Lameness Detection Research Articles

Vertical back movement of cows during locomotion: detecting lameness with a simple image processing technique.

This research paper proposes a simple image processing technique for automatic lameness detection in dairy cows under farm conditions. Seventy-five cows were selected from a dairy farm and visually assessed for a reference/real lameness score (RLS) as they left the milking parlor, while simultaneously being video-captured. The method employed a designated walking path and video recordings processed through image analysis to derive a new computerized automatic lameness score (ALDS) based on calculated factors from back arch posture. The proposed automatic lameness detection system was calibrated using 12 cows, and the remaining 63 were used to evaluate the diagnostic characteristics of the ALDS. The agreement and correlation between ALDS and RLS were investigated. ALDS demonstrated high diagnostic accuracy with 100% sensitivity and specificity and was found to be 100% accurate with a perfect agreement (ρc = 1) and strong correlation (r = 1, P < 0.001) for lameness detection in binary scores (lame/non-lame). Moreover, the ALDS had a strong agreement (ρc = 0.885) and was highly correlated (r = 0.840; 0.796-1.000 95% confidence interval, P < 0.001) with RLS in ordinal scores (lameness severity; LS1 to LS5). Our findings suggest that the proposed method has the potential to compete with vision-based lameness detection methods in dairy cows in farm conditions.

Internet of things infrared imaging device for assessing lameness in racehorses

Lameness is a clinical condition that heavily affects racehorses. As a result, their competitive performance is dramatically deteriorated and side effects such as changes in feeding patterns may manifest. Within this work we have presented a developed portable Internet of Things (IoT) infrared imaging device, whose application is aimed towards on-site farm level detection of lameness in equine. Additionally we have presented an in-debt review of the causes of lameness, the underlying biological changes that it induces, its influence over tissue thermal patterns and how exercise affects a racehorse's temperature profile.

Improving Lameness Detection in Cows: A Machine Learning Algorithm Application

The deployment of diverse data-generating technologies in livestock farming holds the promise of early disease detection and improved animal well-being. In this paper, we combine routinely collected dairy farm and herd data with weather and high frequency sensor data from 6 farms to predict new lameness events in various future periods, spanning from the following day to 3 weeks. A Random Forest classifier, using input features selected by the Boruta Algorithm, was used for the prediction task; effects of individual features were further assessed using partial dependence plots. We achieve precision scores of up to 93% when predicting lameness for the next 3 weeks and when using information from the last 3 weeks, combined with a balanced accuracy of 79%. Removing sensor data results have tendency to reduce the precision for predictions, especially when using information from the last one,2 or 3 weeks. Moving to a larger data set (without sensor data) of 44 farms keeps the similar balanced accuracy but reduces precision by more than 30%, revealing a substantial a trade-off in model quality between false positives (false lameness alerts) and false negatives (missed lameness events). Sensor data holds promise to further improve the precision of these models, but can be partially compensated by high resolution data from other systems, such as automated milking systems.

AI-enhanced real-time cattle identification system through tracking across various environments

Video-based monitoring is essential nowadays in cattle farm management systems for automated evaluation of cow health, encompassing body condition scores, lameness detection, calving events, and other factors. In order to efficiently monitor the well-being of each individual animal, it is vital to automatically identify them in real time. Although there are various techniques available for cattle identification, a significant number of them depend on radio frequency or visible ear tags, which are prone to being lost or damaged. This can result in financial difficulties for farmers. Therefore, this paper presents a novel method for tracking and identifying the cattle with an RGB image-based camera. As a first step, to detect the cattle in the video, we employ the YOLOv8 (You Only Look Once) model. The sample data contains the raw video that was recorded with the cameras that were installed at above from the designated lane used by cattle after the milk production process and above from the rotating milking parlor. As a second step, the detected cattle are continuously tracked and assigned unique local IDs. The tracked images of each individual cattle are then stored in individual folders according to their respective IDs, facilitating the identification process. The images of each folder will be the features which are extracted using a feature extractor called VGG (Visual Geometry Group). After feature extraction task, as a final step, the SVM (Support Vector Machine) identifier for cattle identification will be used to get the identified ID of the cattle. The final ID of a cattle is determined based on the maximum identified output ID from the tracked images of that particular animal. The outcomes of this paper will act as proof of the concept for the use of combining VGG features with SVM is an effective and promising approach for an automatic cattle identification system

Kinematic changes in dairy cows with induced hindlimb lameness: transferring methodology from the field of equine biomechanics

Lameness is a common issue on dairy farms, with serious implications for economy and animal welfare. Affected animals may be overlooked until their condition becomes severe. Thus, improved lameness detection methods are needed. In this study, we describe kinematic changes in dairy cows with induced, mild to moderate hindlimb lameness in detail using a “whole-body approach”. Thereby, we aimed to identify explicable features to discriminate between lame and non-lame animals for use in future automated surveillance systems. For this purpose, we induced a mild to moderate and fully reversible hindlimb lameness in 16 dairy cows. We obtained 41 straight-line walk measurements (containing > 3 000 stride cycles) using 11 inertial measurement units attached to predefined locations on the cows’ upper body and limbs. One baseline and ≥ 1 induction measurement(s) were obtained from each cow. Thirty-one spatial and temporal parameters related to limb movement and inter-limb coordination, upper body vertical displacement symmetry and range of motion (ROMz), as well as pelvic pitch and roll, were calculated on a stride-by-stride basis. For upper body locations, vertical within-stride movement asymmetry was investigated both by calculating within-stride differences between local extrema, and by a signal decomposition approach. For each parameter, the baseline condition was compared with induction condition in linear mixed−effect models, while accounting for stride duration. Significant difference between baseline and induction condition was seen for 23 out of 31 kinematic parameters. Lameness induction was associated with decreased maximum protraction (−5.8%) and retraction (−3.7%) angles of the distal portion of the induced/non-induced limb respectively. Diagonal and lateral dissociation of foot placement (ratio of stride duration) involving the non-induced limb decreased by 8.8 and 4.4%, while diagonal dissociation involving the induced limb increased by 7.7%. Increased within-stride vertical displacement asymmetry of the poll, neck, withers, thoracolumbar junction (back) and tubera sacrale (TS) were seen. This was most notable for the back and poll, where a 40 and 24% increase of the first harmonic amplitude (asymmetric component) and 27 and 14% decrease of the second harmonic amplitude (symmetric component) of vertical displacement were seen. ROMz increased in all these landmarks except for TS. Changes in pelvic roll main components, but not in the range of motion of either pitch or roll angle per stride, were seen. Thus, we identified several kinematic features which may be used in future surveillance systems. Further studies are needed to determine their usefulness in realistic conditions, and to implement methods on farms.

Descriptive evaluation of a camera-based dairy cattle lameness detection technology

Lameness in dairy cattle is a clinical sign of impaired locomotion, mainly caused by painful foot lesions, compromising the US dairy industry's economic, environmental, and social sustainability goals. Combining technology and on farm data may be a more precise and less labor-intensive lameness detection tool, particularly for early detection. The objective of this observational study was to describe the association between average weekly autonomous camera-based (AUTO) locomotion scores and hoof trimming (HT) data. The AUTO data were collected from 3 farms from April 2022 to March 2023. Historical farm HT data were collected from March 2016 to March 2023 and used to determine cow lesion history and date of HT event. The HT events were categorized as a regular HT (TRIM; n = 2290) or a HT with a lesion recorded (LESION; n = 670). Events with LESION were sub-categorized based on lesion category: digital dermatitis (DD; n = 276), sole ulcer (SU; n = 79), white line disease (WLD; n = 141), and other (n = 174). The data also contained the leg of the LESION, classified as front left (FL; n = 54), front right (FR; n = 146), rear left (RL; n = 281), or rear right (RR; n = 183) leg with 6 events missing the leg. Cows' HT histories were classified as follows: cows with no previous recorded instance of any lesion were classified as TRIM0 (n = 1554). The first instance of any hoof lesion was classified as LESION1 (n = 238). This classification was retained until a subsequent TRIM occurred - recorded as TRIM1 (n = 632). The next unique instance of any lesion following a TRIM1 was classified as LESION2 (n = 86). Any LESION events occurring after LESION1 or LESION2 without a subsequent TRIM were considered a hoof lesion recurrence and classified as LESIONRE1 (n = 164) and LESIONRE2 (n = 22), respectively. TRIM events after LESION2 or LESION2RE (n = 104) or LESION events after LESIONRE1 or LESIONRE2 were classified as LESION_OTHER (n = 160). The AUTO scores from -28 to -1 days prior to the HT event were summarized into weekly scores and included if cows had at least 1 observation per week in the 4 weeks before the event. For all weeks, LESION cows had a higher median AUTO score than TRIM cows. Cows with TRIM0 had the lowest and most consistent median weekly score compared to LESION and other TRIM classifications. Before HT cows with TRIM0 and TRIM1, both had median score increases of 1 across the 4 weeks, while the LESION categories had an increase of 4 to 8. Scores increased with each subsequent LESION event compared to the previous LESION event. Cows with SU lesions had the highest median score across the 4 weeks, WLD had the largest score increase, and DD had the lowest median score and score increase. When grouping a LESION event by leg the hoof lesion was found on, the AUTO scores for four groups displayed comparable median values. Due to the difference between TRIM and LESION events, this technology shows potential for the early detection of hoof lesions.

Deep learning pose detection model for sow locomotion

Lameness affects animal mobility, causing pain and discomfort. Lameness in early stages often goes undetected due to a lack of observation, precision, and reliability. Automated and non-invasive systems offer precision and detection ease and may improve animal welfare. This study was conducted to create a repository of images and videos of sows with different locomotion scores. Our goal is to develop a computer vision model for automatically identifying specific points on the sow's body. The automatic identification and ability to track specific body areas, will allow us to conduct kinematic studies with the aim of facilitating the detection of lameness using deep learning. The video database was collected on a pig farm with a scenario built to allow filming of sows in locomotion with different lameness scores. Two stereo cameras were used to record 2D videos images. Thirteen locomotion experts assessed the videos using the Locomotion Score System developed by Zinpro Corporation. From this annotated repository, computational models were trained and tested using the open-source deep learning-based animal pose tracking framework SLEAP (Social LEAP Estimates Animal Poses). The top-performing models were constructed using the LEAP architecture to accurately track 6 (lateral view) and 10 (dorsal view) skeleton keypoints. The architecture achieved average precisions values of 0.90 and 0.72, average distances of 6.83 and 11.37 in pixel, and similarities of 0.94 and 0.86 for the lateral and dorsal views, respectively. These computational models are proposed as a Precision Livestock Farming tool and method for identifying and estimating postures in pigs automatically and objectively. The 2D video image repository with different pig locomotion scores can be used as a tool for teaching and research. Based on our skeleton keypoint classification results, an automatic system could be developed. This could contribute to the objective assessment of locomotion scores in sows, improving their welfare.

Multi-scale keypoints detection and motion features extraction in dairy cows using ResNet101-ASPP network

Detecting Keypoints in dairy cows aims to locate and track the motion trajectories of the body's joints, which plays a crucial role in behavior analysis and lameness detection. However, real farming scenarios, characterized by occlusions and large variations in object scale may result in poor detection results. Therefore we introduce the atrous spatial pyramid pooling (ASPP) module into the shallow network of ResNet101, designed to improve the multi-scale feature extraction capability of the model. The ASPP module enhances the robustness of recognition for different dimensional sizes and occluded keypoints using different dilatation rates in the parallel atrous convolutional layers to expand the model's receptive field. Furthermore, seven types of motion features, including tracking up, gait symmetry, step height balance, motion speed variability, head swing amplitude, head-neck slope and back curvature are extracted simultaneously by monitoring and tracking the motion trajectory of distinct keypoints. Several of these features represent innovative extraction models and attributes, first proposed in this study. Multiple models are trained and tested on datasets containing 2385 frames for ablation experiments. The experiments show that, in comparison with the ResNet50, MobileNet_v2_1.0, and EfficientNet-b0 backbone networks, the training error and test error of ResNet101 improve by 4.04–30.12 pixels and 3.81–28.14 pixels. Therefore, ResNet101 is used as the benchmark for subsequent model improvement by adding the ASPP module. The training error and test error of the ResNet101-ASPP network are improved by 0.27 and 0.24 pixels, respectively, compared to the benchmark network. The prediction confidence improves by 1.65-2.50% at three different dairy cow object scales, In addition, the keypoints under different occlusion conditions improve considerably, especially for small-scale keypoints, demonstrating the capability of the ASPP module for multi-scale feature extraction. By analyzing the distribution between the seven features and health, mild lameness, and severe lameness in dairy cows, it is shown that all the different features play an important role in distinguishing between different levels of lameness.

Evaluation of forelimb gait variation overground at a walk in sound and lame dogs using a combination of diagnostic techniques

BackgroundKinetic and kinematic gait analysis is increasingly practised as a part of lameness evaluation in dogs. The aim of this study was to examine the normal short- and long-term variation in forelimb gait in sound control dogs (CD) at a walk using seven selected variables of objective kinetic and kinematic gait analyses. Also, to compare the findings in CD to a group of forelimb lame dogs with elbow osteoarthritis (OAD). An additional aim was to test a kinetic based graphic method for lameness detection; symmetry squares (SS). A prospective longitudinal study was carried out on client owned CD and OAD. Clinical and orthopaedic evaluations were performed to ensure soundness and detect and grade lameness. Seven kinetic and kinematic variables and SS were tested for lameness evaluation. The CD were divided into two subgroups, CD1 and CD2, and examined twice: CD1 with two months interval and CD2 with 3–4 h interval. The OAD group was evaluated once and compared to the CD groups’ first examination.ResultsThirteen CD and 19 OAD were included. For CD1 and CD2, there were no significant differences in any examined variable between examination occasions. Total peak force/impulse symmetry and fore-hind peak force/impulse symmetry differed significantly between OAD and CD. Symmetry squares had a 74% agreement to subjective orthopaedic evaluations.ConclusionsIn CD, no difference in the examined variables was seen between examination occasions. Four out of seven objective variables differed significantly between CD and OAD. The graphic SS method might have diagnostic potential for lameness detection, making it possible to detect a shift from lame to non-lame limbs. Potentially, this might be especially helpful in bilaterally lame dogs, which often represent a clinical challenge in lameness evaluation.

A novel lameness detection method for dairy cows based on temporal gait and spatial post features

Lameness is one of the common diseases in dairy farms, which seriously affects the health and welfare of dairy cows. The existing lameness detection methods based on computer vision have poor ability to extract spatiotemporal features, which reduces the lameness detection accuracy in dairy cows. In this paper, a spatiotemporal energy network (SEN) is proposed to detect lameness in dairy cows. It compresses the cow walking video into history energy image (HEI) and gait energy image (GEI), and then accurately extracts the temporal gait and spatial pose features of dairy cows. First, the YOLOv8n algorithm is used to remove background information from the video and segment the cow’s body. Second, the body contour sequence of the dairy cow is stacked based on the time series, and then different body parts of dairy cows are stacked on the channel to form the HEI. The HEI preserves the movement trajectory of the dairy cows. The first lameness classification model is obtained by training the MobileNetv2 network with HEI dataset. Third, the body contour sequence of the dairy cow is cropped according to the center of mass and body proportion and then stacked into an image, which is named GEI. The second lameness classification model is obtained by training the MobileNetv2 network with GEI dataset. Finally, the prediction results of the two models are fused according to the weight ratio to detect lameness in dairy cows. To verify the lameness detection effect of this method, 264 samples were randomly selected from 330 samples as the training set and the remaining 66 samples as the test set. The proposed method obtained competitive lameness detection results with classification accuracy of 96.22 %, sensitivity of 96.35 % and specificity of 98.14 %. By combining HEI and GEI, the spatiotemporal features of the cow walking are extracted more comprehensively. This method provides guidance for the lameness detection of dairy cows and reference for the gait analysis of animals.

Development of a real-time cattle lameness detection system using a single side-view camera

Recent advancements in machine learning and deep learning have revolutionized various computer vision applications, including object detection, tracking, and classification. This research investigates the application of deep learning for cattle lameness detection in dairy farming. Our study employs image processing techniques and deep learning methods for cattle detection, tracking, and lameness classification. We utilize two powerful object detection algorithms: Mask-RCNN from Detectron2 and the popular YOLOv8. Their performance is compared to identify the most effective approach for this application. Bounding boxes are drawn around detected cattle to assign unique local IDs, enabling individual tracking and isolation throughout the video sequence. Additionally, mask regions generated by the chosen detection algorithm provide valuable data for feature extraction, which is crucial for subsequent lameness classification. The extracted cattle mask region values serve as the basis for feature extraction, capturing relevant information indicative of lameness. These features, combined with the local IDs assigned during tracking, are used to compute a lameness score for each cattle. We explore the efficacy of various established machine learning algorithms, such as Support Vector Machines (SVM), AdaBoost and so on, in analyzing the extracted lameness features. Evaluation of the proposed system was conducted across three key domains: detection, tracking, and lameness classification. Notably, the detection module employing Detectron2 achieved an impressive accuracy of 98.98%. Similarly, the tracking module attained a high accuracy of 99.50%. In lameness classification, AdaBoost emerged as the most effective algorithm, yielding the highest overall average accuracy (77.9%). Other established machine learning algorithms, including Decision Trees (DT), Support Vector Machines (SVM), and Random Forests, also demonstrated promising performance (DT: 75.32%, SVM: 75.20%, Random Forest: 74.9%). The presented approach demonstrates the successful implementation for cattle lameness detection. The proposed system has the potential to revolutionize dairy farm management by enabling early lameness detection and facilitating effective monitoring of cattle health. Our findings contribute valuable insights into the application of advanced computer vision methods for livestock health management.

Descriptive evaluation of a camera-based dairy cattle lameness detection technology

Lameness in dairy cattle is not a disease but a clinical sign of im­paired locomotion, with the main causative agents being painful foot lesions. Lameness compromises economic, environmental, and social sustainability goals of the U.S. dairy industry. Com­bining technology and farm data may be a more precise and less labor-intensive tool for lameness detection, particularly with regard to early detection. The study objective was to describe the association between average weekly autonomous camera-based (AUTO) mobility scores and cows with lesion (LAME) and with­out lesions (TRIM) to see if this technology can detect lameness occurrence earlier.

The evolution of lameness on North American dairies: Addressing current industry challenges and exploring new and existing approaches to reduce lameness

Lameness is a key issue on commercial dairy farms, impacting productivity, profitability, sustainability, and overall welfare. As the causes of the disorder are multifactorial the persistence of lameness requires more complex approaches that take into account the existing knowledge we have on risk factors and management strategies and couples these with more novel ap­proaches to the issue. With hoof lesions being the source of the overwhelming majority of lameness cases, improving our understanding of what makes for a successful hoof trimming strategy on farms is a first step in addressing lameness. Howev­er, it is our ability to detect and provide early intervention that is proving increasingly vital to overall success in reducing on-farm lameness. Technology, especially when integrated with existing sources of routinely collected herd data, is one such emerging tool that may hold considerable promise for earlier, more accurate, and low labor lameness detection to allow for earlier intervention. Stakeholders, such as hoof trimmers, vet­erinarians, and nutritionists, can serve as effective and trusted facilitators of the adoption of new lameness management prac­tices and technologies, highlighting the need for their involve­ment in the industry pursuit for lower lameness prevalence.

Objective movement asymmetry in horses is comparable between markerless technology and sensor-based systems.

A markerless artificial intelligence (AI) system for lameness detection has recently become available but has not been extensively compared with commonly used inertial measurement unit (IMU) systems for detecting asymmetry under field conditions. Comparison of classification of asymmetric limbs under field conditions and comparison of normalised asymmetry data using a markerless AI system (SleipAI; recorded on a tripod mounted iPhone 14pro [SL]); the Equinosis Q Lameness Locator (LL); the EquiMoves (EM); and subjective evaluation (SE). Descriptive clinical study. Straight line trot data were collected from 52 client-owned horses in regular training. Limbs were categorised as symmetric or asymmetric. Number of analysed strides were compared with Wilcoxon's each pairs test. Inter-rater reliability in classification of asymmetric limbs was assessed with Light's Kappa. Bland Altman analysis of normalised asymmetry data was performed. Data from 41 horses were included. Most horses showed mild asymmetry. The EM analysed significantly more strides than the other systems, both for forelimbs and for hindlimbs (53 ± 11 strides for both, respectively; p < 0.006). The LL analysed significantly more hindlimbs strides (45 ± 13) than the SL (27 ± 6; p < 0.001). Moderate inter-rater agreement for asymmetry classification was found between systems (k = 0.59 forelimbs; 0.44 hindlimbs); agreement decreased when including the SE. For the normalised asymmetry data, the strongest agreement was found between the two IMU systems. Horses were assessed during straight-line trot only. The objective systems were comparable in classification of asymmetric limbs under field conditions when using defined asymmetry thresholds. Discrepancies stemmed largely from the imposed thresholds (i.e., systems largely identified same-side asymmetry). Overall, the strongest agreement was found between LL and EM. The SL analysed significantly fewer hindlimb strides than the LL and EM which could represent a limitation of the Sleip AI.

Lameness detection system for dairy cows based on instance segmentation

Lameness is one of the major health problems on dairy farms, which seriously affects dairy cow welfare and increases the risk of premature culling. Accuracy lameness detection ensures timely treatment of hooves and improves the level of health management on dairy farms. Most of the existing lameness detection methods detect one dairy cow, and it is difficult to detect lameness in multiple dairy cows at the same time. In this paper, a lameness detection system based on instance segmentation is constructed to extract the lameness features of multiple dairy cows and automatically detect lameness. First, an improved SOLOv2 network is designed to reduce the semantic gap between low-level and high-level features and improve the precision of dairy cow segmentation. Second, individual matching of dairy cows in different video frames is performed using the Hungarian algorithm. Third, the Canny algorithm is used to extract the neck and back contour features and key gait features of dairy cows. Finally, a deep learning model is constructed, and multiple lameness features are fused to detect the lameness of dairy cows. To evaluate the performance of the constructed system, 172 videos were randomly selected from 246 videos as training videos, and the remaining 74 videos were selected as the test videos. The lameness detection accuracy of the constructed system was 98.65%. The experimental results showed that the constructed system can extract the lameness features of multiple dairy cows at the same time and accurately detect the lameness of dairy cows.

Revolutionizing Cow Welfare Monitoring: A Novel Top-View Perspective with Depth Camera-Based Lameness Classification.

This study innovates livestock health management, utilizing a top-view depth camera for accurate cow lameness detection, classification, and precise segmentation through integration with a 3D depth camera and deep learning, distinguishing it from 2D systems. It underscores the importance of early lameness detection in cattle and focuses on extracting depth data from the cow's body, with a specific emphasis on the back region's maximum value. Precise cow detection and tracking are achieved through the Detectron2 framework and Intersection Over Union (IOU) techniques. Across a three-day testing period, with observations conducted twice daily with varying cow populations (ranging from 56 to 64 cows per day), the study consistently achieves an impressive average detection accuracy of 99.94%. Tracking accuracy remains at 99.92% over the same observation period. Subsequently, the research extracts the cow's depth region using binary mask images derived from detection results and original depth images. Feature extraction generates a feature vector based on maximum height measurements from the cow's backbone area. This feature vector is utilized for classification, evaluating three classifiers: Random Forest (RF), K-Nearest Neighbor (KNN), and Decision Tree (DT). The study highlights the potential of top-view depth video cameras for accurate cow lameness detection and classification, with significant implications for livestock health management.

Latest Trend and Challenges in Machine Learning– and Deep Learning–Based Computational Techniques in Poultry Health and Disease Management: A Review

To determine the flock’s economic worth, free‐range chicken growers must determine the gender, bird movement, behavior, disease detection, and lameness of the chickens. However, because of the complex environmental background and the fluctuating chicken population, it is difficult for farmers to effectively and properly measure those characteristics. Manual estimation is also inaccurate and time‐consuming because probable identification occurs in their life cycle. Therefore, the industry benefits from automated systems that can produce findings quickly and precisely in managing health and diseases. The advancement of machine learning (ML)– and deep learning (DL)–based algorithms are boons for poultry health and disease management. This study reviews the literature using ML and DL techniques in prediction, classification, and disease detection in various metrics, namely, poultry health and disease management. We have considered the research article published from 2010 to 2023 in this study, which uses ML‐ and DL‐based computation techniques in poultry welfare metrics such as gender identification, tracking of poultry, analysis of broiler chicken behavior, detection of poultry diseases, lameness and broiler weight, and stress monitoring. In addition, this review explores the most recent developments, difficulties, strategies, and databases used in image preprocessing feature extraction and classification. The review addresses these challenges and discusses the approaches and techniques researchers employ to tackle them in the field of poultry management and disease detection.

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.

CowScreeningDB: A public benchmark database for lameness detection in dairy cows

Lameness is one of the costliest pathological problems affecting dairy animals. It is usually assessed by trained veterinary clinicians who observe features such as gait symmetry or gait parameters as step counts in real time. With the development of artificial intelligence, various modular systems have been proposed to minimize subjectivity in lameness assessment. However, the major limitation in their development is the unavailability of a public database, as most existing ones are either commercial or privately held. To tackle this limitation, we have introduced CowScreeningDB, a multi-sensor database which was built with data from 43 dairy cows. Cows were monitored using smart watches during their normal daily routine. The uniqueness of the database lies in its data collection environment, sampling methodology, detailed sensor information, and the applications used for data conversion and storage, which ensure transparency and replicability. This data transparency makes CowScreeningDB a valuable and objectively comparable resource for further development of techniques for lameness detection for dairy cows. In addition to publicly sharing the database, we present a machine learning technique which classifies cows as healthy or lame by using raw sensory data. To facilitate fair comparisons with state-of-the-art methods, we introduce a novel benchmark. Combining the database, the machine learning technique and the benchmark validate our major objective, which is to establish the relationship between sensor data and lameness. The developed technique reports an average accuracy of 77 % for the best case scenario and presents perspectives for further development. By introducing this framework which encompasses the database, the classification algorithm and the benchmark, we significantly reduce subjectively in lameness assessment. This contribution to lameness detection fosters innovation in the field and promotes transparent, reproducible research in the pursuit of more effective management of dairy cow lameness. ImplicationsLameness detection is one of the main tasks in dairy systems, given its importance in the production ambit. However, the data used during detection is generally either held privately or sold commercially. In this study, we create a multi-sensor database (CowScreeningDB), which can be used for lameness. Because we have made the database public11(CowScreeningDB can be downloaded from https://github.com/Shahid-Ismail/CowScreeningDB-A-public-database-for-lameness-detection or https://gpds.ulpgc.es/) and free of charge for research purposes, it should act as a benchmark allowing to objectively compare techniques put forth to deal with lameness. We also provide details of the sampling system used, comprised of hardware and a baseline classification algorithm.

Leveraging Accelerometer Data for Lameness Detection in Dairy Cows: A Longitudinal Study of Six Farms in Germany

Lameness in dairy cows poses a significant challenge to improving animal well-being and optimizing economic efficiency in the dairy industry. To address this, employing automated animal surveillance for early lameness detection and prevention through activity sensors proves to be a promising strategy. In this study, we analyzed activity (accelerometer) data and additional cow-individual and farm-related data from a longitudinal study involving 4860 Holstein dairy cows on six farms in Germany during 2015–2016. We designed and investigated various statistical models and chose a logistic regression model with mixed effects capable of detecting lameness with a sensitivity of 77%. Our results demonstrate the potential of automated animal surveillance and hold the promise of significantly improving lameness detection approaches in dairy livestock.