An automated vertebral heart scale measurement tool based on deep learning: Facilitating screening for prevention of canine cardiomegaly.

Abstract

Automatically measuring the Vertebral Heart Scale (VHS) from canine thoracic X-ray images is an effective approach for the early screening and prevention of cardiomegaly. Establishing automated and precise measurement tools is crucial for advancing population-based research on canine cardiac health. In this study, an integrated framework based on an improved U-Net architecture (SWA-UNet) and YOLOv11 is proposed for precise heart segmentation and key point detection to enable automated and accurate VHS calculation. It provides an efficient, objective, and repeatable auxiliary diagnostic tool for clinical practice, significantly enhancing the standardization of cardiac assessment and diagnostic efficiency. The method achieved a mean Intersection over Union of 95.34 % and a Dice coefficient of 98.20 % for heart segmentation. For key point detection, YOLOv11 attained a precision rate of 96.50 % and a recall rate of 95.20 % for the T3-T10 vertebrae, demonstrating high detection accuracy and reliability. Ultimately, the predicted VHS values showed a strong linear association with manual measurements, with a Pearson correlation coefficient of 0.8985. Furthermore, Bland-Altman analysis indicated that the automated system maintains high consistency with expert assessments, characterized by a minimal mean difference of -0.0696 cm. This result fully validates the effectiveness of this method in addressing challenges such as low-contrast images, blurred boundaries, and structural overlaps. As an auxiliary tool for veterinary radiologists, this method demonstrates great potential and can contribute to efficient and standardized assessment of canine heart diseases.