Artificial intelligence and machine learning have been increasingly used in the medical imaging field in the past few years. The evaluation of medical images is very subjective and complex, and therefore the application of artificial intelligence and deep learning methods to automatize the analysis process would be very beneficial. A lot of researchers have been applying these methods to image analysis diagnosis, developing software capable of assisting veterinary doctors or radiologists in their daily practice. This article details the main methodologies used to develop software applications on machine learning and how veterinarians with an interest in this field can benefit from such methodologies. The main goal of this study is to offer veterinary professionals a simple guide to enable them to understand the basics of artificial intelligence and machine learning and the concepts such as deep learning, convolutional neural networks, transfer learning, and the performance evaluation method. The language is adapted for medical technicians, and the work already published in this field is reviewed for application in the imaging diagnosis of different animal body systems: musculoskeletal, thoracic, nervous, and abdominal.

Background: Ultrasound-guided quadratus lumborum block (QLB) and sacrococcygeal epidural anaesthesia (ScE) have been used for neutering cats, providing effective pain relief. Objectives: To compare the effects of the QLB with those of ScE in cats undergoing ovariectomies. Methods: Feral cats undergoing ovariectomy were premedicated with dexmedetomidine (20 μg kg⁻¹) and methadone (0.2 mg kg⁻¹) intramuscularly. Anaesthesia was induced with 2–4 mg kg⁻¹ of propofol intravenously and maintained with isoflurane in oxygen. The cats were randomly allocated to the groups QLB (bilateral QLB with 0.4 mL kg⁻¹ of 0.25% bupivacaine) and ScE (0.3 mL kg⁻¹ of 0.25% bupivacaine). Hemodynamic data and analgesia rescue were collected at four intraoperative periods. The pain scale and motor block were assessed in both groups during the postoperative period. Results: The ScE results in increased hypotension, prolonged extubation time, and higher postoperative motor block than the QLB (p < 0.05). The QLB and ScE groups required a similar number of intraoperative rescues and presented the same postoperative pain scale classification. Conclusions: The QLB with 0.25% bupivacaine is a potential alternative to ScE with 0.25% bupivacaine in perioperative pain management in elective cat ovariectomy. The QLB promoted less hypotension and postoperative motor block when compared with the ScE group.

Elbow incongruity plays an important role in the development of elbow dysplasia and its diagnosis can be challenging. The objectives of this systematic review were to discuss elbow biomechanics and recent advances in the assessment of incongruity, to revise the diagnostic protocols suggested, debate advantages and disadvantages of measurements proposed to characterize the joint and improve screening.In spite of advances in the understanding of elbow incongruity, the exact mechanisms involved are not fully elucidated. The elbow is a complex joint and structures in contact differ in different phases of the gait cycle. Advances in the biomechanical field allowed new discoveries and a physiological type of incongruity was described. The next challenge is to unravel the dynamic incongruity. Radiology and computed tomography (CT) are nowadays the imaging tools more applied in clinical practice to quantify incongruity. But a CT standardized screening protocol is required. Most reported findings of incongruity were increased articular joint spaces. The proximity of joint structures and standardization of elbow positioning are identified as the main obstacles to a good interpretation. This review serves to highlight controversy between physiological types of cartilage covering described and pathological changes reported in arthroscopic studies. Radioulnar incongruity was reported more often than humeroulnar incongruity, yet prevalence studies are lacking. Sensitive and reproducible methodologies are in development, which seem primordial to assess the phenotypic heterogeneity.