1
|
Doornweerd JE, Kootstra G, Veerkamp RF, Ellen ED, van der Eijk JAJ, van de Straat T, Bouwman AC. Across-Species Pose Estimation in Poultry Based on Images Using Deep Learning. FRONTIERS IN ANIMAL SCIENCE 2021. [DOI: 10.3389/fanim.2021.791290] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
Abstract
Animal pose-estimation networks enable automated estimation of key body points in images or videos. This enables animal breeders to collect pose information repeatedly on a large number of animals. However, the success of pose-estimation networks depends in part on the availability of data to learn the representation of key body points. Especially with animals, data collection is not always easy, and data annotation is laborious and time-consuming. The available data is therefore often limited, but data from other species might be useful, either by itself or in combination with the target species. In this study, the across-species performance of animal pose-estimation networks and the performance of an animal pose-estimation network trained on multi-species data (turkeys and broilers) were investigated. Broilers and turkeys were video recorded during a walkway test representative of the situation in practice. Two single-species and one multi-species model were trained by using DeepLabCut and tested on two single-species test sets. Overall, the within-species models outperformed the multi-species model, and the models applied across species, as shown by a lower raw pixel error, normalized pixel error, and higher percentage of keypoints remaining (PKR). The multi-species model had slightly higher errors with a lower PKR than the within-species models but had less than half the number of annotated frames available from each species. Compared to the single-species broiler model, the multi-species model achieved lower errors for the head, left foot, and right knee keypoints, although with a lower PKR. Across species, keypoint predictions resulted in high errors and low to moderate PKRs and are unlikely to be of direct use for pose and gait assessments. A multi-species model may reduce annotation needs without a large impact on performance for pose assessment, however, with the recommendation to only be used if the species are comparable. If a single-species model exists it could be used as a pre-trained model for training a new model, and possibly require a limited amount of new data. Future studies should investigate the accuracy needed for pose and gait assessments and estimate genetic parameters for the new phenotypes before pose-estimation networks can be applied in practice.
Collapse
|
2
|
Stracke J, Volkmann N, May F, Döhring S, Kemper N, Spindler B. Walking on Tiptoes: Digital Pads Deserve Increased Attention When Scoring Footpad Dermatitis as an Animal Welfare Indicator in Turkeys. Front Vet Sci 2021; 7:613516. [PMID: 33585603 PMCID: PMC7873931 DOI: 10.3389/fvets.2020.613516] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/02/2020] [Accepted: 12/04/2020] [Indexed: 11/20/2022] Open
Abstract
Animal welfare is one of the most challenging issues in modern farm animal husbandry. Animal welfare indicators can be used to monitor welfare on farms or at slaughterhouses, with footpad dermatitis (FPD) being one of the most important indicators used in turkeys. Up to now, the severity of FPD has been measured by evaluating the size of altered lesions on the metatarsal pad of birds. However, such lesions are not only found on the metatarsal pads, but alterations can also occur on the digital pads of the animals, the latter is not included in the European standard scoring systems for turkeys so far. The aim of the present study was to give a detailed outline of alterations on the digital pads of turkeys and associate their occurrence to a standardly used five-point scoring system, which is based on alterations of the metatarsal pad only. Therefore, pictures of 500 feet of turkeys from 16 flocks at the end of the fattening phase were taken, using an automatic camera system. Based on these pictures, alterations on the digits were scored according to different parameters (lesions, swellings, and number of affected digits). Furthermore, detailed measurements were conducted using an imaging software. Results were compared with a standardly used five-point scoring system (standard FPD scoring system), based on the metatarsal pad as reference. Results provide no equivalence in occurrence and severity of alterations on the metatarsal pads compared to those found on the digits. Pathologic alterations on the digits were already present at standard FPD scoring level 0; no differentiation became obvious between the higher scoring levels 2-4. Strong correlations were found when comparing percentage of alterations of the standard FPD scoring system to those of a system including alterations on the digits and the metatarsal pad, using the total foot as a reference (rp = 0.9, p < 0.001). This was the first study conducting a detailed analysis of alterations on the digits of turkeys. In conclusion, results of this study show that including the evaluation of alterations on digits could refine the present FPD scoring system, especially when using FPD as an animal welfare indicator.
Collapse
Affiliation(s)
- Jenny Stracke
- Institute for Animal Hygiene, Animal Welfare and Animal Behavior, University of Veterinary Medicine Hannover, Foundation, Hannover, Germany
| | - Nina Volkmann
- Institute for Animal Hygiene, Animal Welfare and Animal Behavior, University of Veterinary Medicine Hannover, Foundation, Hannover, Germany
| | - Franziska May
- Institute for Animal Hygiene, Animal Welfare and Animal Behavior, University of Veterinary Medicine Hannover, Foundation, Hannover, Germany
| | - Stefanie Döhring
- Faculty of Agricultural Sciences and Landscape Architecture, Osnabrück University of Applied Sciences, Osnabrück, Germany
| | - Nicole Kemper
- Institute for Animal Hygiene, Animal Welfare and Animal Behavior, University of Veterinary Medicine Hannover, Foundation, Hannover, Germany
| | - Birgit Spindler
- Institute for Animal Hygiene, Animal Welfare and Animal Behavior, University of Veterinary Medicine Hannover, Foundation, Hannover, Germany
| |
Collapse
|
3
|
Brito LF, Oliveira HR, McConn BR, Schinckel AP, Arrazola A, Marchant-Forde JN, Johnson JS. Large-Scale Phenotyping of Livestock Welfare in Commercial Production Systems: A New Frontier in Animal Breeding. Front Genet 2020; 11:793. [PMID: 32849798 PMCID: PMC7411239 DOI: 10.3389/fgene.2020.00793] [Citation(s) in RCA: 52] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2020] [Accepted: 07/03/2020] [Indexed: 12/13/2022] Open
Abstract
Genomic breeding programs have been paramount in improving the rates of genetic progress of productive efficiency traits in livestock. Such improvement has been accompanied by the intensification of production systems, use of a wider range of precision technologies in routine management practices, and high-throughput phenotyping. Simultaneously, a greater public awareness of animal welfare has influenced livestock producers to place more emphasis on welfare relative to production traits. Therefore, management practices and breeding technologies in livestock have been developed in recent years to enhance animal welfare. In particular, genomic selection can be used to improve livestock social behavior, resilience to disease and other stress factors, and ease habituation to production system changes. The main requirements for including novel behavioral and welfare traits in genomic breeding schemes are: (1) to identify traits that represent the biological mechanisms of the industry breeding goals; (2) the availability of individual phenotypic records measured on a large number of animals (ideally with genomic information); (3) the derived traits are heritable, biologically meaningful, repeatable, and (ideally) not highly correlated with other traits already included in the selection indexes; and (4) genomic information is available for a large number of individuals (or genetically close individuals) with phenotypic records. In this review, we (1) describe a potential route for development of novel welfare indicator traits (using ideal phenotypes) for both genetic and genomic selection schemes; (2) summarize key indicator variables of livestock behavior and welfare, including a detailed assessment of thermal stress in livestock; (3) describe the primary statistical and bioinformatic methods available for large-scale data analyses of animal welfare; and (4) identify major advancements, challenges, and opportunities to generate high-throughput and large-scale datasets to enable genetic and genomic selection for improved welfare in livestock. A wide variety of novel welfare indicator traits can be derived from information captured by modern technology such as sensors, automatic feeding systems, milking robots, activity monitors, video cameras, and indirect biomarkers at the cellular and physiological levels. The development of novel traits coupled with genomic selection schemes for improved welfare in livestock can be feasible and optimized based on recently developed (or developing) technologies. Efficient implementation of genetic and genomic selection for improved animal welfare also requires the integration of a multitude of scientific fields such as cell and molecular biology, neuroscience, immunology, stress physiology, computer science, engineering, quantitative genomics, and bioinformatics.
Collapse
Affiliation(s)
- Luiz F. Brito
- Department of Animal Sciences, Purdue University, West Lafayette, IN, United States
| | - Hinayah R. Oliveira
- Department of Animal Sciences, Purdue University, West Lafayette, IN, United States
- Department of Animal Biosciences, University of Guelph, Guelph, ON, Canada
| | - Betty R. McConn
- Oak Ridge Institute for Science and Education, Oak Ridge, TN, United States
| | - Allan P. Schinckel
- Department of Animal Sciences, Purdue University, West Lafayette, IN, United States
| | - Aitor Arrazola
- Department of Comparative Pathobiology, Purdue University, West Lafayette, IN, United States
| | | | - Jay S. Johnson
- USDA-ARS Livestock Behavior Research Unit, West Lafayette, IN, United States
| |
Collapse
|
4
|
Mohammadigheisar M, Shouldice VL, Torrey S, Widowski T, Kiarie EG. Research Note: Comparative gastrointestinal, tibia, and plasma attributes in 48-day-old fast- and slow-growing broiler chicken strains. Poult Sci 2020; 99:3086-3091. [PMID: 32475445 PMCID: PMC7597737 DOI: 10.1016/j.psj.2020.01.032] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2019] [Revised: 01/15/2020] [Accepted: 01/29/2020] [Indexed: 11/02/2022] Open
Abstract
Emerging market differentiation for broiler meat from strains exhibiting a range of growth rates is necessitating comparative research on various physiological and production aspects of these strains. The objective of the present study was to compare select gastrointestinal, tibial, and plasma attributes in a sample of 48-day-old (50 male and 50 female) broilers obtained from fast-and slow-growing flocks maintained under similar feed and management regimens. Eight birds were randomly selected from a fast (B; representative of modern commercial strains) and each of the 4 slow-growing strains (SG; D, H, M, and E). The strains differed by estimated time to reach 2.2 kg bodyweight corresponding to 36, 50, 42, 44, and 50 D for B, D, H, M, and E, respectively. Blood samples were collected to determine plasma metabolites, and birds were subsequently euthanized, weighed, and necropsied for gizzard and small intestine weight, jejunal tissue for histomorphology, ceca digesta samples for concentration of short-chain fatty acids (SCFA) and left tibia for ash content. Gizzard was heavier (P < 0.01) for D, H, and M than that for B and E, whereas the small intestine was lighter (P < 0.01) for B, D, and H than for M and E. There were no (P > 0.05) strain differences on SCFA, jejunal villus height and crypt depth, plasma proteins, and electrolytes. Strains D, H, and M exhibited higher (P = 0.01) tibia ash concentration than B; E was intermediate and not different (P > 0.05) from any strain. Specifically, the tibia ash for B, D, H, SG 3, and E were 1.24, 1.44, 1.43, 1.49, and 1.39 g/kg BW, respectively. The B birds showed higher (P < 0.01) plasma concentrations of aspartate transaminase, creatine kinase, lactate dehydrogenase, and creatinine than SG strains. In conclusion, although B and some SG strains had lighter gastrointestinal tract indicative of energy efficiency, higher circulating plasma enzymes in B birds suggested impaired hepatic function. Moreover, lower tibia ash in B suggested disproportionate body mass relative to skeletal support.
Collapse
Affiliation(s)
| | - Victoria L Shouldice
- Department of Animal Biosciences, University of Guelph, Guelph N1G2W1, ON, Canada
| | - Stephanie Torrey
- Department of Animal Biosciences, University of Guelph, Guelph N1G2W1, ON, Canada
| | - Tina Widowski
- Department of Animal Biosciences, University of Guelph, Guelph N1G2W1, ON, Canada
| | - Elijah G Kiarie
- Department of Animal Biosciences, University of Guelph, Guelph N1G2W1, ON, Canada.
| |
Collapse
|
5
|
Hahn G, Judas M, Berk J. Forced locomotor activity improves walking ability of male turkeys and modifies carcass characteristics. Br Poult Sci 2020; 61:107-115. [PMID: 31902229 DOI: 10.1080/00071668.2019.1704684] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
Abstract
1. This trial investigated the effect of forced locomotor activity (training) on walking ability, leg posture, and growth performance, as well as carcass composition and meat quality in male fattening turkeys.2. A flock of 744 commercial turkeys was divided into three experimental groups, either without any training period (control), training from weeks 2 to 8 (short-term), or training from weeks 2 to 21 (long-term). All birds were slaughtered at an age of 21 weeks. To study the effect of short vs. long time lapse between shackling and stunning (suspension time), each training group was split into two halves that were hooked on the shackle for either 15 s or 3 min prior to stunning.3. Long-term physical training, compared to short-term or no training, resulted in better walking ability and in a lower percentage of leg malposition, as assessed at the end of fattening. No effect on final body weight was detected.4. In a subsample, the composition of 80 carcasses was determined by dissection. Long-term training favoured the percentage of the drumstick over that of the breast cut in comparison to the group without any training.5. Meat quality parameters were determined for breast muscle. The pH values 20 min post-mortem were reduced by long-term training, and the highest value was observed for a combination of no training with short suspension. After 24 h, pH values did not differ between experimental groups. The breast muscles were characterised as fast-glycolysing. Prolonged suspension time resulted in higher electrical conductivity after 24 h, and in higher a* values (redness).6. In conclusion, the study revealed that a long-term training period improved walking ability and leg posture of heavy male turkeys. Thus, training can contribute to the improvement of animal welfare in turkey husbandry. Meat quality variables of breast muscles were partially influenced by locomotor activity and suspension time.
Collapse
Affiliation(s)
- G Hahn
- Department of Safety and Quality of Meat, Max Rubner-Institut, Federal Research Institute of Nutrition and Food, Kulmbach, Germany
| | - M Judas
- Department of Safety and Quality of Meat, Max Rubner-Institut, Federal Research Institute of Nutrition and Food, Kulmbach, Germany
| | - J Berk
- Friedrich-Loeffler-Institut, Federal Research Institute for Animal Health, Institute of Animal Welfare and Animal Husbandry, Celle, Germany
| |
Collapse
|
6
|
Kremer JA, Robison CI, Karcher DM. Growth Dependent Changes in Pressure Sensing Walkway Data for Turkeys. Front Vet Sci 2018; 5:241. [PMID: 30356777 PMCID: PMC6189478 DOI: 10.3389/fvets.2018.00241] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2018] [Accepted: 09/12/2018] [Indexed: 12/12/2022] Open
Abstract
Genetic selection for rapidly growing turkeys has created an unfavorable consequence impacting the skeletal system resulting in long bone distortions. These distortions have resulted in locomotor problems, gait abnormalities, leg weakness, or lameness issues. These effects raise welfare concerns along with animal agriculture inefficiency in the form of lost product. The purpose was to determine baseline gait and force distribution in visibly unimpaired growing turkey hens. Hendrix commercial turkey hen poults (n = 100) were placed on pine wood shavings providing 0.78 m2 per bird with ad libitum access to feed and water at the MSU Poultry Farm. Fifty hens were randomly selected at 5 weeks and identified with a leg band to ensure longitudinal data collection. The turkeys were walked across a pressure-sensing walkway (PSW, Tekscan, Boston, MA) and weighed at 5, 6, 8, and 10 weeks of age. PSW collected data on gait length, gait time, step force and step length, and the statistics were analyzed with SAS. Both temporospatial data, including step time and step length, and kinetic data, including peak downward force, and vertical impulse, were recorded. Body weight increased linearly with age (P < 0.001), demonstrating a typical growth pattern. Gait cycle time and peak vertical force (PVF) all displayed no difference between right and left sides, indicating that the hens had no detectable gait abnormalities. Gait velocity increased with age (P = 0.02) suggesting hens' growth impacted their gait velocity. The gait cycle time (P < 0.01) did not correspond with age. PVF increased linearly with age (P < 0.01) from 6 weeks (2.23 kg) to 10 weeks of age (5.91 kg). PVF/kg body weight (P < 0.01) increased from 6 weeks of age (96.9% BW) to 8 weeks of age (106%BW). Overall, the birds were not lame and some data was influenced by the hen's adjustment to the materials or stage of growth; in contrast, some temporospatial data did not coincide with age. The PSW could be used to detect locomotor issues in commercially produced turkey hens providing another tool for assessing well-being.
Collapse
Affiliation(s)
- Jody A Kremer
- Department of Animal Science, Michigan State University, East Lansing, MI, United States
| | - Cara I Robison
- Department of Animal Science, Michigan State University, East Lansing, MI, United States
| | - Darrin M Karcher
- Department of Animal Sciences, Purdue University, West Lafayette, IN, United States
| |
Collapse
|
7
|
Oviedo-Rondón EO, Mente PL, Arellano C, Lascelles BDX, Mitchell A. Influence of gait on bone strength in turkeys with leg defects. Poult Sci 2018; 97:2621-2637. [PMID: 29688463 DOI: 10.3382/ps/pey142] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/26/2017] [Accepted: 03/24/2018] [Indexed: 11/20/2022] Open
Abstract
Leg problems have become more frequent in fast-growing turkeys. The objective of this study was to evaluate the effects of common leg defects on kinetic parameters of gait and biomechanical properties of bone. Nine hundred, day-old, male, Large White turkeys were raised in 48 floor pens. At 42 d of age, turkeys were divided into four categories of leg condition as determined by visual evaluation: Normal, Crooked toes, Shaky legs, and Valgus. Fifteen toms were selected from each group and trained to walk on a pressure sensitive walkway. Gait kinetic data were collected at 92, 115 and 144 d of age. At 145 d of age, turkeys were sacrificed and bones were collected and frozen until analysis. Morphological measurements of femur, tibia and tarsus-metatarsus were recorded. Bone mineral density (BMD) and content (BMC) were obtained using DEXA. Bone strength of tibias was evaluated using a four-point bending test and femurs with a torsion test. ANOVA was used to detect differences among groups, and Tukey's test used for mean separation. There were no differences in BW among different leg conditions. Gait parameters changed as turkeys aged, and age-group interactions were observed on peak vertical force (PVF), contact time, step length (SL) and bipedal cycle. No differences (P > 0.05) were detected in morphological measurements of femur or tibia. Relative asymmetry of femur length was lower (P < 0.05) in Normal and Valgus turkeys than in toms with Crooked toes. There were no differences (P > 0.05) among groups for femur BMD, BMC or strength. Tibia BMD and the area moment of inertia of turkeys with Crooked toes were lower (P < 0.05) than in toms with Valgus. With all four leg conditions, femur strength was positively correlated with PVF and negatively correlated with SL; BMD and BMC were correlated with tibia strength and gait kinetic parameters. In conclusion, only crooked toes caused consistent differences in gait patterns, bone properties and bone strength, but in general, gait kinetics was correlated with bone biomechanics in turkeys.
Collapse
Affiliation(s)
- E O Oviedo-Rondón
- Poultry Science, North Carolina State University, Raleigh, North Carolina, United States
| | - P L Mente
- Biomedical Engineering, North Carolina State University, Raleigh, North Carolina, United States
| | - C Arellano
- Statistics, North Carolina State University, Raleigh, North Carolina, United States
| | - B D X Lascelles
- Clinical Sciences, North Carolina State University College of Veterinary Medicine, Raleigh, North Carolina, United States
| | - A Mitchell
- USDA, ARS, ANRI, Beltsville, Maryland, United States
| |
Collapse
|