Osteoporosis is a common bone disease that increases the risk of bone fracture. Hip-fracture risk screening methods based on finite element analysis depend on segmented computed tomography (CT) images; however, current femur segmentation methods require manual delineations of large data sets. Here we propose a deep neural network for fully automated, accurate, and fast segmentation of the proximal femur from CT. Evaluation on a set of 1147 proximal femurs with ground truth segmentations demonstrates that our method is apt for hip-fracture risk screening, bringing us one step closer to a clinically viable option for screening at-risk patients for hip-fracture susceptibility.
@article{arxiv.2204.09575,
title = {Fast and Robust Femur Segmentation from Computed Tomography Images for Patient-Specific Hip Fracture Risk Screening},
author = {Pall Asgeir Bjornsson and Alexander Baker and Ingmar Fleps and Yves Pauchard and Halldor Palsson and Stephen J. Ferguson and Sigurdur Sigurdsson and Vilmundur Gudnason and Benedikt Helgason and Lotta Maria Ellingsen},
journal= {arXiv preprint arXiv:2204.09575},
year = {2022}
}
Comments
This article has been accepted for publication in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, published by Taylor & Francis