Automated Classification for Visual-Only Post-Mortem Inspection of Porcine Pathology

Stephen McKenna (Lead / Corresponding author), Telmo Amaral, Ilias Kyriazakis

Research output: Contribution to journalArticle

6 Downloads (Pure)

Abstract

Several advantages would arise from the automated detection of pathologies of pig carcasses, including avoidance of the inherent risks of subjectivity and variability between human observers. Here, we develop a novel automated classification of two porcine offal pathologies at abattoir: a focal, localized pathology of the liver and a diffuse pathology of the heart, as cases in point. We develop a pattern recognition system based on machine learning to identify those organs that exhibit signs of the pathology of interest. Specifically, deep neural networks are trained to produce probability heat maps highlighting regions on the surface of an organ potentially affected by a given condition. A final classification stage then decides whether a given organ is affected by the condition in question based on statistics computed from the heat map. We compare outcomes of automated classification with classification by expert pathologists. Results show classification of liver and heart pathologies in agreement with an expert at levels comparable to, or exceeding, inter-expert agreement. A system using methods such as those presented here has potential to overcome the limitations of human-based abattoir inspection, especially if this is based on visual-only inspection, and ultimately to provide a new gold standard for pathology.
Original languageEnglish
Number of pages12
JournalIEEE Transactions on Automation Science and Engineering
Early online date20 Jan 2020
DOIs
Publication statusE-pub ahead of print - 20 Jan 2020

Fingerprint

Swine
Pathology
Abattoirs
Automated Pattern Recognition
Hot Temperature
Liver

Cite this

McKenna, S., Amaral, T., & Kyriazakis, I. (2020). Automated Classification for Visual-Only Post-Mortem Inspection of Porcine Pathology. IEEE Transactions on Automation Science and Engineering. https://doi.org/10.1109/TASE.2019.2960106
McKenna, Stephen ; Amaral, Telmo ; Kyriazakis, Ilias . / Automated Classification for Visual-Only Post-Mortem Inspection of Porcine Pathology. In: IEEE Transactions on Automation Science and Engineering. 2020.
@article{aa237a1e88b24bda890650382bb8253d,
title = "Automated Classification for Visual-Only Post-Mortem Inspection of Porcine Pathology",
abstract = "Several advantages would arise from the automated detection of pathologies of pig carcasses, including avoidance of the inherent risks of subjectivity and variability between human observers. Here, we develop a novel automated classification of two porcine offal pathologies at abattoir: a focal, localized pathology of the liver and a diffuse pathology of the heart, as cases in point. We develop a pattern recognition system based on machine learning to identify those organs that exhibit signs of the pathology of interest. Specifically, deep neural networks are trained to produce probability heat maps highlighting regions on the surface of an organ potentially affected by a given condition. A final classification stage then decides whether a given organ is affected by the condition in question based on statistics computed from the heat map. We compare outcomes of automated classification with classification by expert pathologists. Results show classification of liver and heart pathologies in agreement with an expert at levels comparable to, or exceeding, inter-expert agreement. A system using methods such as those presented here has potential to overcome the limitations of human-based abattoir inspection, especially if this is based on visual-only inspection, and ultimately to provide a new gold standard for pathology.",
author = "Stephen McKenna and Telmo Amaral and Ilias Kyriazakis",
year = "2020",
month = "1",
day = "20",
doi = "10.1109/TASE.2019.2960106",
language = "English",

}

McKenna, S, Amaral, T & Kyriazakis, I 2020, 'Automated Classification for Visual-Only Post-Mortem Inspection of Porcine Pathology', IEEE Transactions on Automation Science and Engineering. https://doi.org/10.1109/TASE.2019.2960106

Automated Classification for Visual-Only Post-Mortem Inspection of Porcine Pathology. / McKenna, Stephen (Lead / Corresponding author); Amaral, Telmo ; Kyriazakis, Ilias .

In: IEEE Transactions on Automation Science and Engineering, 20.01.2020.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated Classification for Visual-Only Post-Mortem Inspection of Porcine Pathology

AU - McKenna, Stephen

AU - Amaral, Telmo

AU - Kyriazakis, Ilias

PY - 2020/1/20

Y1 - 2020/1/20

N2 - Several advantages would arise from the automated detection of pathologies of pig carcasses, including avoidance of the inherent risks of subjectivity and variability between human observers. Here, we develop a novel automated classification of two porcine offal pathologies at abattoir: a focal, localized pathology of the liver and a diffuse pathology of the heart, as cases in point. We develop a pattern recognition system based on machine learning to identify those organs that exhibit signs of the pathology of interest. Specifically, deep neural networks are trained to produce probability heat maps highlighting regions on the surface of an organ potentially affected by a given condition. A final classification stage then decides whether a given organ is affected by the condition in question based on statistics computed from the heat map. We compare outcomes of automated classification with classification by expert pathologists. Results show classification of liver and heart pathologies in agreement with an expert at levels comparable to, or exceeding, inter-expert agreement. A system using methods such as those presented here has potential to overcome the limitations of human-based abattoir inspection, especially if this is based on visual-only inspection, and ultimately to provide a new gold standard for pathology.

AB - Several advantages would arise from the automated detection of pathologies of pig carcasses, including avoidance of the inherent risks of subjectivity and variability between human observers. Here, we develop a novel automated classification of two porcine offal pathologies at abattoir: a focal, localized pathology of the liver and a diffuse pathology of the heart, as cases in point. We develop a pattern recognition system based on machine learning to identify those organs that exhibit signs of the pathology of interest. Specifically, deep neural networks are trained to produce probability heat maps highlighting regions on the surface of an organ potentially affected by a given condition. A final classification stage then decides whether a given organ is affected by the condition in question based on statistics computed from the heat map. We compare outcomes of automated classification with classification by expert pathologists. Results show classification of liver and heart pathologies in agreement with an expert at levels comparable to, or exceeding, inter-expert agreement. A system using methods such as those presented here has potential to overcome the limitations of human-based abattoir inspection, especially if this is based on visual-only inspection, and ultimately to provide a new gold standard for pathology.

U2 - 10.1109/TASE.2019.2960106

DO - 10.1109/TASE.2019.2960106

M3 - Article

ER -

McKenna S, Amaral T, Kyriazakis I. Automated Classification for Visual-Only Post-Mortem Inspection of Porcine Pathology. IEEE Transactions on Automation Science and Engineering. 2020 Jan 20. https://doi.org/10.1109/TASE.2019.2960106