Fast and Robust Femur Segmentation from Computed Tomography Images for Patient-Specific Hip Fracture Risk Screening

TL;DR

This paper introduces a deep learning-based method for fully automated, accurate, and rapid segmentation of the proximal femur from CT images, facilitating improved hip-fracture risk screening.

Contribution

A novel deep neural network approach that automates femur segmentation from CT scans, reducing manual effort and increasing speed for clinical risk assessment.

Findings

Achieved high accuracy in femur segmentation on 1147 CT scans.

Demonstrated potential for clinical application in hip-fracture risk screening.

Streamlined the segmentation process for large datasets.

Abstract

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.