Validation of an automatic scoring system for the assessment of hock burn in broiler

This study aimed to develop and validate a camera vision score that could detect macroscopic alterations of the hock, to identify errors and to assess possible factors that could influence the assessment. Two hundred hocks in the first (calibration) phase and 500 hocks in the second (validation) phase were collected at slaughter, visually assessed, placed back into the evisceration line and assessed by a camera system with 2 software systems. The size of the alteration in percent (%) measured by the camera system was evaluated (“camera score”, CS). Additionally, temperature, humidity, and light intensities were measured. In the calibration phase, threshold values of camera scores for respective macro scores were defined and performance measures evaluated. In the validation phase, the generated threshold values were validated, occurring errors, as well as possible impacts of climatic factors analyzed. The results showed that the generated thresholds predict the camera score values at which the respective macro score has the highest probability of appearance. Small hock burn lesions ≤0.5 cm have the highest probability at a camera score of ≥0.2 (original CS) or ≥0.1 (updated CS), and lesions >0.5 cm have the highest probability at a camera score of ≥0.7 (original CS) or ≥1.1 (updated CS). Large lesions (>0.5 cm) are more reliably identified by the system than small lesions. The risks of errors in assessing reference areas and lesions showed a correct identification of lesions to be the most probable result even if the reference area is not correctly identified. The probability of a correct identification of lesions by the camera system was slightly higher (not significant) with the updated software (risk = 0.66 [0.62–0.70]) than with the original software (risk = 0.63 [0.58–0.67]). Automatic assessment systems at slaughter could be adjusted to the presented threshold values to classify hock burn lesions. Software adaptations can improve the performance measures of diagnosis and reduce the probability of errors.