Mastitis, a production disease with multiple etiologies, inflicts significant economic losses among dairy farmers around the globe. In this study, an attempt has been made to detect mastitis through a Convolutional Neural Networks (CNN)-based deep learning model using 7615 udder thermograms of 40 Murrah buffaloes. The thermograms were grouped separately as healthy, sub-clinical (SCM), and clinical mastitis (CM) affected udder quarters based on California Mastitis Test (CMT) scores, Somatic Cell Count (SCC) values and thermal image analysis. Results of thermogram analysis revealed a significant increase (p < 0.01) in the mean values of udder skin surface temperature (USST) among SCM and CM-affected quarters compared to healthy quarters to the tune of 1.32 and 2.61 °C, respectively. The USST showed a strong positive correlation with the CMT score (r = 0.87, p < 0.01) and logSCC value (r = 0.88, p < 0.01). The sequential (Normal Clinical and Normal Sub-clinical) models had training accuracy and validation accuracy of 0.999 and 0.988, 0.991 and 0.978, respectively. The confusion matrix for Normal Clinical and Normal Sub-clinical models reflected a loss of 0.009 and 0.029, precision of 0.947 and 0.980, and recall of 0.996 and 0.904, respectively. Consequently, the sequential (Normal Clinical and Normal Sub-clinical) models achieved a testing accuracy of 0.970 and 0.943, respectively. Thus, the improved deep-learning CNN models efficiently predicted SCM and CM cases in Murrah buffaloes.

中文翻译：

---

基于乳房热图的深度学习方法用于检测默拉水牛的乳腺炎

乳腺炎是一种具有多种病因的生产疾病，给全球奶农造成了巨大的经济损失。在这项研究中，尝试使用 40 头默拉水牛的 7615 幅乳房热图，通过基于卷积神经网络 (CNN) 的深度学习模型来检测乳腺炎。根据加州乳腺炎测试 (CMT) 评分、体细胞计数 (SCC) 值和热图像分析，将热图分别分组为健康、亚临床 (SCM) 和临床乳腺炎 (CM) 影响的乳房区。热分析结果显示，与健康群体相比，SCM 和 CM 受影响群体的乳房皮肤表面温度 (USST) 平均值显着增加 (p < 0.01)，分别为 1.32 和 2.61 °C。 USST 与 CMT 评分（r = 0.87，p < 0.01）和 logSCC 值（r = 0.88，p < 0.01）呈强正相关。序贯（正常临床和正常亚临床）模型的训练准确度和验证准确度分别为 0.999 和 0.988、0.991 和 0.978。正常临床和正常亚临床模型的混淆矩阵分别反映了 0.009 和 0.029 的损失、0.947 和 0.980 的精确度以及 0.996 和 0.904 的召回率。因此，序贯（正常临床和正常亚临床）模型的测试准确度分别为 0.970 和 0.943。因此，改进的深度学习 CNN 模型可以有效预测穆拉水牛的 SCM 和 CM 病例。