Detecting ear lesions in slaughtered pigs through open-source convolutional neural networks
Abstract Background Ear biting is a damaging behavior of pigs, likely triggered by a genetic predisposition, previous health issues and/or poor environmental conditions. The accurate assessment of animal health and welfare relies on the systematic gathering of data about animals, resources and manag...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-05-01
|
| Series: | Porcine Health Management |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40813-025-00442-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849309340295495680 |
|---|---|
| author | Matteo D’Angelo Domenico Sciota Anastasia Romano Alfonso Rosamilia Chiara Guarnieri Chiara Cecchini Alberto Olivastri Giuseppe Marruchella |
| author_facet | Matteo D’Angelo Domenico Sciota Anastasia Romano Alfonso Rosamilia Chiara Guarnieri Chiara Cecchini Alberto Olivastri Giuseppe Marruchella |
| author_sort | Matteo D’Angelo |
| collection | DOAJ |
| description | Abstract Background Ear biting is a damaging behavior of pigs, likely triggered by a genetic predisposition, previous health issues and/or poor environmental conditions. The accurate assessment of animal health and welfare relies on the systematic gathering of data about animals, resources and management. In this respect, slaughterhouse surveys offer valuable insights, as distinct tail and skin lesions can act as ‘iceberg’ parameters, suitable to estimate welfare during the entire animals’ lifecycle. However, the routine recording of lesions is often costly and time-consuming, making it unfeasible in high-throughput abattoirs. This study aims to train open-source convolutional neural networks for detecting ear biting lesions in slaughtered pigs, as a pre-requisite for a systematic and cost-effective welfare monitoring. Results A total of 3,140 pictures were employed to train and test open-source convolutional neural networks. Investigations were carried out by three veterinarians, who agreed to assess porcine ears using a simplified method, to minimize inter-observers’ variability and to facilitate the convolutional neural networks’ training: a) healthy auricles (label 0); deformed auricles displaying alterations in their contour due to real lesions (label 1); postmortem artefacts due to slaughtering (label 2). The entire dataset (training set and test set) was evaluated by one observer, while a supplementary set of 150 pictures was assessed by all veterinarians. Overall, the agreement among observers was very high (Cohen’s kappa coefficient > 0.88). Moreover, convolutional neural networks’ performances appeared suitable when compared with veterinarians: overall accuracy 0.89, specificity 0.96, sensitivity 0.86, agreement with each individual observer 0.79 (Cohen’s kappa coefficient). Conclusions Open-source convolutional neural networks can achieve good performances, especially when the task is strictly defined and rather easy. Valuable experiences are being gathered about the routine application of artificial intelligence-powered tools in pig abattoirs. We consider that such tools will likely enable the systematic collection of data, addressing the distinct needs of stakeholders in a cost-effective manner. |
| format | Article |
| id | doaj-art-95cd2c225ef541bc8b82cc4961401760 |
| institution | Kabale University |
| issn | 2055-5660 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | BMC |
| record_format | Article |
| series | Porcine Health Management |
| spelling | doaj-art-95cd2c225ef541bc8b82cc49614017602025-08-20T03:54:11ZengBMCPorcine Health Management2055-56602025-05-011111810.1186/s40813-025-00442-9Detecting ear lesions in slaughtered pigs through open-source convolutional neural networksMatteo D’Angelo0Domenico Sciota1Anastasia Romano2Alfonso Rosamilia3Chiara Guarnieri4Chiara Cecchini5Alberto Olivastri6Giuseppe Marruchella7Department of Bioscience and Agro-Food and Environmental Technology, University of TeramoDepartment of Veterinary Medicine, University of TeramoDepartment of Veterinary Medicine, University of TeramoIstituto Zooprofilattico Sperimentale della Lombardia e dell’Emilia-Romagna “Bruno Ubertini”Local Health Unit AuthorityDepartment of Veterinary Medicine, University of TeramoLocal Health Unit AuthorityDepartment of Veterinary Medicine, University of TeramoAbstract Background Ear biting is a damaging behavior of pigs, likely triggered by a genetic predisposition, previous health issues and/or poor environmental conditions. The accurate assessment of animal health and welfare relies on the systematic gathering of data about animals, resources and management. In this respect, slaughterhouse surveys offer valuable insights, as distinct tail and skin lesions can act as ‘iceberg’ parameters, suitable to estimate welfare during the entire animals’ lifecycle. However, the routine recording of lesions is often costly and time-consuming, making it unfeasible in high-throughput abattoirs. This study aims to train open-source convolutional neural networks for detecting ear biting lesions in slaughtered pigs, as a pre-requisite for a systematic and cost-effective welfare monitoring. Results A total of 3,140 pictures were employed to train and test open-source convolutional neural networks. Investigations were carried out by three veterinarians, who agreed to assess porcine ears using a simplified method, to minimize inter-observers’ variability and to facilitate the convolutional neural networks’ training: a) healthy auricles (label 0); deformed auricles displaying alterations in their contour due to real lesions (label 1); postmortem artefacts due to slaughtering (label 2). The entire dataset (training set and test set) was evaluated by one observer, while a supplementary set of 150 pictures was assessed by all veterinarians. Overall, the agreement among observers was very high (Cohen’s kappa coefficient > 0.88). Moreover, convolutional neural networks’ performances appeared suitable when compared with veterinarians: overall accuracy 0.89, specificity 0.96, sensitivity 0.86, agreement with each individual observer 0.79 (Cohen’s kappa coefficient). Conclusions Open-source convolutional neural networks can achieve good performances, especially when the task is strictly defined and rather easy. Valuable experiences are being gathered about the routine application of artificial intelligence-powered tools in pig abattoirs. We consider that such tools will likely enable the systematic collection of data, addressing the distinct needs of stakeholders in a cost-effective manner.https://doi.org/10.1186/s40813-025-00442-9PigSlaughterhouseAnimal welfareEar lesionsArtificial intelligence |
| spellingShingle | Matteo D’Angelo Domenico Sciota Anastasia Romano Alfonso Rosamilia Chiara Guarnieri Chiara Cecchini Alberto Olivastri Giuseppe Marruchella Detecting ear lesions in slaughtered pigs through open-source convolutional neural networks Porcine Health Management Pig Slaughterhouse Animal welfare Ear lesions Artificial intelligence |
| title | Detecting ear lesions in slaughtered pigs through open-source convolutional neural networks |
| title_full | Detecting ear lesions in slaughtered pigs through open-source convolutional neural networks |
| title_fullStr | Detecting ear lesions in slaughtered pigs through open-source convolutional neural networks |
| title_full_unstemmed | Detecting ear lesions in slaughtered pigs through open-source convolutional neural networks |
| title_short | Detecting ear lesions in slaughtered pigs through open-source convolutional neural networks |
| title_sort | detecting ear lesions in slaughtered pigs through open source convolutional neural networks |
| topic | Pig Slaughterhouse Animal welfare Ear lesions Artificial intelligence |
| url | https://doi.org/10.1186/s40813-025-00442-9 |
| work_keys_str_mv | AT matteodangelo detectingearlesionsinslaughteredpigsthroughopensourceconvolutionalneuralnetworks AT domenicosciota detectingearlesionsinslaughteredpigsthroughopensourceconvolutionalneuralnetworks AT anastasiaromano detectingearlesionsinslaughteredpigsthroughopensourceconvolutionalneuralnetworks AT alfonsorosamilia detectingearlesionsinslaughteredpigsthroughopensourceconvolutionalneuralnetworks AT chiaraguarnieri detectingearlesionsinslaughteredpigsthroughopensourceconvolutionalneuralnetworks AT chiaracecchini detectingearlesionsinslaughteredpigsthroughopensourceconvolutionalneuralnetworks AT albertoolivastri detectingearlesionsinslaughteredpigsthroughopensourceconvolutionalneuralnetworks AT giuseppemarruchella detectingearlesionsinslaughteredpigsthroughopensourceconvolutionalneuralnetworks |