Deep learning framework for vertebral heart size and cardiothoracic ratio estimation in dogs and cats using thoracic radiographs.

Abstract

Introduction: Heart disease is a major cause of mortality in aging dogs and cats, with cardiomegaly being the most frequent radiographic finding. While deep learning methods have shown potential in detecting and quantifying cardiomegaly, their integration into clinical veterinary practice remains limited due to challenges in interpretability and workflow alignment.

Methods: We developed a deep learning framework for the automatic estimation of Vertebral Heart Size (VHS) and Cardiothoracic Ratio (CTR) from thoracic radiographs of dogs and cats. A diverse dataset collected from two veterinary institutions was used. Segmentation of cardiac and thoracic anatomical regions was performed using Mask R-CNN, followed by automatic measurement of VHS and CTR. Model performance was evaluated against expert radiologist annotations.

Results: The proposed framework demonstrated strong agreement with manual evaluations. Pearson correlation coefficients reached 0.922 for VHS and 0.933 for CTR, with regression slopes close to unity and minimal intercepts. The method was validated on both lateral and ventrodorsal projections, confirming its versatility across common clinical views.

Discussion/conclusion: This work introduces an automated, robust approach for cardiac size assessment in dogs and cats. By supporting objective and reproducible measurements of VHS and CTR, the framework has potential to aid in the early detection and monitoring of heart disease, particularly in veterinary settings with limited access to specialized radiology expertise.