

[18]  David Julius,et al.  Cellular and Molecular Mechanisms of Pain , 2009, Cell.

[19]  M. Blumberg,et al.  Rapid Whisker Movements in Sleeping Newborn Rats , 2012, Current Biology.

[20]  J. Mogil,et al.  The Pain Genes Database: An interactive web browser of pain-related transgenic knockout studies , 2007, Pain.

[21]  Benjamin F. Grewe,et al.  An amygdalar neural ensemble that encodes the unpleasantness of pain , 2018, Science.

[22]  R. Baron,et al.  Diagnosis and assessment of neuropathic pain through questionnaires , 2018, The Lancet Neurology.

[23]  Martin A Styner,et al.  A deep neural network to assess spontaneous pain from mouse facial expressions , 2018, Molecular pain.

[24]  J. Mogil,et al.  Pain genetics: past, present and future. , 2012, Trends in genetics : TIG.

[25]  T. Brennan,et al.  Strain and Sex Influence on Pain Sensitivity after Plantar Incision in the Mouse , 2006, Anesthesiology.

[26]  Irina Vetter,et al.  Methods Used to Evaluate Pain Behaviors in Rodents , 2017, Front. Mol. Neurosci..

[27]  Mikhail Kislin,et al.  Fast animal pose estimation using deep neural networks , 2018, Nature Methods.

[28]  F. Engert,et al.  Escape Behavior Elicited by Single, Channelrhodopsin-2-Evoked Spikes in Zebrafish Somatosensory Neurons , 2008, Current Biology.

[29]  David J. Anderson,et al.  Computational Neuroethology: A Call to Action , 2019, Neuron.

[30]  Michael J. O'Donovan,et al.  Identification of a novel spinal nociceptive-motor gate control for Aδ pain stimuli in rats , 2017, eLife.

[31]  Kevin M. Cury,et al.  DeepLabCut: markerless pose estimation of user-defined body parts with deep learning , 2018, Nature Neuroscience.

[32]  Kyle S Severson,et al.  Active Touch and Self-Motion Encoding by Merkel Cell-Associated Afferents , 2017, Neuron.

[33]  Carmen Birchmeier,et al.  Touch Receptor-Derived Sensory Information Alleviates Acute Pain Signaling and Fine-Tunes Nociceptive Reflex Coordination , 2017, Neuron.

[34]  G. Elmer,et al.  Heritability of nociception I: Responses of 11 inbred mouse strains on 12 measures of nociception , 1999, Pain.