Image Classification and Automated Machine Learning to Classify Lung Pathologies in Deceased Feedlot Cattle

SIMPLE SUMMARY: Respiratory syndromes are the main cause of ill and deceased animals in the feedlot industry. The correct diagnostic of lung lesions is important to prevent and adapt managements strategies within feedyards. The necropsy of deceased animals is veterinarians’ main tool for postmortem diagnoses; however, it is prone to time and location constraints. Necropsy image analysis can be used to overcome these challenges. Image classification models using machine learning were developed to determine respiratory syndromes’ diagnostic accuracy in right lateral necropsied feedlot cattle lungs. Models performed better at classifying bovine respiratory disease and bronchopneumonia with an interstitial pattern compared to acute interstitial pneumonia. Models developed still require fine-tuning; however, they present potential to assist veterinarians in diagnosing lung diseases during field necropsies. ABSTRACT: 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.