Automating hock wound detection in dairy cattle

Abstract

Hock scoring in dairy cattle is a crucial welfare assessment tool used to evaluate the condition of a cow's hocks, particularly for signs of injury, swelling, or lesions. These scores provide insight into the overall well-being of the animals and are essential for ensuring proper management and housing conditions. Accurate hock scoring is vital because it can indicate issues such as poor bedding quality or inadequate space, which directly affect the health and productivity of the herd. Traditionally, hock scoring is performed manually by trained observers. However, consistency in scoring can be a challenge. Two studies were conducted to quantify inconsistency in hock scoring. In one study, manual scoring reproducibility was measured. In the second study, manual and video scoring repeatability was measured. Repeatability was quantified with a weighted Cohen's kappa metric. Manual scoring was found to be inconsistent but more consistent than video scoring. This variability highlights the need for a more reliable, objective method of scoring. To address this, we explored the automation of hock score detection using artificial intelligence. Specifically, we employed a simple U-net semantic segmentation algorithm to detect wounds on the hocks without classifying them into specific categories. Automating the detection process can reduce observer bias, improve consistency, and allow for continuous monitoring of large herds. This approach holds promise for enhancing animal welfare by providing a more efficient and accurate method of assessing hock health in dairy cattle.