Computer-Aided Diagnosis for Lung Lesion in Companion Animals from X-ray Images Using Deep Learning Techniques

Artificial intelligence in veterinary diagnostic imaging: A literature review

“…These maps were compared against similar, manually produced maps created by radiologists, demonstrating similarities between the regions that the NN and the radiologists both identified as abnormal and used to classify the lung pattern. 42 The higher accuracy achieved for alveolar patterns in this study is similar to human reader performance, in which identification of an alveolar pattern is agreed upon more often amongst radiologists than interstitial or bronchial patterns. 51 Ott et al 43 41 These results are reflective of clinical reality in which normal and abnormal lungs are relatively easy to differentiate, while determining the underlying cause for pulmonary parenchymal changes based on radiographs is often challenging, necessitating multiple differentials.…”

“…Notably, this study included class activation maps (heatmaps) and bounding boxes that identified the spatial areas in the radiographs that influenced the NN's ultimate decision. These maps were compared against similar, manually produced maps created by radiologists, demonstrating similarities between the regions that the NN and the radiologists both identified as abnormal and used to classify the lung pattern 42 . The higher accuracy achieved for alveolar patterns in this study is similar to human reader performance, in which identification of an alveolar pattern is agreed upon more often amongst radiologists than interstitial or bronchial patterns 51 …”

“…Arsomngern et al 42 Notably, this study included class activation maps (heatmaps) and bounding boxes that identified the spatial areas in the radiographs that influenced the NN's ultimate decision. These maps were compared against similar, manually produced maps created by radiologists, demonstrating similarities between the regions that the NN and the radiologists both identified as abnormal and used to classify the lung pattern.…”

RapidRead: Global Deployment of State-of-the-art Radiology AI for a Large Veterinary Teleradiology Practice

“…The lack of external validation, limited data size, narrow use case, and lack of deployment insights diminish real-world applicability. Another retrospective study was recently reported leveraging both canine and feline thoracic radiographs with two views (frontal and lateral) and three clinical labels in a dataset of 2800 images reported less than state-of-the-art performance compared to human radiology machine learning clinical models [2] of comparable scale. The fact that the dataset presented in this paper is thousand orders of magnitude larger than those in aforementioned studies leads to significant gains in generalizability and robustness effects.…”

Classification of Canine Maturity and Bone Fracture Time Based on X-Ray Images of Long Bones

“…Arsomngern et al investigated a lung lesion problem in pets using 2862 thoracic X-ray images taken from both dogs and cats. The results showed that CNN accurately identified the lesion in 79.6% of the cases [12].…”