Liao Mingsi, Morota Gota, Bi Ye, Cockrum Rebecca R
School of Animal Sciences, Virginia Polytechnic Institute and State University, Blacksburg, VA 24060, USA.
Laboratory of Biometry and Bioinformatics, Department of Agricultural and Environmental Biology, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Bunkyo 113-8657, Tokyo, Japan.
Animals (Basel). 2025 Mar 18;15(6):868. doi: 10.3390/ani15060868.
Monitoring calf body weight (BW) before weaning is essential for assessing growth, feed efficiency, health, and weaning readiness. However, labor, time, and facility constraints limit BW collection. Additionally, Holstein calf coat patterns complicate image-based BW estimation, and few studies have explored non-contact measurements taken at early time points for predicting later BW. The objectives of this study were to (1) develop deep learning-based segmentation models for extracting calf body metrics, (2) compare deep learning segmentation with threshold-based methods, and (3) evaluate BW prediction using single-time-point cross-validation with linear regression (LR) and extreme gradient boosting (XGBoost) and multiple-time-point cross-validation with LR, XGBoost, and a linear mixed model (LMM). Depth images from Holstein (n = 63) and Jersey (n = 5) pre-weaning calves were collected, with 20 Holstein calves being weighed manually. Results showed that You Only Look Once version 8 (YOLOv8) deep learning segmentation (intersection over union = 0.98) outperformed threshold-based methods (0.89). In single-time-point cross-validation, XGBoost achieved the best BW prediction (R = 0.91, mean absolute percentage error (MAPE) = 4.37%), while LMM provided the most accurate longitudinal BW prediction (R = 0.99, MAPE = 2.39%). These findings highlight the potential of deep learning for automated BW prediction, enhancing farm management.
在断奶前监测犊牛体重（BW）对于评估生长、饲料效率、健康状况和断奶准备情况至关重要。然而，劳动力、时间和设施限制阻碍了体重数据的收集。此外，荷斯坦犊牛的毛色图案使基于图像的体重估计变得复杂，并且很少有研究探索在早期时间点进行的非接触式测量以预测后期体重。本研究的目的是：（1）开发基于深度学习的分割模型以提取犊牛身体指标；（2）将深度学习分割与基于阈值的方法进行比较；（3）使用线性回归（LR）和极端梯度提升（XGBoost）的单时间点交叉验证以及使用LR、XGBoost和线性混合模型（LMM）的多时间点交叉验证来评估体重预测。收集了荷斯坦（n = 63）和泽西（n = 5）断奶前犊牛的深度图像，其中20头荷斯坦犊牛进行了手动称重。结果表明，You Only Look Once版本8（YOLOv8）深度学习分割（交并比 = 0.98）优于基于阈值的方法（0.89）。在单时间点交叉验证中，XGBoost实现了最佳的体重预测（R = 0.91，平均绝对百分比误差（MAPE） = 4.37%），而LMM提供了最准确的纵向体重预测（R = 0.99，MAPE = 2.39%）。这些发现凸显了深度学习在自动体重预测方面的潜力，有助于加强农场管理。
