Pérez-Cano, Francisco DanielParra-Cabrera, GemaCamacho-García, RubénJiménez, Juan JoséMarco, JulioPatow, Gustavo2024-06-032024-06-032024978-3-03868-261-5https://doi.org/10.2312/ceig.20241140https://diglib.eg.org/handle/10.2312/ceig20241140The extraction of the main features of a fractured bone area enables subsequent virtual reproduction for bone simulations. Exploring the fracture zone for other applications remains largely unexplored in current research. Recreating and analyzing fracture patterns has direct applications in medical training programs for traumatologists, automatic bone fracture reduction algorithms, and diagnostics. Furthermore, pattern classification aids in establishing treatment guidelines that specialists can follow during the surgical process. This paper focuses on the process of obtaining an accurate representation of bone fractures, starting with computed tomography scans, and subsequently classifying these patterns using a convolutional neural network. The proposed methodology aims to streamline the extraction and classification of fractures from clinical cases, contributing to enhanced diagnosis and medical simulation applications.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Artificial intelligence; Machine learning; Computer graphicsCCS ConceptsComputing methodologies → Artificial intelligenceMachine learningComputer graphics10.2312/ceig.202411408 pages