BishtRef
Articles Journals Publishers Authors Subjects Most Cited New Papers Year Stats Open Access
journal article Jan 01, 2018

A deep neural network to assess spontaneous pain from mouse facial expressions

Alexander H Tuttle Mark J Molinaro Jasmine F Jethwa Susana G Sotocinal Juan C Prieto Martin A Styner Jeffrey S Mogil Mark J Zylka
Molecular Pain Vol. 14 · SAGE Publications
View at Publisher Save 10.1177/1744806918763658
Abstract
Grimace scales quantify characteristic facial expressions associated with spontaneous pain in rodents and other mammals. However, these scales have not been widely adopted largely because of the time and effort required for highly trained humans to manually score the images. Convoluted neural networks were recently developed that distinguish individual humans and objects in images. Here, we trained one of these networks, the InceptionV3 convolutional neural net, with a large set of human-scored mouse images. Output consists of a binary pain/no-pain assessment and a confidence score. Our automated Mouse Grimace Scale integrates these two outputs and is highly accurate (94%) at assessing the presence of pain in mice across different experimental assays. In addition, we used a novel set of “pain” and “no pain” images to show that automated Mouse Grimace Scale scores are highly correlated with human scores (Pearson’s r = 0.75). Moreover, the automated Mouse Grimace Scale classified a greater proportion of images as “pain” following laparotomy surgery when compared to animals receiving a sham surgery or a post-surgical analgesic. Together, these findings suggest that the automated Mouse Grimace Scale can eliminate the need for tedious human scoring of images and provide an objective and rapid way to quantify spontaneous pain and pain relief in mice.
Topics

No keywords indexed for this article. Browse by subject →

References
41
[6]
Sotocinal SG Mol Pain (2011)
[7]
Ekman P (1978)
[10]
Lu Y, Mahmoud M, andRobinson P. Estimating sheep pain level using facial action unit detection. Washington, DC: IEEE, 2017, pp.394–399. 10.1109/fg.2017.56
[11]
Development of the Horse Grimace Scale (HGS) as a Pain Assessment Tool in Horses Undergoing Routine Castration

Emanuela Dalla Costa, Michela Minero, Dirk Lebelt et al.

PLoS ONE 10.1371/journal.pone.0092281
[17]
Matsumiya LC J Am Assoc Lab Anim Sci (2012)
[21]
Waite ME J Am Assoc Lab Anim Sci (2015)
[24]
Szegedy C Comp Vis Found (2015)
[25]
Liu D J Mach Learn Res (2017)
[31]
Antropova N Med Phys (2017)
[35]
Bar Y, Diamant I, Wolf L, and Greenspan H. Deep learning with non-medical training used for chest pathology identification. In: Proceedings SPIE 2015, vol. 9414, p. 94140 10.1117/12.2083124
[36]
High-Throughput Classification of Radiographs Using Deep Convolutional Neural Networks

Alvin Rajkomar, Sneha Lingam, Andrew G. Taylor et al.

Journal of Digital Imaging 10.1007/s10278-016-9914-9
Cited By
144
Classification of multiple emotional states from facial expressions in head-fixed mice using a deep learning-based image analysis

Yudai Tanaka, Takuto Nakata · 2023

PLoS ONE
Face detection and grimace scale prediction of white furred mice

Andrea Vidal, Sumit Jha · 2022

Machine Learning with Applications
Metrics
144
Citations
41
References
Details
Published
Jan 01, 2018
Vol/Issue
14
License
View
Authors
A
Alexander H Tuttle

Department of Cell Biology and Physiology, UNC Neuroscience Center, The University of North Carolina, Chapel Hill, NC, USA

M
Mark J Molinaro

Department of Cell Biology and Physiology, UNC Neuroscience Center, The University of North Carolina, Chapel Hill, NC, USA

J
Jasmine F Jethwa

Department of Cell Biology and Physiology, UNC Neuroscience Center, The University of North Carolina, Chapel Hill, NC, USA

S
Susana G Sotocinal

Department of Psychology, Alan Edwards Centre for Research on Pain, McGill University, Montreal, QC, Canada

J
Juan C Prieto

Department of Psychiatry, Carolina Institute for Developmental Disabilities, The University of North Carolina, Chapel Hill, NC, USA

M
Martin A Styner

Department of Psychiatry, Carolina Institute for Developmental Disabilities, The University of North Carolina, Chapel Hill, NC, USA

J
Jeffrey S Mogil

Department of Psychology, Alan Edwards Centre for Research on Pain, McGill University, Montreal, QC, Canada

M
Mark J Zylka

Department of Cell Biology and Physiology, UNC Neuroscience Center, The University of North Carolina, Chapel Hill, NC, USA

Funding
NIH Office of the Director Award: DP1ES024088
NIH Clinical Center Award: U54HD079124
Eunice Kennedy Shriver National Institute of Child Health and Human Development Award: T32HD040127
Louise and Alan Edwards Foundation Award: unrestricted grant
Cite This Article
Alexander H Tuttle, Mark J Molinaro, Jasmine F Jethwa, et al. (2018). A deep neural network to assess spontaneous pain from mouse facial expressions. Molecular Pain, 14. https://doi.org/10.1177/1744806918763658
Related

You May Also Like

A Simplified Up-Down Method (SUDO) for Measuring Mechanical Nociception in Rodents Using von Frey Filaments

Robert P Bonin, Cyril Bories · 2014

361 citations

HC-030031, a TRPA1 Selective Antagonist, Attenuates Inflammatory- and Neuropathy-Induced Mechanical Hypersensitivity

Samer R Eid, Eric D Crown · 2008

358 citations

Expression of Nav1.7 in DRG Neurons Extends from Peripheral Terminals in the Skin to Central Preterminal Branches and Terminals in the Dorsal Horn

Joel A Black, Noémie Frézel · 2012

174 citations

S1 is Associated with Chronic Low Back Pain: A Functional and Structural MRI Study

Jian Kong, B Spaeth · 2013

120 citations

The Chemokine CXCL1/Growth Related Oncogene Increases Sodium Currents and Neuronal Excitability in Small Diameter Sensory Neurons

Jun-Gang Wang, Judith A Strong · 2008

82 citations