Artificial Intelligence for Lameness Detection in Horses—A Preliminary Study

SIMPLE SUMMARY: In the expanding field of artificial intelligence, deep learning and smart-device-technology, a diagnostic software tool was developed, which can help distinguish between lame and sound horses and locate the affected limb. As lameness influences the welfare of horses and is often difficult to detect, this tool can help owners and veterinarians in the process of evaluation. The technology is based on pose estimation, which is already used in human and veterinary science to study movement of limbs or bodies without the need to fix any devices onto the object of interest. In this study, 22 horses with unilateral fore- or hindlimb lameness and a control group of eight sound horses were analysed with the program. Based on the results of the program, it was possible to differentiate between horses with fore- and hindlimb lameness and sound horses. Difficult light settings, such as direct sunlight or darkness, or very even-coloured coats, complicate the precise placement of reference points. The analysis and detection with software-generated movement trajectories using pose estimation is very promising but requires further development. ABSTRACT: Lameness in horses is a long-known issue influencing the welfare, as well as the use, of a horse. Nevertheless, the detection and classification of lameness mainly occurs on a subjective basis by the owner and the veterinarian. The aim of this study was the development of a lameness detection system based on pose estimation, which permits non-invasive and easily applicable gait analysis. The use of 58 reference points on easily detectable anatomical landmarks offers various possibilities for gait evaluation using a simple setup. For this study, three groups of horses were used: one training group, one analysis group of fore and hindlimb lame horses and a control group of sound horses. The first group was used to train the network; afterwards, horses with and without lameness were evaluated. The results show that forelimb lameness can be detected by visualising the trajectories of the reference points on the head and both forelimbs. In hindlimb lameness, the stifle showed promising results as a reference point, whereas the tuber coxae were deemed unsuitable as a reference point. The study presents a feasible application of pose estimation for lameness detection, but further development using a larger dataset is essential.