Image Classification and Automated Machine Learning to Classify Lung Pathologies in Deceased Feedlot Cattle
Bovine respiratory disease (BRD) and acute interstitial pneumonia (AIP) are the main reported respiratory syndromes (RSs) causing significant morbidity and mortality in feedlot cattle. Recently, bronchopneumonia with an interstitial pattern (BIP) was described as a concerning emerging feedlot lung d...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Veterinary Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-7381/10/2/113 |
| _version_ | 1797617834837147648 |
|---|---|
| author | Eduarda M. Bortoluzzi Paige H. Schmidt Rachel E. Brown Makenna Jensen Madeline R. Mancke Robert L. Larson Phillip A. Lancaster Brad J. White |
| author_facet | Eduarda M. Bortoluzzi Paige H. Schmidt Rachel E. Brown Makenna Jensen Madeline R. Mancke Robert L. Larson Phillip A. Lancaster Brad J. White |
| author_sort | Eduarda M. Bortoluzzi |
| collection | DOAJ |
| description | Bovine respiratory disease (BRD) and acute interstitial pneumonia (AIP) are the main reported respiratory syndromes (RSs) causing significant morbidity and mortality in feedlot cattle. Recently, bronchopneumonia with an interstitial pattern (BIP) was described as a concerning emerging feedlot lung disease. Necropsies are imperative to assist lung disease diagnosis and pinpoint feedlot management sectors that require improvement. However, necropsies can be logistically challenging due to location and veterinarians’ time constraints. Technology advances allow image collection for veterinarians’ asynchronous evaluation, thereby reducing challenges. This study’s goal was to develop image classification models using machine learning to determine RS diagnostic accuracy in right lateral necropsied feedlot cattle lungs. Unaltered and cropped lung images were labeled using gross and histopathology diagnoses generating four datasets: unaltered lung images labeled with gross diagnoses, unaltered lung images labeled with histopathological diagnoses, cropped images labeled with gross diagnoses, and cropped images labeled with histopathological diagnoses. Datasets were exported to create image classification models, and a best trial was selected for each model based on accuracy. Gross diagnoses accuracies ranged from 39 to 41% for unaltered and cropped images. Labeling images with histopathology diagnoses did not improve average accuracies; 34–38% for unaltered and cropped images. Moderately high sensitivities were attained for BIP (60–100%) and BRD (20–69%) compared to AIP (0–23%). The models developed still require fine-tuning; however, they are the first step towards assisting veterinarians’ lung diseases diagnostics in field necropsies. |
| first_indexed | 2024-03-11T08:01:26Z |
| format | Article |
| id | doaj.art-2e6e6ec074274851a0acb05152429dd1 |
| institution | Directory Open Access Journal |
| issn | 2306-7381 |
| language | English |
| last_indexed | 2024-03-11T08:01:26Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Veterinary Sciences |
| spelling | doaj.art-2e6e6ec074274851a0acb05152429dd12023-11-16T23:45:49ZengMDPI AGVeterinary Sciences2306-73812023-02-0110211310.3390/vetsci10020113Image Classification and Automated Machine Learning to Classify Lung Pathologies in Deceased Feedlot CattleEduarda M. Bortoluzzi0Paige H. Schmidt1Rachel E. Brown2Makenna Jensen3Madeline R. Mancke4Robert L. Larson5Phillip A. Lancaster6Brad J. White7Beef Cattle Institute, Kansas State University, Manhattan, KS 66506, USABeef Cattle Institute, Kansas State University, Manhattan, KS 66506, USABeef Cattle Institute, Kansas State University, Manhattan, KS 66506, USABeef Cattle Institute, Kansas State University, Manhattan, KS 66506, USABeef Cattle Institute, Kansas State University, Manhattan, KS 66506, USABeef Cattle Institute, Kansas State University, Manhattan, KS 66506, USABeef Cattle Institute, Kansas State University, Manhattan, KS 66506, USABeef Cattle Institute, Kansas State University, Manhattan, KS 66506, USABovine respiratory disease (BRD) and acute interstitial pneumonia (AIP) are the main reported respiratory syndromes (RSs) causing significant morbidity and mortality in feedlot cattle. Recently, bronchopneumonia with an interstitial pattern (BIP) was described as a concerning emerging feedlot lung disease. Necropsies are imperative to assist lung disease diagnosis and pinpoint feedlot management sectors that require improvement. However, necropsies can be logistically challenging due to location and veterinarians’ time constraints. Technology advances allow image collection for veterinarians’ asynchronous evaluation, thereby reducing challenges. This study’s goal was to develop image classification models using machine learning to determine RS diagnostic accuracy in right lateral necropsied feedlot cattle lungs. Unaltered and cropped lung images were labeled using gross and histopathology diagnoses generating four datasets: unaltered lung images labeled with gross diagnoses, unaltered lung images labeled with histopathological diagnoses, cropped images labeled with gross diagnoses, and cropped images labeled with histopathological diagnoses. Datasets were exported to create image classification models, and a best trial was selected for each model based on accuracy. Gross diagnoses accuracies ranged from 39 to 41% for unaltered and cropped images. Labeling images with histopathology diagnoses did not improve average accuracies; 34–38% for unaltered and cropped images. Moderately high sensitivities were attained for BIP (60–100%) and BRD (20–69%) compared to AIP (0–23%). The models developed still require fine-tuning; however, they are the first step towards assisting veterinarians’ lung diseases diagnostics in field necropsies.https://www.mdpi.com/2306-7381/10/2/113acute interstitial pneumoniabovine respiratory diseasebronchopneumonia with an interstitial patternfeedlot necropsyimage classification |
| spellingShingle | Eduarda M. Bortoluzzi Paige H. Schmidt Rachel E. Brown Makenna Jensen Madeline R. Mancke Robert L. Larson Phillip A. Lancaster Brad J. White Image Classification and Automated Machine Learning to Classify Lung Pathologies in Deceased Feedlot Cattle Veterinary Sciences acute interstitial pneumonia bovine respiratory disease bronchopneumonia with an interstitial pattern feedlot necropsy image classification |
| title | Image Classification and Automated Machine Learning to Classify Lung Pathologies in Deceased Feedlot Cattle |
| title_full | Image Classification and Automated Machine Learning to Classify Lung Pathologies in Deceased Feedlot Cattle |
| title_fullStr | Image Classification and Automated Machine Learning to Classify Lung Pathologies in Deceased Feedlot Cattle |
| title_full_unstemmed | Image Classification and Automated Machine Learning to Classify Lung Pathologies in Deceased Feedlot Cattle |
| title_short | Image Classification and Automated Machine Learning to Classify Lung Pathologies in Deceased Feedlot Cattle |
| title_sort | image classification and automated machine learning to classify lung pathologies in deceased feedlot cattle |
| topic | acute interstitial pneumonia bovine respiratory disease bronchopneumonia with an interstitial pattern feedlot necropsy image classification |
| url | https://www.mdpi.com/2306-7381/10/2/113 |
| work_keys_str_mv | AT eduardambortoluzzi imageclassificationandautomatedmachinelearningtoclassifylungpathologiesindeceasedfeedlotcattle AT paigehschmidt imageclassificationandautomatedmachinelearningtoclassifylungpathologiesindeceasedfeedlotcattle AT rachelebrown imageclassificationandautomatedmachinelearningtoclassifylungpathologiesindeceasedfeedlotcattle AT makennajensen imageclassificationandautomatedmachinelearningtoclassifylungpathologiesindeceasedfeedlotcattle AT madelinermancke imageclassificationandautomatedmachinelearningtoclassifylungpathologiesindeceasedfeedlotcattle AT robertllarson imageclassificationandautomatedmachinelearningtoclassifylungpathologiesindeceasedfeedlotcattle AT phillipalancaster imageclassificationandautomatedmachinelearningtoclassifylungpathologiesindeceasedfeedlotcattle AT bradjwhite imageclassificationandautomatedmachinelearningtoclassifylungpathologiesindeceasedfeedlotcattle |