Regular Articles

Improving bone strength prediction in human proximal femur specimens through geometrical characterization of trabecular bone microarchitecture and support vector regression

[+] Author Affiliations
Chien-Chun Yang, Mahesh B. Nagarajan, Markus B. Huber

University of Rochester, Departments of Imaging Sciences and Biomedical Engineering, Rochester, New York 14627

Julio Carballido-Gamio, Sharmila Majumdar, Thomas M. Link

University of California San Francisco, Musculoskeletal and Quantitative Imaging Research, Department of Radiology and Biomedical Imaging, San Francisco, California 94143

Jan S. Bauer, Thomas Baum

Technische Universität München, Institut Für Röntgendiagnostik, Munich, München 85748, Germany

Felix Eckstein, Eva Lochmüller

Paracelsus Medical University Salzburg, Institute of Anatomy and Musculoskeletal Research, Salzburg 5020, Austria

Axel Wismüller

University of Rochester, Departments of Imaging Sciences and Biomedical Engineering, Rochester, New York 14627

University of Munich, Department of Radiology, München 80539, Germany

J. Electron. Imaging. 23(1), 013013 (Feb 04, 2014). doi:10.1117/1.JEI.23.1.013013
History: Received July 16, 2013; Revised December 1, 2013; Accepted January 9, 2014
Text Size: A A A

Abstract.  We investigate the use of different trabecular bone descriptors and advanced machine learning techniques to complement standard bone mineral density (BMD) measures derived from dual-energy x-ray absorptiometry (DXA) for improving clinical assessment of osteoporotic fracture risk. For this purpose, volumes of interest were extracted from the head, neck, and trochanter of 146 ex vivo proximal femur specimens on multidetector computer tomography. The trabecular bone captured was characterized with (1) statistical moments of the BMD distribution, (2) geometrical features derived from the scaling index method (SIM), and (3) morphometric parameters, such as bone fraction, trabecular thickness, etc. Feature sets comprising DXA BMD and such supplemental features were used to predict the failure load (FL) of the specimens, previously determined through biomechanical testing, with multiregression and support vector regression. Prediction performance was measured by the root mean square error (RMSE); correlation with measured FL was evaluated using the coefficient of determination R2. The best prediction performance was achieved by a combination of DXA BMD and SIM-derived geometric features derived from the femoral head (RMSE: 0.869±0.121, R2: 0.68±0.079), which was significantly better than DXA BMD alone (RMSE: 0.948±0.119, R2: 0.61±0.101) (p<104). For multivariate feature sets, SVR outperformed multiregression (p<0.05). These results suggest that supplementing standard DXA BMD measurements with sophisticated femoral trabecular bone characterization and supervised learning techniques can significantly improve biomechanical strength prediction in proximal femur specimens.

Figures in this Article
© 2014 SPIE and IS&T

Topics

Bone

Citation

Chien-Chun Yang ; Mahesh B. Nagarajan ; Markus B. Huber ; Julio Carballido-Gamio ; Jan S. Bauer, et al.
"Improving bone strength prediction in human proximal femur specimens through geometrical characterization of trabecular bone microarchitecture and support vector regression", J. Electron. Imaging. 23(1), 013013 (Feb 04, 2014). ; http://dx.doi.org/10.1117/1.JEI.23.1.013013


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.