Department of Medical Sciences, School of Veterinary Medicine, University of Wisconsin, Madison 53706.
Department of Pathobiological Sciences, School of Veterinary Medicine, University of Wisconsin, Madison 53706; Department of Computer Sciences, University of Wisconsin, Madison 53706.
J Dairy Sci. 2020 Oct;103(10):9110-9115. doi: 10.3168/jds.2019-17478. Epub 2020 Aug 26.
Digital dermatitis (DD) is linked to severe lameness, infertility, and decreased milk production in cattle. Early detection of DD provides an improved prognosis for treatment and recovery; however, this is extremely challenging on commercial dairy farms. Computer vision (COMV) models can help facilitate early DD detection on commercial dairy farms. The aim of this study was to develop and implement a novel COMV tool to identify DD lesions on a commercial dairy farm. Using a database of more than 3,500 DD lesion images, a model was trained using the YOLOv2 architecture to detect the M-stages of DD. The YOLOv2 COMV model detected DD with an accuracy of 71%, and the agreement was quantified as "moderate" by Cohen's kappa when compared with a human evaluator for the internal validation. In the external validation, the YOLOv2 COMV model detected DD with an accuracy of 88% and agreement was quantified as "fair" by Cohen's kappa. Implementation of COMV tools for DD detection provides an opportunity to identify cows for DD treatment, which has the potential to lower DD prevalence and improve animal welfare on commercial dairy farms.
数字性皮炎（DD）与牛的严重跛行、不孕和产奶量下降有关。早期发现 DD 可为治疗和恢复提供更好的预后；然而，这在商业奶牛场极具挑战性。计算机视觉（COMV）模型可以帮助促进商业奶牛场的早期 DD 检测。本研究旨在开发和实施一种新的 COMV 工具，以识别商业奶牛场的 DD 病变。使用一个包含超过 3500 张 DD 病变图像的数据库，使用 YOLOv2 架构训练了一个模型，以检测 DD 的 M 期。与人类评估者进行内部验证时，YOLOv2 COMV 模型对 DD 的检测准确率为 71%，一致性用 Cohen's kappa 量化为“中等”。在外部验证中，YOLOv2 COMV 模型对 DD 的检测准确率为 88%，一致性用 Cohen's kappa 量化为“一般”。DD 检测的 COMV 工具的实施为 DD 治疗提供了一个识别奶牛的机会，这有可能降低商业奶牛场的 DD 流行率并改善动物福利。
