APPLICATION OF ARTIFICIAL INTELLIGENCE IN THE MEASUREMENT OF VERTEBRAL HEART SIZE (VHS) IN DOGS

Abstract

Vertebral Heart Size (VHS) is a widely used radiographic parameter for assessing the cardiac silhouette in dogs and is essential for diagnosing cardiomegaly. Although manual measurement of VHS is well-established in clinical practice, it may be influenced by observer subjectivity and technical variability. In this context, Artificial Intelligence (AI) is being explored as an innovative tool in veterinary radiology, offering potential for automation, standardization, and increased efficiency in thoracic image
analysis. Recent advances in machine learning algorithms have shown promising results in VHS measurement, with accuracy levels comparable to those achieved by specialists. However, the clinical adoption of these technologies still faces challenges related to validation and applicability across different scenarios. Terefore, this review aims to critically analyze the application of AI in the measurement of VHS in dogs, highlighting the advances, limitations, and future perspectives.