Scoring pleurisy in slaughtered pigs using convolutional neural networks

• DOI: 10.1186/s13567-020-00775-z
• Publication Date: 2020-04-10T14:02:52Z
• Authors: Abigail R. Trachtman; Luca Bergamini; Andrea Palazzi; Angelo Porrello; Andrea Capobianco...; Ercole Del Negro; Andrea Paolini; Giorgio Vignola; Simone Calderara; Giuseppe Marruchella
• Keywords: Pleurisy

Abstract Diseases of the respiratory system are known to negatively impact profitability pig industry, worldwide. Considering relatively short lifespan pigs, lesions can be still evident at slaughter, where they usefully recorded and scored. Therefore, slaughterhouse represents a key check-point assess health status providing unique valuable feedback farm, as well an important source data for epidemiological studies. Although relevant, scoring in slaughtered pigs very time-consuming costly activity, thus making difficult their systematic recording. The present study has been carried out train convolutional neural network-based automatically score pleurisy pigs. automation such process would extremely helpful enable examination all livestock. Overall, our indicate that proposed is able differentiate half carcasses affected with from healthy ones, overall accuracy 85.5%. was better recognize severely compared those showing less severe lesions. training networks identify pneumonia, on one hand, achievement trials large capacity slaughterhouses, other, represent natural pursuance study. As result, technologies could provide fast cheap tool systematically record supplying enormous amount useful stakeholders industry.