FREE SHIPPING over $40
OVER 10000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
PloS one2021; 16(10); e0258672; doi: 10.1371/journal.pone.0258672

Pain assessment in horses using automatic facial expression recognition through deep learning-based modeling.

Abstract: The aim of this study was to develop and evaluate a machine vision algorithm to assess the pain level in horses, using an automatic computational classifier based on the Horse Grimace Scale (HGS) and trained by machine learning method. The use of the Horse Grimace Scale is dependent on a human observer, who most of the time does not have availability to evaluate the animal for long periods and must also be well trained in order to apply the evaluation system correctly. In addition, even with adequate training, the presence of an unknown person near an animal in pain can result in behavioral changes, making the evaluation more complex. As a possible solution, the automatic video-imaging system will be able to monitor pain responses in horses more accurately and in real-time, and thus allow an earlier diagnosis and more efficient treatment for the affected animals. This study is based on assessment of facial expressions of 7 horses that underwent castration, collected through a video system positioned on the top of the feeder station, capturing images at 4 distinct timepoints daily for two days before and four days after surgical castration. A labeling process was applied to build a pain facial image database and machine learning methods were used to train the computational pain classifier. The machine vision algorithm was developed through the training of a Convolutional Neural Network (CNN) that resulted in an overall accuracy of 75.8% while classifying pain on three levels: not present, moderately present, and obviously present. While classifying between two categories (pain not present and pain present) the overall accuracy reached 88.3%. Although there are some improvements to be made in order to use the system in a daily routine, the model appears promising and capable of measuring pain on images of horses automatically through facial expressions, collected from video images.
Get Full Text
Publication Date: 2021-10-19 PubMed ID: 34665834PubMed Central: PMC8525760DOI: 10.1371/journal.pone.0258672Google Scholar: Lookup
The Equine Research Bank provides access to a large database of publicly available scientific literature. Inclusion in the Research Bank does not imply endorsement of study methods or findings by Mad Barn.
LinkedInCopy
  • Journal Article
  • Research Support
  • Non-U.S. Gov't

Summary

This research summary has been generated with artificial intelligence and may contain errors and omissions. Refer to the original study to confirm details provided. Submit correction.

The research article discusses the development and testing of a machine vision algorithm capable of assessing pain in horses through automated recognition of facial expressions.

Study Objective and Approach

  • This research was focused on building and evaluating a machine vision algorithm that would automatically assess the pain level in horses. The tool was designed to improve upon the existing Horse Grimace Scale, which often requires a well-trained human observer on site, may be influenced by the observer’s presence, and may not permit continuous evaluation of the animal’s condition.
  • The researchers wanted to devise a solution that could deliver more accurate, real-time monitoring of pain responses in horses, thereby ensuring timely diagnosis and improved treatment effectiveness.

Methodology and Data Collection

  • This study utilized video footage of seven horses undergoing castration, captured from a camera positioned above the feeding station. The images were collected at four different times each day, for a period of two days before and four days after the surgical procedure.
  • The collected facial images were then labeled to construct a database signaling pain, which was used to train the computational pain classifier using machine learning techniques.

Algorithm Development and Accuracy

  • The researchers developed the machine vision algorithm with the help of a Convolutional Neural Network (CNN), a type of deep learning model most commonly applied to analyzing visual data.
  • The CNN was trained to classify the pain level into three distinct categories: not present, moderately present, and obviously present. It achieved an overall accuracy of 75.8% in this task.
  • When the pain level was simplified into two categories, pain not present and pain present, the consistency of the algorithm was notably higher at 88.3%.

Conclusions and Future Directions

  • Despite some areas of improvement, the researchers concluded that the model appears promising for future applications. It offers the capability to measure pain in horses automatically through facial expressions captured in video images.
  • In future iterations, the researchers will likely look to improve the accuracy of the model, and refine it for more practical, routine use in high-traffic areas such as barns or veterinary clinics.

Cite This Article

APA
Lencioni GC, de Sousa RV, de Souza Sardinha EJ, Corrêa RR, Zanella AJ. (2021). Pain assessment in horses using automatic facial expression recognition through deep learning-based modeling. PLoS One, 16(10), e0258672. https://doi.org/10.1371/journal.pone.0258672

Publication

PloS one
ISSN: 1932-6203
NlmUniqueID: 101285081
Country: United States
Language: English
Volume: 16
Issue: 10
Pages: e0258672
PII: e0258672

Researcher Affiliations

Lencioni, Gabriel Carreira
  • Department of Preventive Veterinary Medicine and Animal Health of the School of Veterinary Medicine and Animal Science (FMVZ) of the University of São Paulo (USP), São Paulo, SP, Brazil.
de Sousa, Rafael Vieira
  • Department of Biosystems Engineering, Faculty of Animal Science and Food Engineering (FZEA), of the University of São Paulo, Pirassununga, São Paulo, Brazil.
de Souza Sardinha, Edson José
  • Department of Biosystems Engineering, Faculty of Animal Science and Food Engineering (FZEA), of the University of São Paulo, Pirassununga, São Paulo, Brazil.
Corrêa, Rodrigo Romero
  • Department of Surgery of the School of Veterinary Medicine and Animal Science (FMVZ) of the University of São Paulo (USP), São Paulo, SP, Brazil.
Zanella, Adroaldo José
  • Department of Preventive Veterinary Medicine and Animal Health of the School of Veterinary Medicine and Animal Science (FMVZ) of the University of São Paulo (USP), São Paulo, SP, Brazil.

MeSH Terms

  • Algorithms
  • Animals
  • Automated Facial Recognition / methods
  • Databases, Factual
  • Deep Learning
  • Facial Recognition
  • Horses
  • Humans
  • Image Interpretation, Computer-Assisted / methods
  • Neural Networks, Computer
  • Orchiectomy / adverse effects
  • Orchiectomy / veterinary
  • Pain Measurement / veterinary
  • Video Recording

Conflict of Interest Statement

The authors have declared that no competing interests exist.

References

This article includes 23 references
  1. Flecknell P. Analgesia from a veterinary perspective.. Br J Anaesth 2008 Jul;101(1):121-4.
    doi: 10.1093/bja/aen087pubmed: 18424804google scholar: lookup
  2. Dalla Costa E, Minero M, Lebelt D, Stucke D, Canali E, Leach MC. Development of the Horse Grimace Scale (HGS) as a pain assessment tool in horses undergoing routine castration.. PLoS One 2014;9(3):e92281.
    doi: 10.1371/journal.pone.0092281pmc: PMC3960217pubmed: 24647606google scholar: lookup
  3. Muir WW. Pain: mechanisms and management in horses.. Vet Clin North Am Equine Pract 2010 Dec;26(3):467-80.
    doi: 10.1016/j.cveq.2010.07.008pubmed: 21056294google scholar: lookup
  4. Gleerup KB, Lindegaard C. Recognition and quantification of pain in horses: A tutorial review. Equine Vet Educ 2016;28: 47–57.
    doi: 10.1111/eve.12383google scholar: lookup
  5. Jordan A, Hughes J, Pakresi M, Hepburn S, O'Brien JT. The utility of PAINAD in assessing pain in a UK population with severe dementia.. Int J Geriatr Psychiatry 2011 Feb;26(2):118-26.
    doi: 10.1002/gps.2489pubmed: 20652872google scholar: lookup
  6. Grunau RVE, Craig KD. Pain expression in neonates: facial action and cry.. Pain 1987 Mar;28(3):395-410.
    doi: 10.1016/0304-3959(87)90073-Xpubmed: 3574966google scholar: lookup
  7. Darwin C. The expression of the emotions in man and animals. London: John Murray; 1872.
  8. Deyo KS, Prkachin KM, Mercer SR. Development of sensitivity to facial expression of pain.. Pain 2004 Jan;107(1-2):16-21.
    doi: 10.1016/s0304-3959(03)00263-xpubmed: 14715384google scholar: lookup
  9. Cohen Kadosh K, Johnson MH. Developing a cortex specialized for face perception.. Trends Cogn Sci 2007 Sep;11(9):367-9.
    doi: 10.1016/j.tics.2007.06.007pubmed: 17631408google scholar: lookup
  10. Langford DJ, Bailey AL, Chanda ML, Clarke SE, Drummond TE, Echols S, Glick S, Ingrao J, Klassen-Ross T, Lacroix-Fralish ML, Matsumiya L, Sorge RE, Sotocinal SG, Tabaka JM, Wong D, van den Maagdenberg AM, Ferrari MD, Craig KD, Mogil JS. Coding of facial expressions of pain in the laboratory mouse.. Nat Methods 2010 Jun;7(6):447-9.
    doi: 10.1038/nmeth.1455pubmed: 20453868google scholar: lookup
  11. Gleerup KB, Forkman B, Lindegaard C, Andersen PH. An equine pain face.. Vet Anaesth Analg 2015 Jan;42(1):103-14.
    doi: 10.1111/vaa.12212pmc: PMC4312484pubmed: 25082060google scholar: lookup
  12. Marcantonio Coneglian M, Duarte Borges T, Weber SH, Godoi Bertagnon H, Michelotto PV. Use of the horse grimace scale to identify and quantify pain due to dental disorders in horses. Appl Anim Behav Sci 2020;225: 104970.
    doi: 10.1016/j.applanim.2020.104970google scholar: lookup
  13. Wathan J, Burrows AM, Waller BM, McComb K. EquiFACS: The Equine Facial Action Coding System.. PLoS One 2015;10(8):e0131738.
    doi: 10.1371/journal.pone.0131738pmc: PMC4526551pubmed: 26244573google scholar: lookup
  14. Rashid M, Silventoinen A, Gleerup KB, Andersen PH. Equine Facial Action Coding System for determination of pain-related facial responses in videos of horses.. PLoS One 2020;15(11):e0231608.
    doi: 10.1371/journal.pone.0231608pmc: PMC7608869pubmed: 33141852google scholar: lookup
  15. Andersen PH, Gleerup KB, Wathan J, Coles B, Kjellström H, Broomé S. Can a Machine Learn to See Horse Pain? An Interdisciplinary Approach Towards Automated Decoding of Facial Expressions of Pain in the Horse. Proc Meas Behav 2018; 6–8.
  16. Kil N, Ertelt K, Auer U. Development and Validation of an Automated Video Tracking Model for Stabled Horses.. Animals (Basel) 2020 Nov 30;10(12).
    doi: 10.3390/ani10122258pmc: PMC7760072pubmed: 33266297google scholar: lookup
  17. Mathis MW, Mathis A. Deep learning tools for the measurement of animal behavior in neuroscience.. Curr Opin Neurobiol 2020 Feb;60:1-11.
    doi: 10.1016/j.conb.2019.10.008pubmed: 31791006google scholar: lookup
  18. Kamilaris A, Prenafeta-Boldú FX. Deep learning in agriculture: A survey. Comput Electron Agric 2018;147: 70–90.
    doi: 10.1016/j.compag.2018.02.016google scholar: lookup
  19. Neethirajan S. The role of sensors, big data and machine learning in modern animal farming. Sens Bio-Sensing Res 2020;29: 100367.
    doi: 10.1016/j.sbsr.2020.100367google scholar: lookup
  20. Tuttle AH, Molinaro MJ, Jethwa JF, Sotocinal SG, Prieto JC, Styner MA, Mogil JS, Zylka MJ. A deep neural network to assess spontaneous pain from mouse facial expressions.. Mol Pain 2018 Jan-Dec;14:1744806918763658.
    doi: 10.1177/1744806918763658pmc: PMC5858615pubmed: 29546805google scholar: lookup
  21. Lu Y, Mahmoud M, Robinson P. Estimating Sheep Pain Level Using Facial Action Unit Detection. Proc - 12th IEEE Int Conf Autom Face Gesture Recognition, FG 2017 - 1st Int Work Adapt Shot Learn Gesture Underst Prod ASL4GUP 2017, Biometrics Wild, Bwild 2017, Heteroge 2017; 394–399.
    doi: 10.1109/FG.2017.56google scholar: lookup
  22. Andersen PH, Broomé S, Rashid M, Lundblad J, Ask K, Li Z, Hernlund E, Rhodin M, Kjellström H. Towards Machine Recognition of Facial Expressions of Pain in Horses.. Animals (Basel) 2021 Jun 1;11(6).
    doi: 10.3390/ani11061643pmc: PMC8229776pubmed: 34206077google scholar: lookup
  23. Auer J, Stick J. Equine Surgery. 5th edition. 2018. p. 1896.

Citations

This article has been cited 23 times.
Subscribe to our newsletter
Join 100,127 horse owners like you who receive our email updates on horse health and nutrition.