Automated dairy cattle lameness detection utilizing the power of artificial intelligence; current status quo and future research opportunities.

Lameness represents a major welfare and health problem for the dairy industry across all farming systems. Visual mobility scoring, although very useful, is labour-intensive and physically demanding, especially in large dairies, often leading to inconsistencies and inadequate uptake of the practice. Technological and computational advancements of artificial intelligence (AI) have led to the development of numerous automated solutions for livestock monitoring. The objective of this study was to review the automated systems using AI algorithms for lameness detection developed to-date. These systems rely on gait analysis using accelerometers, weighing platforms, acoustic analysis, radar sensors and computer vision technology. The lameness features of interest, the AI techniques used to process the data as well as the ground truth of lameness selected in each case are described. Measures of accuracy regarding correct classification of cows as lame or non-lame varied with most systems being able to classify cows with adequate reliability. Most studies used visual mobility scoring as the ground truth for comparison with only a few studies using the presence of specific foot pathologies. Given the capabilities of AI, and the benefits of early treatment of lameness, longitudinal studies to identify gait abnormalities using automated scores related to the early developmental stages of different foot pathologies are required. Farm-specific optimal thresholds for early intervention should then be identified to ameliorate cow health and welfare but also minimise unnecessary inspections.

Objective comparison of a sit to stand test to the walk test for the identification of unilateral lameness caused by cranial cruciate ligament disease in dogs.

OBJECTIVE: The purpose of this study was to evaluate a sit to stand test with the walk test for the identification of unilateral cranial cruciate ligament rupture in dogs. MATERIALS AND METHODS: Peak vertical force and vertical impulse were measured on a pressure-sensitive walkway, during a sit to stand test and walk test, and in 10 dogs with unilateral cranial cruciate ligament rupture and 18 non-lame dogs. Data collected were used to calculate symmetry indices (SI) of ipsilateral and contralateral hindlimbs (HL), diagonal limb pairs (DLP) and ipsilateral limb pairs (ILP). RESULTS: The symmetry indices of peak vertical force of HL during the walk test and sit to stand test were 100% and 90% sensitive for discriminating lame and non-lame dogs respectively. The symmetry indices of vertical impulse of HLs during the walk test and sit to stand test were 100% and 50% sensitive for discriminating lame and non-lame dogs respectively. Analysis of ipsilateral and diagonal limb pairs did not improve the discrimination in either test. The time taken to collect data from the sit to stand test data was shorter than for the walk test. CLINICAL SIGNIFICANCE: Whilst the sit to stand test required a shorter time for collection of data than the walk test, it did not accurately identify all dogs with lameness associated with CCLR, and thus has relatively limited clinical utility in its tested form.

Retrospective evaluation and review of approaches for nonspecific lameness in dogs presented to an emergency service (2013-2014): 134 cases.

OBJECTIVE: This retrospective study aimed to characterize and evaluate the emergency approach, diagnosis, management, treatment, and follow-up of nonspecific canine lameness cases. DESIGN: Retrospective case series from September 25, 2013 to September 25, 2014. SETTING: The study was conducted at an urban university teaching hospital. ANIMALS: A consecutive sample of dogs presenting to the emergency service with nonspecific lameness in the designated timeframe was used to identify 134 cases. Owners were contacted to participate in the follow-up survey; dogs that died prior to data collection were excluded from the survey. Medical records were reviewed for lameness localization, etiology of lameness, diagnostics obtained, medications prescribed, and owner recommendations. INTERVENTIONS: Based on review of the medical records, the lameness localization, presumptive source of lameness (joint, soft tissue, neurological, or bone), diagnostics obtained, medications prescribed, and owner recommendations were recorded. Survey data included duration of lameness, perceived response to treatment, and activity level. MEASUREMENTS AND MAIN RESULTS: Definitive diagnoses were not assigned in 88.8% of lameness cases. A presumptive diagnosis of soft tissue injury was assigned in 45.3% of cases. Single limb lameness was more prevalent than multiple limb lameness. Owners whose dogs were treated with medication were significantly more likely to report that the lameness resolved (P = 0.049). Dogs with injury localized to ≥1 of the joints were significantly less likely to have resolution of lameness (P = 0.037). Treatment recommendations were predominantly pain control and activity restriction. CONCLUSIONS: Nonspecific lameness represents approximately 4% of canine urban emergency cases. Highlighting the points of clinical care considerations in understanding the etiology of lameness in dogs represents an opportunity for improved patient care and growth in emergency referral and follow-up.

Allogeneic chondrogenic-induced mesenchymal stem cells for the treatment of tarsometatarsal lameness in horses.

OBJECTIVE: To assess the efficacy of commercial intra-articular blood-derived allogeneic-induced mesenchymal stem cells (CIMSCs) to treat tarsometatarsal lameness in horses. STUDY DESIGN: This was a retrospective cohort study. ANIMALS: Records from 167 adult light breed horses with bilateral tarsometatarsal lameness. METHODS: Horses with tarsometatarsal lameness were retrospectively selected from medical records. Diagnosis followed subjective graded lameness assessment before and after intra-articular analgesia, with graded radiographic tarsal examination. Horses were excluded if they were diagnosed or treated for any other concurrent lameness conditions during the study. Time to last follow-up and time of recurrence of lameness was recorded at veterinary re-assessment. RESULTS: A total of 67 horses were recruited to the CIMSC-treated group and 100 to the corticosteroid (CS)-treated group. Median age was 9 years, with no difference in signalment, use or radiographic grade between groups. First re-examination was 38 days (95% CI: 38-49), with no difference between groups, CIMSC 42 (35-45), control 34 (25-42). Median follow-up was 438 days for CIMSC, 546 for controls. Symptoms of lameness recurred in 86/100 controls compared to 17/67 (25%) CIMSC. Median time to lameness recurring in CIMSC was 336 days (95% CI: 239-400), control 90 days (95% CI: 80-108), p < .0001. Cox proportional hazard ratio for treatment was 8.35, 95% CI: 4.67 to 14.92, p < .0001. CONCLUSIONS: Lameness was abolished in all treated horses. It recurred significantly less often, and later, in CIMSC-treated horses. CLINICAL SIGNIFICANCE: Intra-articular CIMSC treatment results in prolonged soundness in horses with tarsometatarsal lameness.

Sensitivity and specificity of mobility scoring for the detection of foot lesions in pasture-based Irish dairy cows.

Lameness is an important production disease in dairy cows worldwide and has detrimental effects on cows' welfare, production, and reproductive performance, thus affecting the sustainability of dairy farming. Timely and effective detection of lameness allows for effective treatment, minimizing progression of disease, and maximizing the prognosis of recovery. Mobility scoring (MSc) is a 4 point (0-3) visual lameness scoring system that is the industry standard in several countries. However, few studies have examined the sensitivity (Se) and specificity (Sp) of MSc to detect foot lesions. The aim of this observational study was to determine the Se and Sp of MSc to detect foot lesions in dairy cattle in a pasture-based system. Five hundred ninety-five primi- and multiparous cows were randomly selected from 12 commercial Irish dairy farms and recruited for the study. Recruited cows were mobility scored and passed through a foot-paring crate where all 4 feet were lifted for examination. The team recorded the anatomical location and severity of any foot lesions present based on appearance only. Then, based on the type and severity of the lesions present, cows were classified according to 3 case definitions case definition 1: Any lesion present; case definition 2: Moderate lesions present (excluding minor lesions expected to have a low probability of affecting gait); and case definition 3: Severe lesions present (only including lesions most likely to result in a detectable gait abnormality). Sensitivity and Sp of MSc was calculated based on a threshold of MSc ≥2, defined as impaired (MSc = 2) or severely impaired (MSc = 3) mobility for each of the 3 case definitions, at the overall level and disaggregated by parity. The overall cow-level lesion prevalence based on the case definition 1 was 0.54 with significant between-herd variation. The overall Se and Sp of MSc for the detection of foot lesions were 0.18 and 0.96, 0.35 and 0.94, 0.43 and 0.94 for the case definitions 1, 2, and 3, respectively. Our findings showed poor Se, but high Sp of MSc for the detection of cows with foot lesions in a pasture-based system.

DEVELOPMENT AND EVALUATION OF A STANDARDIZED SYSTEM FOR THE ASSESSMENT OF LOCOMOTOR HEALTH IN ELEPHANTS UNDER HUMAN CARE.

Although lameness is a common problem in elephants (Asian elephant [Elephas maximus] and African elephants Loxodonta africana and Loxodonta cyclotis) under human care, there has not been a standardized lameness assessment system to date. This study developed and evaluated a standardized system for the assessment of locomotion in elephants under human care regardless of husbandry system. In total, 72 elephants out of a possible 73 in the United Kingdom and Ireland were filmed from behind, from in front, and from both sides. Using a questionnaire and a select panel of elephant specialists, a zoo veterinarian, and a locomotion expert, a numerical rating scoring (NRS) system was proposed. Locomotion was scored on a 4-point scale with numerical values 0-4 corresponding to specific criteria as follows: 0 = clinically sound, 1 = stiffness, 2 = abnormal tracking, and 4 = reluctance to bear weight. The intra- and interobserver repeatability of five veterinary surgeons using this system was determined and compared with a visual analog scale (VAS) expressed as a 100-mm line. Overall intraobserver reliability was moderate (Cohen's kappa [κ] = 0.676) and interobserver reliability was fair (κ = 0.37) for the presence of lameness. Interobserver agreement improved from the first scoring to second scoring from slight agreement to fair agreement for stiffness and reluctance to bear weight. Abnormal tracking had moderate intraobserver agreement for both scoring sessions. There were wide widths of agreement for the VAS interobserver (67 mm); however, they were narrower for the intraobserver (33 mm). The developed NRS can be used on freely moving elephants to evaluate elephant locomotion, regardless of husbandry methods, and has been shown to be more reliable than a VAS.

Comparing Inertial Measurement Units to Markerless Video Analysis for Movement Symmetry in Quarter Horses.

BACKGROUND: With an increasing number of systems for quantifying lameness-related movement asymmetry, between-system comparisons under non-laboratory conditions are important for multi-centre or referral-level studies. This study compares an artificial intelligence video app to a validated inertial measurement unit (IMU) gait analysis system in a specific group of horses. METHODS: Twenty-two reining Quarter horses were equipped with nine body-mounted IMUs while being videoed with a smartphone app. Both systems quantified head and pelvic movement symmetry during in-hand trot (hard/soft ground) and on the lunge (left/right rein, soft ground). Proportional limits of agreement (pLoA) were established. RESULTS: Widths of pLoA were larger for head movement (29% to 50% in-hand; 22% to 38% on lunge) than for pelvic movement (13% to 24% in-hand; 14% to 24% on lunge). CONCLUSION: The between-system pLoAs exceed current "lameness thresholds" aimed at identifying the affected limb(s) in lame horses. They also exceed published limits of agreement for stride-matched data but are similar to repeatability values and "lameness thresholds" from "non-lame" horses. This is encouraging for multi-centre studies and referral-level veterinary practice. The narrower pLoA values for pelvic movement asymmetry are particularly encouraging, given the difficulty of grading hind limb lameness "by eye".

Normal variation in pelvic roll motion pattern during straight-line trot in hand in warmblood horses.

In horses, hip hike asymmetry, i.e. left-right difference in hip upwards movement during hind limb protraction in trot, is a crucial lameness sign. Vertical hip movements are complex, influenced by both pelvic roll and pelvic vertical motion. Veterinarians find it challenging to identify low-grade lameness, and knowledge of normal variation is a prerequisite for discerning abnormalities. This study, which included 100 clinically sound Warmblood horses, aimed to describe normal variation in pelvic roll stride patterns. Data were collected during straight-line trot in hand using optical motion capture. Stride-segmented pelvic roll data, normalised with respect to time (0-100% of the stride) and amplitude (± 0.5 of horse average stride range of motion), were modelled as a linear combination of sine and cosine curves. A sine curve with one period per stride and a cosine curve with three periods per stride explained the largest proportions of roll motion: model estimate 0.335 (p < 0.01) and 0.138 (p < 0.01), respectively. Using finite mixture models, the horses could be separated into three groups sharing common pelvic roll characteristics. In conclusion, pelvic roll motion in trot follows a similar basic pattern in most horses, yet there is significant individual variation in the relative prominence of the most characteristic features.

Inertial Sensor Technologies-Their Role in Equine Gait Analysis, a Review.

Objective gait analysis provides valuable information about the locomotion characteristics of sound and lame horses. Due to their high accuracy and sensitivity, inertial measurement units (IMUs) have gained popularity over objective measurement techniques such as force plates and optical motion capture (OMC) systems. IMUs are wearable sensors that measure acceleration forces and angular velocities, providing the possibility of a non-invasive and continuous monitoring of horse gait during walk, trot, or canter during field conditions. The present narrative review aimed to describe the inertial sensor technologies and summarize their role in equine gait analysis. The literature was searched using general terms related to inertial sensors and their applicability, gait analysis methods, and lameness evaluation. The efficacy and performance of IMU-based methods for the assessment of normal gait, detection of lameness, analysis of horse-rider interaction, as well as the influence of sedative drugs, are discussed and compared with force plate and OMC techniques. The collected evidence indicated that IMU-based sensor systems can monitor and quantify horse locomotion with high accuracy and precision, having comparable or superior performance to objective measurement techniques. IMUs are reliable tools for the evaluation of horse-rider interactions. The observed efficacy and performance of IMU systems in equine gait analysis warrant further research in this population, with special focus on the potential implementation of novel techniques described and validated in humans.

Predicting lameness in dairy cattle using untargeted liquid chromatography-mass spectrometry-based metabolomics and machine learning.

Lameness in dairy cattle is a highly prevalent condition that impacts on the health and welfare of dairy cows. Prompt detection and implementation of effective treatment is important for managing lameness. However, major limitations are associated with visual assessment of lameness, which is the most commonly used method to detect lameness. The aims of this study were to investigate the use of metabolomics and machine learning to develop novel methods to detect lameness. Untargeted metabolomics using liquid chromatography-mass spectrometry (LC-MS) alongside machine learning models and a stability selection method were utilized to evaluate the predictive accuracy of differences in the metabolomics profile of first-lactation dairy cows before (during the transition period) and at the time of lameness (based on visual assessment using the 0-3 scale of the Agriculture and Horticulture Development Board). Urine samples were collected from 2 cohorts of dairy heifers and stored at -86°C before analysis using LC-MS. Cohort 1 (n = 90) cows were recruited as current first-lactation cows with weekly mobility scores recorded over a 4-mo timeframe, from which newly lame and nonlame cows were identified. Cohort 2 (n = 30) cows were recruited within 3 wk before calving, and lameness events (based on mobility score) were recorded through lactation until a minimum of 70 d in milk (DIM). All cows were matched paired by DIM ± 14 d. The median DIM at lameness identification was 187.5 and 28.5 for cohort 1 and 2, respectively. The best performing machine learning models predicted lameness at the time of lameness with an accuracy of between 81 and 82%. Using stability selection, the prediction accuracy at the time of lameness was 80 to 81%. For samples collected before and after calving, the best performing machine learning model predicted lameness with an accuracy of 71 and 75%, respectively. The findings from this study demonstrate that untargeted LC-MS profiling combined with machine learning methods can be used to predict lameness as early as before calving and before observable changes in gait in first-lactation dairy cows. The methods also provide accuracies for detecting lameness at the time of observable changes in gait of up to 82%. The findings demonstrate that these methods could provide substantial advancements in the early prediction and prevention of lameness risk. Further external validation work is required to confirm these findings are generalizable; however, this study provides the basis from which future work can be conducted.

Pressure sensing mat as an objective and sensitive tool for the evaluation of lameness in rabbits.

In orthopaedic research, the analysis of the gait pattern is an often-used evaluation method. It allows an assessment of changes in motion sequence and pain level during postoperative follow up periods. Visual assessments are highly subjective and dependent on the circumstances. Particular challenge in rabbits is their hopping gait pattern. The aim of the present study was to establish a more objective and sensitive lameness evaluation using a pressure sensing mat. Twelve NZW rabbits were implemented in the study. They got an artificial anterior cruciate ligament transection of the right knee in connection with an experimental study, which investigated PTOA treatment. Rabbits were examined by a visual lameness score. Additionally, load of the hindlimbs was measured by the use of a pressure sensing mat and a video was recorded. Peak pressure and time force integral, defined as cumulated integral of all sensors associated to a hind paw, were evaluated. Preoperative data were collected on three independent days. As postoperative measurement time points, week 1 and week 12 after surgery were chosen. The subjective visual scoring was compared to the objective data of the pressure sensing mat. Following the visual score, lameness in week one was mild to moderate. In week twelve, rabbits were evaluated as lame free bar one. Contrary, following the values of the sensor mat, lameness in week one appeared to be more pronounced and almost all rabbits still showed low-grade lameness in week twelve. Consequently, the pressure sensing mat is more sensitive than the visual score and captures the grade of lameness much more accurately. For specific orthopaedic issues, where subtle differences in lameness are important to detect, the used system is a good supplementary evaluation method.

Crowd sourcing remote comparative lameness assessments for dairy cattle.

Lameness assessments are rarely conducted routinely on dairy farms and when completed typically underestimate lameness prevalence, hampering early diagnosis and treatment. A well-known feature of many perceptual tasks is that relative assessments are more accurate than absolute assessments, suggesting that creating methods that allow for the relative scoring of which cow is more lame will allow for reliable lameness assessments. Here we developed and tested a remote comparative lameness assessment method: we recruited nonexperienced crowd workers via an online platform and asked them to watch 2 videos side-by-side, each showing a cow walking, and to identify which cow was more lame and by how much (on a scale of -3 to 3). We created 11 tasks, each with 10 video pairs for comparison, and recruited 50 workers per task. All tasks were also completed by 5 experienced cattle lameness assessors. We evaluated data filtering and clustering methods based on worker responses and determined the agreement among workers, among experienced assessors, and between these groups. A moderate to high interobserver reliability was observed (intraclass correlation coefficient, ICC = 0.46 to 0.77) for crowd workers and agreement was high among the experienced assessors (ICC = 0.87). Average crowd-worker responses showed excellent agreement with the average of experienced assessor responses (ICC = 0.89 to 0.91), regardless of data processing method. To investigate if we could use fewer workers per task while still retaining high agreement with experienced assessors, we randomly subsampled 2 to 43 (1 less than the minimum number of workers retained per task after data cleaning) workers from each task. The agreement with experienced assessors increased substantially as we increased the number of workers from 2 to 10, but little increase was observed after 10 or more workers were used (ICC > 0.80). The proposed method provides a fast and cost-effective way to assess lameness in commercial herds. In addition, this method allows for large-scale data collection useful for training computer vision algorithms that could be used to automate lameness assessments on farm.

Comparing video examinations with physical clinical examinations using finishing pigs with umbilical outpouchings as a model.

BACKGROUND: Veterinary telemedicine has only been adopted to some degree. One aspect that needs to be evaluated is clinical examinations using video. The objective of this study was to evaluate agreement between a traditional physical clinical examination and a clinical examination using recorded video using finishing pigs with umbilical outpouchings (umbilical hernias, cysts, and abscesses) as the study unit. A total of 102 finisher pigs with umbilical outpouchings were clinically examined and recorded on video. Four experienced pig veterinarians were allowed to examine each pig for approximately 10 min and were individually asked to fill out a predesigned clinical record. Approximately 1 month after the physical examinations, the veterinarians individually reexamined all 102 pigs in a blinded manner, utilizing the video recordings and filling in a predesigned clinical record. RESULTS: For all measurements using a ruler, a high Pearson correlation coefficient was observed between physical and video examinations (range 0.69-0.95). In comparison, the visual bodyweight estimation had a lower Pearson correlation coefficient (range 0.57-0.64). Substantial to almost perfect agreement was observed between the physical and video examinations for abnormal weight distribution on any leg, restricted gait movements, lameness, signs of pain, fitness for transportation, presence of wounds, and categorization of the number of wounds > 4 cm2 on the umbilical outpouching (mean Kappa range 0.67-0.87). Fair agreement was observed for the presence of perineal soiling, ear wounds, pendulation of umbilical outpouching, umbilical outpouching touching the legs, skin not movable over the umbilical outpouching, and umbilical outpouching wound characteristics: type, presence of crusts, active bleeding, thick wound edges, connective tissue (mean Kappa range 0.21-0.40). Slight agreement was observed for umbilical outpouching characteristics: shape, macroscopic vascularization of the skin covering the outpouching, and the presence of scars, excoriations, and fistulas (mean Kappa range 0.10-0.20). Poor agreement was observed for the presence of granulation tissue (mean Kappa = - 0.05). CONCLUSIONS: The agreement between a physical clinical examination and a clinical examination using recorded video of the same pig varies from poor to almost perfect, depending on the clinical sign and the executing veterinarian.

Automated pose estimation reveals walking characteristics associated with lameness in broilers.

Walking ability of broilers can be improved by selective breeding, but large-scale phenotypic records are required. Currently, gait of individual broilers is scored by trained experts, however, precision phenotyping tools could offer a more objective and high-throughput alternative. We studied whether specific walking characteristics determined through pose estimation are linked to gait in broilers. We filmed male broilers from behind, walking through a 3 m × 0.4 m (length × width) corridor one by one, at 3 time points during their lifetime (at 14, 21, and 33 d of age). We used a deep learning model, developed in DeepLabCut, to detect and track 8 keypoints (head, neck, left and right knees, hocks, and feet) of broilers in the recorded videos. Using the keypoints of the legs, 6 pose features were quantified during the double support phase of walking, and 1 pose feature was quantified during steps, at maximum leg lift. Gait was scored on a scale from 0 to 5 by 4 experts, using the videos recorded on d 33, and the broilers were further classified as having either good gait (mean gait score ≤2) or suboptimal gait (mean gait score >2). The relationship of pose features on d 33 with gait was analyzed using the data of 84 broilers (good gait: 57.1%, suboptimal gait: 42.9%). Birds with suboptimal gait had sharper hock joint lateral angles and lower hock-feet distance ratios during double support on d 33, on average. During steps, relative step height was lower in birds with suboptimal gait. Step height and hock-feet distance ratio showed the largest mean deviations in broilers with suboptimal gait compared to those with good gait. We demonstrate that pose estimation can be used to assess walking characteristics during a large part of the productive life of broilers, and to phenotype and monitor broiler gait. These insights can be used to understand differences in the walking patterns of lame broilers, and to build more sophisticated gait prediction models.

An Unusual Cause of Femoral Nerve Paresis in a Horse: Disseminated B Cell Lymphoma With Plasmacytoid Differentiation and Direct Neuronal Invasion.

A 21-year-old Quarter Horse mare presented with a chronic, progressively worsening left pelvic limb lameness of 3 weeks duration. The initial examination identified a consistent lameness at a walk. Neurological examination showed sensory and gait abnormalities consistent with left femoral nerve dysfunction. The horse minimally advanced the leg cranially and had a shortened stride length at the walk. During the stance phase, the heels of the left hind foot did not contact the ground and the horse quickly took weight off of the limb. Diagnostic imaging (ultrasound and nuclear scintigraphy) examinations did not reveal a cause. Severe lymphocytosis was identified on complete blood cell count (69,600 cells /uL; reference range: 1,500-4,000 cells/uL), suggestive of lymphoma. Postmortem examination revealed focal swelling of the left femoral nerve. Multiple masses were found in the stomach, large colon, adrenal gland, mesentery, heart, and meninges. The entire left pelvic limb was dissected and did not reveal other causes of the gait deficit. Histologic evaluation of the left femoral nerve revealed disseminated intermediate cell size B cell lymphoma, with an immunophenotype suggestive of plasmacytoid differentiation. These lymphocytes infiltrated the femoral nerve at the location of the focal nerve swelling, in addition to other peripheral nerves. This case highlights a horse with an atypical diagnosis of femoral nerve paresis caused by direct neoplastic lymphocyte infiltration, deriving from disseminated B cell lymphoma with plasmacytoid differentiation (neurolymphomatosis). Though rare, disseminated lymphoma with direct nerve infiltration should be considered in horses with peripheral neuropathies.

Retrospective evaluation of the causes and distribution of lameness in beef and dairy cattle evaluated by ambulatory and in-house clinical services at a North American veterinary teaching hospital.

OBJECTIVE: To describe the causes and distribution of lameness in beef and dairy cattle presenting to either a primary care ambulatory or in-house clinical service at a veterinary teaching hospital. SAMPLE: This retrospective clinical case study was conducted by reviewing hospital admissions of beef and dairy cattle seen by in-house or ambulatory clinicians at a veterinary teaching hospital from 2001 to 2021. PROCEDURES: Final diagnosis was recorded and, when available, the affected limb, whether a lesion was localized to the digit, and the affected claw were also recorded. Data were stratified by location of initial evaluation (ambulatory vs in hospital), period of presentation, production class, age, sex, and whether the final diagnosis was infectious or noninfectious. RESULTS: Overall, 2,220 animals met criteria for inclusion in the study. The most common diagnoses were noninfectious in nature and affected a hind limb more often than a forelimb. More than 82% of all cattle had lameness localized to the digit, with the lateral claw being affected more than 80% of the time. CLINICAL RELEVANCE: Lameness is an important concern from both a humane and economic standpoint. The results of this study will help with the diagnosis and prevention of lameness in beef and dairy cattle of different ages and production classes.

Deep learning pose estimation for multi-cattle lameness detection.

The objective of this study was to develop a fully automated multiple-cow real-time lameness detection system using a deep learning approach for cattle detection and pose estimation that could be deployed across dairy farms. Utilising computer vision and deep learning, the system can analyse simultaneously both the posture and gait of each cow within a camera field of view to a very high degree of accuracy (94-100%). Twenty-five video sequences containing 250 cows in varying degrees of lameness were recorded and independently scored by three accredited Agriculture and Horticulture Development Board (AHDB) mobility scorers using the AHDB dairy mobility scoring system to provide ground truth lameness data. These observers showed significant inter-observer reliability. Video sequences were broken down into their constituent frames and with a further 500 images downloaded from google, annotated with 15 anatomical points for each animal. A modified Mask-RCNN estimated the pose of each cow to output 5 key-points to determine back arching and 2 key-points to determine head position. Using the SORT (simple, online, and real-time tracking) algorithm, cows were tracked as they move through frames of the video sequence (i.e., in moving animals). All the features were combined using the CatBoost gradient boosting algorithm with accuracy being determined using threefold cross-validation including recursive feature elimination. Precision was assessed using Cohen's kappa coefficient and assessments of precision and recall. This methodology was applied to cows with varying degrees of lameness (according to accredited scoring, n = 3) and demonstrated that some characteristics directly associated with lameness could be monitored simultaneously. By combining the algorithm results over time, more robust evaluation of individual cow lameness was obtained. The model showed high performance for predicting and matching the ground truth lameness data with the outputs of the algorithm. Overall, threefold lameness detection accuracy of 100% and a lameness severity classification accuracy of 94% respectively was achieved with a high degree of precision (Cohen's kappa = 0.8782, precision = 0.8650 and recall = 0.9209).

Comparison of Asymmetry During Trot In-Hand With Evaluations of Discomfort and Pain in Horses While Exercised.

Traditional visual lameness assessment is subjective. Ethograms have been developed for evaluating pain and objective sensors to detect lameness. Heart rate (HR) and heart rate variability (HRV) have been used to evaluate stress and pain. The aim of our study was to compare subjective and behavioral lameness scores, a sensor system measuring movement asymmetry, HR, and HRV. We hypothesized that these measures would show related trends. In 30 horses, an inertial sensor system was used to measure movement asymmetries during trot in-hand. A horse was categorized as sound if each asymmetry was less than 10 mm. We recorded riding to observe lameness and evaluate behavior. Heart rate and RR intervals were measured. Root mean squares of successive RR intervals (RMSSD) were calculated. Five horses were categorized as sound and 25 horses as lame by the inertial sensor system. No significant differences were detected between sound and lame horses in the ethogram, subjective lameness score, HR, and RMSSD. Overall asymmetry, ethogram, and lameness score had no significant correlation with each other, whereas overall asymmetry and ethogram correlated significantly with HR and RMSSD during certain phases of the ridden exercise. The main limitation of our study was the small number of sound horses detected by the inertial sensor system. The association between gait asymmetry and HRV suggests that the more gait asymmetry a horse shows during trot in-hand, the more pain or discomfort it probably experiences when ridden with a higher intensity. The threshold for lameness used by the inertial sensor system may require further evaluation.

Cost of lameness in dairy herds: An integrated bioeconomic modeling approach.

Foot disorders are costly health disorders in dairy farms, and their prevalence is related to several factors such as breed, nutrition, and farmer's management strategy. Very few modeling approaches have considered the dynamics of foot disorders and their interaction with farm management strategies within a holistic farm simulation model. The aim of this study was to estimate the cost of foot disorders in dairy herds by simulating strategies for managing lameness. A dynamic and stochastic simulation model (DairyHealthSim) was used to simulate the herd dynamics, reproduction management, and health events. A specific module was built for lameness and related herd-level management strategies. Foot disorder occurrences were simulated with a base risk for each etiology [digital dermatitis (DD), interdigital dermatitis, interdigital phlegmon, sole ulcer (SU), white line disease (WLD)]. Two state machines were implemented in the model: the first was related to the disease-induced lameness score (from 1 to 5), and the second concerned DD-state transitions. A total of 880 simulations were run to represent the combination of the following 5 scenarios: (1) housing (concrete vs. textured), (2) hygiene (2 different scraping frequencies), (3) the existence of preventive trimming, (4) different thresholds of DD prevalence detected and from which a collective footbath is applied to treat DD, and (5) farmer's ability to detect lameness (detection rate). Housing, hygiene, and trimming scenarios were associated with risk factors applied for each foot disorder etiologies. The footbath and lameness detection scenarios both determined the treatment setup and the policy of herd observance. The economic evaluation outcome was the gross margin per year. A linear regression model was run to estimate the cost per lame cow (lameness score ≥3), per case of DD and per week of a cow's medium lameness duration. The bioeconomic model reproduced a lameness prevalence varying from 26 to 98% depending on the management scenario, demonstrating a high capacity of the model to represent the diversity of the field situations. Digital dermatitis represented half of the total lameness cases, followed by interdigital dermatitis (28%), SU (19%), WLD (13%), and interdigital phlegmon (4%). The housing scenarios dramatically influenced the prevalence of SU and WLD, whereas scraping frequency and threshold for footbath application mainly determined the presence of DD. Interestingly, the results showed that preventive trimming allowed a better reduction in lameness prevalence than spending time on early detection. Scraping frequency was highly associated with DD occurrence, especially with a textured floor. The regression showed that costs were homogeneous (i.e., did not change with lameness prevalence; marginal cost equals average cost). A lame cow and a DD-affected cow cost €307.50 ± 8.40 (SD) and €391.80 ± 10.0 per year on average, respectively. The results also showed a cost of €12.10 ± 0.36 per week-cow lameness. The present estimation is the first to account for interactions between etiologies and for the complex DD dynamics with all the M-stage transitions, bringing a high level of accuracy to the results.