Early Detection of Mastitis by using Infrared Thermography in Holstein-Friesian Dairy Cows via Classification and Regression Tree (CART) Analysis

Subclinical mastitis is an important udder disease that negatively affects both the animal health and reduces profitability in dairy farms. The increasing performance of thermal cameras over time their usability different areas increase use livestocks. Infrared thermography (IRT) technology a noninvasive method can estimate surface temperature objects. objective this study was to evaluate early detection Holstein-Friesian cattle by using temperatures (Tmax) from images obtained with help FLIR One Pro camera some parameters such as Lab (CIE L*, a*, b*), HSB (Hue, Saturation, Brightness), RGB (Red, Green, Blue) processing ImageJ program via classification regression tree (CART) analysis. According California Mastitis Test CMT CART analysis study, 64.9% cows lower than 38.85 were healthy, 73.3% higher determined unhealthy. As for SCC, 77.6% 38.65 healthy 58.6% under ROC (AUC) found be statistically significant diagnosis subclinical mastitis. (P<0.01) sensitivity specificity algorithm SCC diagnostic tests 85.42%, 81.48% 90.20%, 80.39%, respectively. There no difference between area curve (P>0.05). result, IRT used useful tool