Hostname: page-component-8448b6f56d-mp689 Total loading time: 0 Render date: 2024-04-23T08:28:14.568Z Has data issue: false hasContentIssue false
  • English
  • Français

Individualised automated lameness detection in dairy cows and the impact of historical window length on algorithm performance

Published online by Cambridge University Press:  29 July 2019

D. Piette Open the ORCID record for D. Piette [Opens in a new window] ,
T. Norton ,
V. Exadaktylos  and
D. Berckmans
D. Piette
Affiliation:
M3-BIORES, Division Animal and Human Health Engineering, Department of Biosystems, KU Leuven, Kasteelpark Arenberg 30, 3001 Heverlee, Vlaams-Brabant, Belgium
T. Norton*
Affiliation:
M3-BIORES, Division Animal and Human Health Engineering, Department of Biosystems, KU Leuven, Kasteelpark Arenberg 30, 3001 Heverlee, Vlaams-Brabant, Belgium
V. Exadaktylos
Affiliation:
BioRICS nv, Technologielaan 3, 3001 Leuven, Vlaams-Brabant, Belgium
D. Berckmans
Affiliation:
M3-BIORES, Division Animal and Human Health Engineering, Department of Biosystems, KU Leuven, Kasteelpark Arenberg 30, 3001 Heverlee, Vlaams-Brabant, Belgium BioRICS nv, Technologielaan 3, 3001 Leuven, Vlaams-Brabant, Belgium
*
†E-mail: tomas.norton@kuleuven.be
Get access

Abstract

Lameness is an important economic problem in the dairy sector, resulting in production loss and reduced welfare of dairy cows. Given the modern-day expansion of dairy herds, a tool to automatically detect lameness in real-time can therefore create added value for the farmer. The challenge in developing camera-based tools is that one system has to work for all the animals on the farm despite each animal having its own individual lameness response. Individualising these systems based on animal-level historical data is a way to achieve accurate monitoring on farm scale. The goal of this study is to optimise a lameness monitoring algorithm based on back posture values derived from a camera for individual cows by tuning the deviation thresholds and the quantity of the historical data being used. Back posture values from a sample of 209 Holstein Friesian cows in a large herd of over 2000 cows were collected during 15 months on a commercial dairy farm in Sweden. A historical data set of back posture values was generated for each cow to calculate an individual healthy reference per cow. For a gold standard reference, manual scoring of lameness based on the Sprecher scale was carried out weekly by a single skilled observer during the final 6 weeks of data collection. Using an individual threshold, deviations from the healthy reference were identified with a specificity of 82.3%, a sensitivity of 79%, an accuracy of 82%, and a precision of 36.1% when the length of the healthy reference window was not limited. When the length of the healthy reference window was varied between 30 and 250 days, it was observed that algorithm performance was maximised with a reference window of 200 days. This paper presents a high-performing lameness detection system and demonstrates the importance of the historical window length for healthy reference calculation in order to ensure the use of meaningful historical data in deviation detection algorithms.

Keywords

healthyreferencebackposturedata
Type
Research Article
Information
animal , Volume 14 , Issue 2 , February 2020 , pp. 409 - 417
Copyright
© The Animal Consortium 2019 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Abuelo, A, Gandy, JC, Neuder, L, Brester, J and Sordillo, LM 2016. Short communication: markers of oxidant status and inflammation relative to the development of claw lesions associated with lameness in early lactation cows. Journal of Dairy Science 99, 5640–5648.CrossRefGoogle ScholarPubMed
Alban, L, Agger, J and Lawson, LG 1996. Lameness in tied Danish dairy cattle: the possible influence of housing systems, management, milk yield, and prior incidents of lameness. Preventive Veterinary Medicine 29, 135–149.CrossRefGoogle Scholar
Alsaaod, M, Römer, C, Kleinmanns, J, Hendriksen, K, Rose-Meierhöfer, S, Plümer, L and Büscher, W 2012. Electronic detection of lameness in dairy cows through measuring pedometric activity and lying behavior. Applied Animal Behaviour Science 142, 134–141.CrossRefGoogle Scholar
Archer, S, Green, M and Huxley, J 2010. Association between milk yield and serial locomotion score assessments in UK dairy cows. Journal of Dairy Science 93, 4045–4053.CrossRefGoogle ScholarPubMed
Baggott, D and Russell, A 1981. Lameness in cattle. British Veterinary Journal 137, 113–132.CrossRefGoogle ScholarPubMed
Barnes, A, Rutherford, K, Langford, F and Haskell, M 2011. The effect of lameness prevalence on technical efficiency at the dairy farm level: an adjusted data development analysis approach. Journal of Dairy Science 94, 5449–5457.CrossRefGoogle Scholar
Berckmans, D 2006. Automatic on-line monitoring of animals by Precision Livestock Farming. In Livestock production and society (ed. Geers, R and Madec, F), pp. 287–294. Wageningen Academic Publishers, Wageningen, the Netherlands.Google Scholar
Cook, NB, Rieman, J, Gomez, A and Burgi, K 2012. Observations on the design and use of footbaths for the control of infectious hoof disease in dairy cattle. The Veterinary Journal 193, 669–673.CrossRefGoogle ScholarPubMed
Dórea, F, Revie, C, McEwen, B, McNab, W, Kelton, D and Sanchez, J 2013. Retrospective time series analysis of veterinary laboratory data: preparing a historical baseline for cluster detection in syndromic surveillance. Preventive Veterinary Medicine 109, 219–227.CrossRefGoogle ScholarPubMed
Guarino, M, Norton, T, Berckmans, D, Vranken, E and Berckmans, D 2017. A blueprint for developing and applying precision livestock farming tools: a key output of the EU-PLF project. Animal Frontiers 7, 12–17.CrossRefGoogle Scholar
Horseman, SV, Roe, EJ, Huxley, JN, Bell, NJ, Mason, CS and Whay, HR 2014. The use of in-depth interviews to understand the process of treating lame dairy cows from the farmer’s perspective. Animal Welfare 23, 157–165.CrossRefGoogle Scholar
Jabbar, KA, Hansen, MF, Smith, ML and Smith, LN 2017. Early and non-intrusive lameness detection in dairy cows using 3-dimensional video. Biosystems Engineering 153, 63–69.CrossRefGoogle Scholar
Lafrance, J and Miller, D 2010. Defining acute kidney injury in database studies: the effects of varying the baseline kidney function assessment period and considering CKD status. American Journal of Kidney Diseases 56, 651–660.CrossRefGoogle ScholarPubMed
Leach, K, Paul, E, Whay, H, Barker, Z, Maggs, C, Sedgwick, A and Main, D 2013. Reducing lameness in dairy herds - Overcoming some barriers. Research in Veterinary Science 94, 820–825.CrossRefGoogle ScholarPubMed
Liu, J, Neerchal, NK, Tasch, U, Dyer, RM and Rajkondawar, PG 2009. Enhancing the prediction accuracy of bovine lameness models through transformations of limb movement variables. Journal of Dairy Science 92, 2539–2550.CrossRefGoogle ScholarPubMed
Maertens, W, Vangeyte, J, Baert, J, Jantuan, A, Mertens, KC, De Campeneere, S, Pluk, A, Opsomer, G, Van Weyenberg, S and Van Nuffel, A 2011. Development of a real time cow gait tracking and analysing tool to assess lameness using a pressure sensitive walkway: the GAITWISE system. Biosystems Engineering 110, 29–39.CrossRefGoogle Scholar
NFACC 2018. Code of practice for the care and handling of dairy cattle. Retrieved on 13 November 2018 from http://www.nfacc.ca/pdfs/codes/dairy_code_of_practice.pdf.Google Scholar
Pastell, M and Kujala, M 2007. A probabilistic neural network model for lameness detection. Journal of Dairy Science 90, 2283–2292.CrossRefGoogle ScholarPubMed
Pastell, M and Madsen, H 2008. Application of CUSUM charts to detect lameness in a milking robot. Expert Systems with Applications 35, 2032–2040.CrossRefGoogle Scholar
Pluk, A, Bahr, C, Poursaberi, A, Maertens, W, van Nuffel, A and Berckmans, D 2012. Automatic measurement of touch and release angles of the fetlock joint for lameness detection in dairy cattle using vision techniques. Journal of Dairy Science 95, 1738–1748.CrossRefGoogle ScholarPubMed
Poursaberi, A, Bahr, C, Pluk, A, Van Nuffel, A and Berckmans, D 2010. Real-time automatic lameness detection based on back posture extraction in dairy cattle: Shape analysis of cow with image processing techniques. Computers and Electrons in Agriculture 74, 110–119.CrossRefGoogle Scholar
Sadiq, MB, Ramanoon, SZ, Mossadeq, WMS, Mansor, R and Syed-Hussain, SS 2017. Association between lameness and indicators of dairy cow welfare based on locomotion scoring, body and hock condition, leg hygiene and lying behavior. Animals 7, 79.CrossRefGoogle Scholar
Schlageter-Tello, A, Bokkers, EAM, Groot Koerkamp, PWG, Van Hertem, T, Viazzi, S, Romanini, CEB, Halachmi, I, Bahr, C, Berckmans, D and Lokhorst, K 2015. Comparison of locomotion scoring for dairy cows by experienced and inexperienced raters using live or video observation methods. Animal Welfare 24, 69–79.CrossRefGoogle Scholar
Sprecher, D, Hostetler, D and Kanneene, J 1997. A lameness scoring system that uses posture and gait to predict dairy cattle reproductive performance. Theriogenology 47, 1179–1187.CrossRefGoogle ScholarPubMed
Tambuyzer, T, Baschun, D and Aerts, J-M 2018. Towards individualised model-based monitoring: from biology to technology. PhD thesis, KU Leuven University, Leuven, Belgium.Google Scholar
Van Hertem, T, Maltz, E, Antler, A, Romanini, CEB, Viazzi, S, Bahr, C, Schlageter-Tello, A, Lokhorst, C, Berckmans, D and Halachmi, I 2013. Lameness detection based on multivariate continuous sensing of milk yield, rumination, and neck activity. Journal of Dairy Science 96, 4286–4298.CrossRefGoogle ScholarPubMed
Van Hertem, T, Viazzi, S, Steensels, M, Maltz, E, Antler, A, Alchanatis, V, Schlageter-Tello, AA, Lokhorst, K, Romanini, ECB, Bahr, C, Berckmans, D and Halachmi, I 2014. Automatic lameness detection based on consecutive 3D-video recordings. Biosystems Engineering 119, 108–116.CrossRefGoogle Scholar
Van Nuffel, A, Zwertvaegher, I, Pluym, L, Van Weyenberg, S, Thorup, V, Pastell, M, Sonck, B and Saeys, W 2015. Lameness detection in dairy cows: part 1. How to distinguish between non-lame and lame cows based on differences in locomotion and behavior. Animals 5, 838–860.CrossRefGoogle Scholar
Van Nuffel, A, Zwertvaegher, I, Van Weyenberg, S, Pastell, M, Thorup, V, Bahr, C, Sonck, B and Saeys, W 2015b. Lameness detection in dairy cows: part 2. Use of sensors to automatically register changes in locomotion or behavior. Animals 5, 861–885.CrossRefGoogle ScholarPubMed
Vial, F and Berezowski, J 2015. A practical approach to designing syndromic surveillance systems for livestock and poultry. Preventive Veterinary Medicine 120, 27–38.CrossRefGoogle ScholarPubMed
Viazzi, S, Bahr, C, Schlageter-Tello, A, Van Hertem, T, Romanini, CEB, Pluk, A, Halachmi, I, Lokhorst, C and Berckmans, D 2013. Analysis of individual classification of lameness using automatic measurement of back posture in dairy cattle. Journal of Dairy Science 96, 257–266.CrossRefGoogle ScholarPubMed
Viazzi, S, Bahr, C, Van Hertem, T, Schlageter-Tello, A, Romanini, CEB, Halachmi, I, Lokhorst, C and Berckmans, D 2014. Comparison of a three-dimensional and two-dimensional camera system for automated measurement of back posture in dairy cows. Computers and Electronics in Agriculture 100, 139–147.CrossRefGoogle Scholar
Weber, A, Stamer, E, Junge, W and Thaller, G 2013. Genetic parameters for lameness and claw and leg diseases in dairy cows. Journal of Dairy Science 96, 3310–3318.CrossRefGoogle ScholarPubMed