Interactive graph-cut segmentation for fast creation of finite element models from clinical ct data for hip fracture prediction

Yves Pauchard*, Thomas Fitze, Diego Browarnik, Amiraslan Eskandari, Irene Pauchard, William Enns-Bray, Halldór Pálsson, Sigurdur Sigurdsson, Stephen J. Ferguson, Tamara B. Harris, Vilmundur Gudnason, Benedikt Helgason

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

34 Citations (Scopus)


In this study, we propose interactive graph cut image segmentation for fast creation of femur finite element (FE) models from clinical computed tomography scans for hip fracture prediction. Using a sample of N = 48 bone scans representing normal, osteopenic and osteoporotic subjects, the proximal femur was segmented using manual (gold standard) and graph cut segmentation. Segmentations were subsequently used to generate FE models to calculate overall stiffness and peak force in a sideways fall simulations. Results show that, comparable FE results can be obtained with the graph cut method, with a reduction from 20 to 2–5 min interaction time. Average differences between segmentation methods of 0.22 mm were not significantly correlated with differences in FE derived stiffness (R2 = 0.08, p = 0.05) and weakly correlated to differences in FE derived peak force (R2 = 0.16, p = 0.01). We further found that changes in automatically assigned boundary conditions as a consequence of small segmentation differences were significantly correlated with FE derived results. The proposed interactive graph cut segmentation software MITK-GEM is freely available online at

Original languageEnglish
Pages (from-to)1693-1703
Number of pages11
JournalComputer Methods in Biomechanics and Biomedical Engineering
Issue number16
Publication statusPublished - 9 Dec 2016

Bibliographical note

Publisher Copyright:
© 2016 Informa UK Limited, trading as Taylor & Francis Group.

Other keywords

  • clinical computed tomography
  • femur segmentation
  • Hip fracture prediction
  • image segmentation
  • image-based finite element modeling


Dive into the research topics of 'Interactive graph-cut segmentation for fast creation of finite element models from clinical ct data for hip fracture prediction'. Together they form a unique fingerprint.

Cite this