Deep learning framework for vertebral heart size and cardiothoracic ratio estimation in dogs and cats using thoracic radiographs
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.
Authors
- Daniel J. Mayor (ORCID: https://orcid.org/0000-0002-1295-0041)
- Arnau Oliver (ORCID: https://orcid.org/0000-0002-0115-0647)
- Núria Puig (ORCID: https://orcid.org/0000-0002-4699-3162)
- Xavier Cufí (ORCID: https://orcid.org/0000-0003-2845-7304)
- Anthony Elson
- Xavier Lladó (ORCID: https://orcid.org/0000-0003-2777-3479)
- S. T. C. Campos (ORCID: https://orcid.org/0000-0001-8930-9554)
- Robert Martí (ORCID: https://orcid.org/0000-0002-8080-2710)
- Jordi Freixenet (ORCID: https://orcid.org/0000-0001-9524-3328)
- Francisco Javier Moreno Hernández (ORCID: https://orcid.org/0000-0002-2520-892X)
- Elena López (ORCID: https://orcid.org/0000-0001-9524-2018)
- Paula Martínez
- Habtamu Tilahun Mekonnen
- Jorge Quilis
Institutions
- Universitat de Girona (ES)
- Fundación para el Fomento de la Investigación Sanitaria y Biomédica de la Comunitat Valenciana (ES)
- Biomechanics Institute of Valencia (ES)
- Associação Brasileira de Oncologia Veterinária (BR)
Publication Details
- Journal
- Frontiers in Veterinary Science
- Published
- 2025-09-19
- DOI
- https://doi.org/10.3389/fvets.2025.1612338
- Primary Topic
- Cardiovascular Conditions and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00