Using Neural Networks to Predict the Trabecular Arrangement in the Proximal Femur

• Type: Article in International Conference Proceedings Book
• Date: 2023

Authors

Pais, I (Author) Other; Jorge Lino (Author) FEUP; Belinha, J (Author) Other

Conference proceedings International

Title: Lecture Notes in Bioengineering

Pages: 41-48

10th Congress of the Portuguese Society of Biomechanics, CNB 2023

Figueira da Foz, 5 May 2023 through 6 May 2023

Indexing

Scopus - 0 Citations

Other information

Authenticus ID: P-010-6E6

DOI: 10.1007/978-3-031-47790-4_4

Abstract (EN): Differences in the anatomy of this bone occur naturally in the population and will lead to different structural responses which then lead to different trabecular bone arrangements. These can be predicted through computational analysis which the literature has shown to deliver accurate results in agreement to medical imaging. Machine learning techniques can be combined with the FEM to reduce the computational cost associated with the prediction of the remodelling process. In this work it is shown that neural networks achieved accurate solutions in a fraction of the time being the main disadvantage the need to gather high volumes of data. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 7