The prediction of hip fracture is an important clinical aim. Finite element simulations provide data related to the mechanical response of the bone to the event of fall. However, the selection of the critical zones to analyse is often based on visual identification of the fracture zones. The over-estimation of such critical zone introduce noise in the results obtain by simulations. During this project we want to adapt a matlab tool based on random field theory [1] to automatically identify regions/elements with statistical differences.
These elements selected will be used for statistical analysis that lead to hip fracture classification and prediction [2].

[1]    M. Brett, W. Penny, S. Kiebel, 14. Introduction to Random Field Theory, Hum. Brain Funct. (2003) 1–23. doi:10.1049/sqj.1969.0076.

[2]    C. Ruiz-Wills, A.L. Olivares, S. Tassani, M. Ceresa, V. Zimmer, M.A. González Ballester, L.M. del Río, L. Humbert, J. Noailly, 3D patient-specific finite element models of the proximal femur based on DXA towards the classification of fracture and non-fracture cases, Bone. 121 (2019) 89–99. doi:10.1016/j.bone.2019.01.