Evaluating automated infrared thermography and vulva exposure tracking as components of an estrus detection platform in a commercial dairy herd

The primary objective of this study was to develop an automated infrared thermography platform (Estrus BenchMark) capable of measuring skin temperature and tail movements as a means of identifying cows in estrus. The secondary objective was to evaluate the accuracy of Estrus BenchMark to detect estrus compared to in-line milk progesterone (P-4) analysis (Herd Navigator System) in a commercial dairy herd managed under a robotic milking system. Data were collected on forty-six cows from 45 to 120 d after calving. Cows were flagged in estrus when milk P-4 fell below 5 ng/mL. The Estrus BenchMark true positive estrus alerts (Sensitivity; Se%) were compared to Herd Navigator System estrus alerts at different time -windows (+/- 12 h, +/- 24 h, +/- 48 h, and +/- 72 h) relative to the Estrus BenchMark estrus alerts for all the estrus alerts (AE) and confidence-quality estrus (CQE; > 80% quality) alerts identified by Herd Navigator System. The Estrus BenchMark captured skin temperature and tail movements resulting in vulva exposure (left tail movements, LTail; right tail movements, RTail; and pooled tail movements, PTail) for each milking event. Skin temperature tended to increase when the milk P-4 concentration (Least-Squares Means +/- SE) dropped for AE (estrus day [d 0]; P-4; 3.51 +/- 0.05 ng/mL, Skin temperature; 33.31 +/- 2.38 degrees C) compared with d-7 (P-4; 20.22 +/- 0.73 ng/mL; Skin temperature: 32.05 +/- 3.77 degrees C). The increase in skin temperature, however, was significant in cows with CQE > 80% at d 0 (32.75 +/- 0.29 degrees C) compared to d-7 (31.80 +/- 0.28 degrees C). The prevalence of tail movements to expose vulva was greater (P = 0.01) in AE at d 0 (LTail: 62.50%; PTail; 68.75%; and RTail: 56.25%) compared with d-7 (LTail: 18.75%; PTail: 9.37%: and RTail: 9.37%), and d +4 (LTail: 9.37%; PTail: 9.37%; and RTail: 12.5%). Moreover, the higher prevalence of tail movements at d 0 was observed in cows with CQE > 80% (LTail; 65%, PTail; 80%, and RTail; 70%) compared to those with CQE < 80%. The highest Estrus BenchMark Youden index (YJ; 0.45), diagnostic odds ratio (DOR; 9.04), and Efficiency (0.77) were achieved for AE in a +/- 48 h window and at +/- 72 h window for CQE (YJ; 0.66, DOR; 25.29, and Efficiency 0.76) relative to Herd Navigator System estrus alerts. The highest Estrus BenchMark resulted in 58% estrus detection rates for AE and 80% for cows with CQE compared to the Herd Navigator System. (C) 2022 The Authors. Published by Elsevier B.V. on behalf of The Animal Consortium.

Automated summary

The primary objective of this study was to develop an automated infrared thermography platform capable of identifying cows in estrus by measuring skin temperature and tail movements. The study also evaluated the accuracy of the platform compared to in-line milk progesterone analysis and found that skin temperature and tail movements were associated with the estrus status of cows.