Details

Autor(en) / Beteiligte

• Presbítero-Espinosa, Gerardo
• Quiroga-Arias, José
• Hernández-Ferruzca, Inés
• González-Pérez, Bibiana
• Mora-Núñez, Carlos
• Macías-Ávila, Eduardo
• Gómez-Ovalle, Álvaro
• Mendoza-Buenrostro, Christian
• Hernandez-Rodriguez, Marco A. L.

Titel

Deep Learning and Finite Element Method Towards the Application of Microfracture Analysis for Prevention of Fatigue Fractures in Bones

Ist Teil von

• TMS 2022 151st Annual Meeting & Exhibition Supplemental Proceedings, p.748-758

Ort / Verlag

Cham: Springer International Publishing

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Our current work aims to confirm the identification and growth modalities of microfractures on X-ray computed tomography images. We worked in the automatic identification by deep learningDeep learning modalities and finite element analysisFinite element analysis in microfractures developed in sections of cortical boneBone microdamage tissue. We achieved a modality for detecting microfractures through image processing with a convolutional neural network. Additionally, it was possible to create a meshwork of the microstructure and develop finite elementFinite element analysis models by differentiating the phases. The studies presented will enable us to define trends in the development of fatigue fracturesFatigue fractures based on the growth of microfractures. We previously described the distribution of microfracture lengths using the two-parameter WeibullWeibull distribution equation towards developing theoretical models to prevent fractures and boneBone microdamage injuries due to fatigue. These affirmations will converge soon with the results currently obtained, confirming a methodology towards precise prediction procedures for the prevention of fatigue fracturesFatigue fracturesin boneBone microdamage and biomedical materials through the development of microfractures and the use of non-destructive tests.