Unsupervised clustering based coronary artery segmentation
This clustering-based segmentation approach offers a robust framework that can be easily integrated into clinical workflows, improving both accuracy and efficiency in coronary artery analysis. Additionally, the ability to visualize clusters and graphs from any cross-section enhances the method's explainability, providing clinicians with deeper insights into vascular structures. The study demonstrates the potential of clustering algorithms for improving segmentation performance in coronary artery imaging.
Authors
- María Bastos-Fernández (ORCID: https://orcid.org/0000-0002-7088-5858)
- Manuel Villa (ORCID: https://orcid.org/0000-0001-8968-8136)
- Brais Díaz‐Fernández
- José Ramón González‐Juanatey (ORCID: https://orcid.org/0000-0001-9681-3388)
- Diego López‐Otero (ORCID: https://orcid.org/0000-0003-2810-3979)
- Belén Serrano-Antón (ORCID: https://orcid.org/0000-0001-9328-9525)
- Alberto P. Muñuzuri (ORCID: https://orcid.org/0000-0002-0579-9347)
- Santiago Paramés-Estévez (ORCID: https://orcid.org/0000-0003-0747-0761)
- Alberto Otero-Cacho (ORCID: https://orcid.org/0000-0003-1044-891X)
- Santiago Pendón-Minguillón
Institutions
- Universidade de Santiago de Compostela (ES)
- Centro de Supercomputación de Galicia (ES)
- Centro de Investigación en Red en Enfermedades Cardiovasculares (ES)
- Centro de Investigación Biomédica en Red (ES)
- Instituto de Investigación Sanitaria de Santiago (ES)
- Complejo Hospitalario de Pontevedra (ES)
Publication Details
- Journal
- BioData Mining
- Published
- 2025-03-07
- DOI
- https://doi.org/10.1186/s13040-025-00435-y
- Citations
- 2
- Primary Topic
- Cerebrovascular and Carotid Artery Diseases
- Type
- article
- Field-Weighted Citation Impact
- 3.04
Funders
- Ministerio de Ciencia e Innovación