Artificial intelligence in veterinary diagnostic imaging: A literature review

Hennessey, Erin; DiFazio, Matthew R.; Hennessey, Ryan; Cassel, Nicky

doi:10.1111/vru.13163

Cited by 27 publications

(40 citation statements)

References 76 publications

(227 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With advances in technology, digital storage capabilities, and accessibility, images are being used as a diagnostic tool when veterinarians are not present at the time of animal necropsy, especially due to time and location constraints [ 19 ]. More recently, image classification and automated machine learning have been implemented in human and veterinary medicine as auxiliary diagnostic tools [ 20 , 21 , 24 , 25 ]. Similar technology was applied to identify postmortem organ images in humans, and it is expected to assist human disease diagnosis in the near future [ 26 ].…”

Section: Discussionmentioning

confidence: 99%

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

Bortoluzzi

Schmidt

Brown

et al. 2023

Veterinary Sciences

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Bortoluzzi

Schmidt

Brown

et al. 2023

Veterinary Sciences

View full text Add to dashboard Cite

show abstract

“…In veterinary medicine, as well as in humans, automated technology for wound management could help to quickly assess the severity of an open wound that may require prompt intervention in acute injuries [ 7 , 8 , 9 ]; likewise, it may objectify the state of the wound at the time of clinical presentation. Automated solutions for wound management may help in the monitoring of the subsequent wound healing process.…”

Section: Introductionmentioning

confidence: 99%

Automated Wound Image Segmentation: Transfer Learning from Human to Pet via Active Semi-Supervised Learning

Buschi

Curti

Cola

et al. 2023

Animals

View full text Add to dashboard Cite

Wound management is a fundamental task in standard clinical practice. Automated solutions already exist for humans, but there is a lack of applications regarding wound management for pets. Precise and efficient wound assessment is helpful to improve diagnosis and to increase the effectiveness of treatment plans for chronic wounds. In this work, we introduced a novel pipeline for the segmentation of pet wound images. Starting from a model pre-trained on human-based wound images, we applied a combination of transfer learning (TL) and active semi-supervised learning (ASSL) to automatically label a large dataset. Additionally, we provided a guideline for future applications of TL+ASSL training strategy on image datasets. We compared the effectiveness of the proposed training strategy, monitoring the performance of an EfficientNet-b3 U-Net model against the lighter solution provided by a MobileNet-v2 U-Net model. We obtained 80% of correctly segmented images after five rounds of ASSL training. The EfficientNet-b3 U-Net model significantly outperformed the MobileNet-v2 one. We proved that the number of available samples is a key factor for the correct usage of ASSL training. The proposed approach is a viable solution to reduce the time required for the generation of a segmentation dataset.

show abstract

“…Multiple recent studies have demonstrated artificial intelligence's (AI) ability to evaluate a range of canine thoracic radiographic features such as cardiac size, pulmonary patterns, and pleural changes. [1][2][3][4][5][6][7][8][9][10][11] Although the practicality of AI in veterinary diagnostic imaging is not yet fully established, several commercial AI platforms are currently available to the practitioner. Further independent scrutiny of these tools is necessary to validate these products, in large part so that practitioners can build confidence in their application.…”

Section: Introductionmentioning

confidence: 99%

Performance of a commercially available artificial intelligence software for the detection of confirmed pulmonary nodules and masses in canine thoracic radiography

Pomerantz,

Solano,

Kalosa‐Kenyon

2023

Vet Radiology Ultrasound

View full text Add to dashboard Cite

Advancements in the field of artificial intelligence (AI) are modest in veterinary medicine relative to their substantial growth in human medicine. However, interest in this field is increasing, and commercially available veterinary AI products are already on the market. In this retrospective, diagnostic accuracy study, the accuracy of a commercially available convolutional neural network AI product (Vetology AI®) is assessed on 56 thoracic radiographic studies of pulmonary nodules and masses, as well as 32 control cases. Positive cases were confirmed to have pulmonary pathology consistent with a nodule/mass either by CT, cytology, or histopathology. The AI software detected pulmonary nodules/masses in 31 of 56 confirmed cases and correctly classified 30 of 32 control cases. The AI model accuracy is 69.3%, balanced accuracy 74.6%, F1‐score 0.7, sensitivity 55.4%, and specificity 93.75%. Building on these results, both the current clinical relevance of AI and how veterinarians can be expected to use available commercial products are discussed.

show abstract

Artificial intelligence in veterinary diagnostic imaging: A literature review

Cited by 27 publications

References 76 publications

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

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

Automated Wound Image Segmentation: Transfer Learning from Human to Pet via Active Semi-Supervised Learning

Performance of a commercially available artificial intelligence software for the detection of confirmed pulmonary nodules and masses in canine thoracic radiography

Contact Info

Product

Resources

About