Scoring Enzootic Pneumonia-like Lesions in Slaughtered Pigs: Traditional vs. Artificial-Intelligence-Based Methods
Artificial-intelligence-based methods are regularly used in the biomedical sciences, mainly in the field of diagnostic imaging. Recently, convolutional neural networks have been trained to score pleurisy and pneumonia in slaughtered pigs. The aim of this study is to further evaluate the performance...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Pathogens |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-0817/12/12/1460 |
| _version_ | 1797379688675409920 |
|---|---|
| author | Jasmine Hattab Angelo Porrello Anastasia Romano Alfonso Rosamilia Sergio Ghidini Nicola Bernabò Andrea Capobianco Dondona Attilio Corradi Giuseppe Marruchella |
| author_facet | Jasmine Hattab Angelo Porrello Anastasia Romano Alfonso Rosamilia Sergio Ghidini Nicola Bernabò Andrea Capobianco Dondona Attilio Corradi Giuseppe Marruchella |
| author_sort | Jasmine Hattab |
| collection | DOAJ |
| description | Artificial-intelligence-based methods are regularly used in the biomedical sciences, mainly in the field of diagnostic imaging. Recently, convolutional neural networks have been trained to score pleurisy and pneumonia in slaughtered pigs. The aim of this study is to further evaluate the performance of a convolutional neural network when compared with the gold standard (i.e., scores provided by a skilled operator along the slaughter chain through visual inspection and palpation). In total, 441 lungs (180 healthy and 261 diseased) are included in this study. Each lung was scored according to traditional methods, which represent the gold standard (Madec’s and Christensen’s grids). Moreover, the same lungs were photographed and thereafter scored by a trained convolutional neural network. Overall, the results reveal that the convolutional neural network is very specific (95.55%) and quite sensitive (85.05%), showing a rather high correlation when compared with the scores provided by a skilled veterinarian (Spearman’s coefficient = 0.831, <i>p</i> < 0.01). In summary, this study suggests that convolutional neural networks could be effectively used at slaughterhouses and stimulates further investigation in this field of research. |
| first_indexed | 2024-03-08T20:26:38Z |
| format | Article |
| id | doaj.art-0b4af3b7bd4e4bb4b9079a3c8537026f |
| institution | Directory Open Access Journal |
| issn | 2076-0817 |
| language | English |
| last_indexed | 2024-03-08T20:26:38Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Pathogens |
| spelling | doaj.art-0b4af3b7bd4e4bb4b9079a3c8537026f2023-12-22T14:31:05ZengMDPI AGPathogens2076-08172023-12-011212146010.3390/pathogens12121460Scoring Enzootic Pneumonia-like Lesions in Slaughtered Pigs: Traditional vs. Artificial-Intelligence-Based MethodsJasmine Hattab0Angelo Porrello1Anastasia Romano2Alfonso Rosamilia3Sergio Ghidini4Nicola Bernabò5Andrea Capobianco Dondona6Attilio Corradi7Giuseppe Marruchella8Department of Veterinary Medicine, University of Teramo, Loc. Piano d’Accio, 64100 Teramo, ItalyAImageLab, University of Modena and Reggio Emilia, Via Vivarelli 10/1, 41125 Modena, ItalyAssociació Porcsa. GSP, Partida La Caparrella 97C, 25192 Lleida, SpainIstituto Zooprofilattico Sperimentale della Lombardia e dell’Emilia-Romagna “Bruno Ubertini” (IZSLER), 25124 Brescia, ItalyDepartment of Food and Drug, University of Parma, Via del Taglio 10, 43126 Parma, ItalyDepartment of Bioscience and Technology for Food, Agriculture and Environment, University of Teramo, Via Renato Balzarini 1, 64100 Teramo, ItalyFarm4trade s.r.l., Via IV Novembre 33, 66041 Atessa, ItalyDepartment of Veterinary Science, University of Parma, Via del Taglio 10, 43126 Parma, ItalyDepartment of Veterinary Medicine, University of Teramo, Loc. Piano d’Accio, 64100 Teramo, ItalyArtificial-intelligence-based methods are regularly used in the biomedical sciences, mainly in the field of diagnostic imaging. Recently, convolutional neural networks have been trained to score pleurisy and pneumonia in slaughtered pigs. The aim of this study is to further evaluate the performance of a convolutional neural network when compared with the gold standard (i.e., scores provided by a skilled operator along the slaughter chain through visual inspection and palpation). In total, 441 lungs (180 healthy and 261 diseased) are included in this study. Each lung was scored according to traditional methods, which represent the gold standard (Madec’s and Christensen’s grids). Moreover, the same lungs were photographed and thereafter scored by a trained convolutional neural network. Overall, the results reveal that the convolutional neural network is very specific (95.55%) and quite sensitive (85.05%), showing a rather high correlation when compared with the scores provided by a skilled veterinarian (Spearman’s coefficient = 0.831, <i>p</i> < 0.01). In summary, this study suggests that convolutional neural networks could be effectively used at slaughterhouses and stimulates further investigation in this field of research.https://www.mdpi.com/2076-0817/12/12/1460slaughtered pigsenzootic pneumoniascoreartificial intelligence |
| spellingShingle | Jasmine Hattab Angelo Porrello Anastasia Romano Alfonso Rosamilia Sergio Ghidini Nicola Bernabò Andrea Capobianco Dondona Attilio Corradi Giuseppe Marruchella Scoring Enzootic Pneumonia-like Lesions in Slaughtered Pigs: Traditional vs. Artificial-Intelligence-Based Methods Pathogens slaughtered pigs enzootic pneumonia score artificial intelligence |
| title | Scoring Enzootic Pneumonia-like Lesions in Slaughtered Pigs: Traditional vs. Artificial-Intelligence-Based Methods |
| title_full | Scoring Enzootic Pneumonia-like Lesions in Slaughtered Pigs: Traditional vs. Artificial-Intelligence-Based Methods |
| title_fullStr | Scoring Enzootic Pneumonia-like Lesions in Slaughtered Pigs: Traditional vs. Artificial-Intelligence-Based Methods |
| title_full_unstemmed | Scoring Enzootic Pneumonia-like Lesions in Slaughtered Pigs: Traditional vs. Artificial-Intelligence-Based Methods |
| title_short | Scoring Enzootic Pneumonia-like Lesions in Slaughtered Pigs: Traditional vs. Artificial-Intelligence-Based Methods |
| title_sort | scoring enzootic pneumonia like lesions in slaughtered pigs traditional vs artificial intelligence based methods |
| topic | slaughtered pigs enzootic pneumonia score artificial intelligence |
| url | https://www.mdpi.com/2076-0817/12/12/1460 |
| work_keys_str_mv | AT jasminehattab scoringenzooticpneumonialikelesionsinslaughteredpigstraditionalvsartificialintelligencebasedmethods AT angeloporrello scoringenzooticpneumonialikelesionsinslaughteredpigstraditionalvsartificialintelligencebasedmethods AT anastasiaromano scoringenzooticpneumonialikelesionsinslaughteredpigstraditionalvsartificialintelligencebasedmethods AT alfonsorosamilia scoringenzooticpneumonialikelesionsinslaughteredpigstraditionalvsartificialintelligencebasedmethods AT sergioghidini scoringenzooticpneumonialikelesionsinslaughteredpigstraditionalvsartificialintelligencebasedmethods AT nicolabernabo scoringenzooticpneumonialikelesionsinslaughteredpigstraditionalvsartificialintelligencebasedmethods AT andreacapobiancodondona scoringenzooticpneumonialikelesionsinslaughteredpigstraditionalvsartificialintelligencebasedmethods AT attiliocorradi scoringenzooticpneumonialikelesionsinslaughteredpigstraditionalvsartificialintelligencebasedmethods AT giuseppemarruchella scoringenzooticpneumonialikelesionsinslaughteredpigstraditionalvsartificialintelligencebasedmethods |