Accurate classification of lung lesions at necropsy is crucial for guiding the diagnostic process and ensuring effective management of porcine respiratory diseases. Post-mortem inspection of the lungs during slaughter also provides valuable insights into disease occurrence, offering useful feedback on the efficacy of on-farm prevention and control strategies. However, manual assessment protocols may be impaired by high slaughtering speeds and low inter-rater agreement, which limits continuous data collection and hinders comparability. Artificial intelligence, particularly computer vision (CV), may offer a promising alternative. This study aimed to train and test a commercial CV model for segmenting both anatomical structures and lesions in pig lungs. Overall, 1742 lungs were collected at slaughter, examined macroscopically, and photographed laterally. Two veterinarians with expertise in swine pathology manually annotated the acquired images to outline anatomical (i.e., lung, heart, lung lobes), pathological (i.e., bronchopneumonia, fibrinous pleuropneumonia, chronic pleuritis), and artefactual (i.e., parenchymal laceration, bronchoinhalation of blood) classes, forming the reference dataset for model training and testing. Model performance in segmenting these classes varied by confidence threshold, with sensitivity (36-84 %), positive predictive value (62-93 %) and F1 score (52-78 %) indicating imperfect yet improvable performance. Overall, anatomical structure segmentation outperformed lesion detection, likely due to class imbalance in the training dataset and the complexity of pulmonary pathology. Integrating standardized and real-time detection of lung lesions via digital imaging could improve respiratory health surveillance, thereby enhancing the role of abattoirs as strategic epidemiological observatories.

On-farm emergency slaughter (OFES) is employed when cattle are unfit for transport but still suitable for human consumption, thereby ensuring animal welfare and reducing food waste. This study analysed OFES patterns in Northern Italy, where a large cattle population is housed but information on the practice is rarely analysed. A total of 12,052 OFES cases from 2021 to 2023 were analysed. Most involved female cattle (94%) from dairy farms (79%). Locomotor disorders were the leading reason (70%), particularly trauma and fractures, followed by recumbency (13%) and calving-related issues (10%). Post-mortem findings showed limbs and joints as the most frequent condemnation sites (36%), often linked to trauma. A significant reduction in OFES cases occurred over time, mainly due to fewer recumbency and calving issues, likely reflecting stricter eligibility criteria introduced in 2022. Weekly variations, with peaks on Mondays and lows on Saturdays, suggest that logistical constraints may sometimes influence OFES promptness. These findings suggest that on-farm management and animal handling could be improved further to reduce welfare risks and carcass waste. Due to the lack of standardised data collection and regulatory harmonisation, a multi-country investigation could improve our understanding of this topic and inform best practice.