Artificial Intelligence in Veterinary Diagnostic Imaging: A Narrative Review of the State of the Art and its Applications.
Authors
Affiliations (6)
Affiliations (6)
- Clinica Veterinaria San Giorgio (CVSG), Via Vecchia Pentimele, 63, 89121, Reggio Calabria, Italy. Electronic address: [email protected].
- Department of Veterinary Sciences, University of Messina, Polo Universitario dell'Annunziata, Via Palatucci 13, 98168 Messina, Italy. Electronic address: [email protected].
- Institute of Clinical Physiology, National Research Council, Via Vallone Petrara, snc, 89124, Reggio Calabria, Italy; Department of Mathematics and Computer Science, Physical Sciences and Earth Sciences, University of Messina, Viale Ferdinando Stagno d'Alcontres 31, 98166, Messina, Italy. Electronic address: [email protected].
- Department of Veterinary Sciences, University of Messina, Polo Universitario dell'Annunziata, Via Palatucci 13, 98168 Messina, Italy. Electronic address: [email protected].
- Institute of Clinical Physiology, National Research Council, Via Vallone Petrara, snc, 89124, Reggio Calabria, Italy. Electronic address: [email protected].
- Institute of Clinical Physiology, National Research Council, Via Vallone Petrara, snc, 89124, Reggio Calabria, Italy. Electronic address: [email protected].
Abstract
Artificial intelligence (AI) is transforming veterinary diagnostic imaging, improving the accuracy, speed, and efficiency of complex data analysis. This emerging field could respond to the growing demand for radiologists, optimizing workflow and automating image interpretation. This narrative review explores the current state of AI use in veterinary diagnostics. We reviewed recent literature focusing on the application of AI in medical imaging, including magnetic resonance, computed tomography, cone beam computed tomography, ultrasound, and radiography, with a focus on the animal species involved, the target organs and tissues, and the diseases identified with AI. The literature search showed an extensive use of these models in dogs, followed by mice. These models have specially proven effective in auto segmentation of magnetic resonance images and the classification of thoracic lesions and cardiac pathologies using radiography. In conclusion, AI tools show potential in veterinary diagnostic imaging, offering numerous applications in this field.