Share Email Print
cover

Proceedings Paper

Predicting the biomechanical strength of proximal femur specimens with bone mineral density features and support vector regression
Author(s): Markus B. Huber; Chien-Chun Yang; Julio Carballido-Gamio; Jan S. Bauer; Thomas Baum; Mahesh B. Nagarajan; Felix Eckstein; Eva Lochmüller; Sharmila Majumdar; Thomas M. Link; Axel Wismüller
Format Member Price Non-Member Price
PDF $15.00 $18.00

Paper Abstract

To improve the clinical assessment of osteoporotic hip fracture risk, recent computer-aided diagnosis systems explore new approaches to estimate the local trabecular bone quality beyond bone density alone to predict femoral bone strength. In this context, statistical bone mineral density (BMD) features extracted from multi-detector computed tomography (MDCT) images of proximal femur specimens and different function approximations methods were compared in their ability to predict the biomechanical strength. MDCT scans were acquired in 146 proximal femur specimens harvested from human cadavers. The femurs' failure load (FL) was determined through biomechanical testing. An automated volume of interest (VOI)-fitting algorithm was used to define a consistent volume in the femoral head of each specimen. In these VOIs, the trabecular bone was represented by statistical moments of the BMD distribution and by pairwise spatial occurrence of BMD values using the gray-level co-occurrence (GLCM) approach. A linear multi-regression analysis (MultiReg) and a support vector regression algorithm with a linear kernel (SVRlin) were used to predict the FL from the image feature sets. The prediction performance was measured by the root mean square error (RMSE) for each image feature on independent test sets; in addition the coefficient of determination R2 was calculated. The best prediction result was obtained with a GLCM feature set using SVRlin, which had the lowest prediction error (RSME = 1.040±0.143, R2 = 0.544) and which was significantly lower that the standard approach of using BMD.mean and MultiReg (RSME = 1.093±0.133, R2 = 0.490, p<0.0001). The combined sets including BMD.mean and GLCM features had a similar or slightly lower performance than using only GLCM features. The results indicate that the performance of high-dimensional BMD features extracted from MDCT images in predicting the biomechanical strength of proximal femur specimens can be significantly improved by using support vector regression.

Paper Details

Date Published: 23 February 2012
PDF: 7 pages
Proc. SPIE 8315, Medical Imaging 2012: Computer-Aided Diagnosis, 83151W (23 February 2012); doi: 10.1117/12.911402
Show Author Affiliations
Markus B. Huber, Univ. of Rochester Medical Ctr. (United States)
Chien-Chun Yang, Univ. of Rochester Medical Ctr. (United States)
Julio Carballido-Gamio, Univ. of California, San Francisco (United States)
Jan S. Bauer, Technische Univ. München (Germany)
Thomas Baum, Technische Univ. München (Germany)
Mahesh B. Nagarajan, Univ. of Rochester Medical Ctr. (United States)
Felix Eckstein, Paracelsus Medical Univ. Salzburg (Austria)
Eva Lochmüller, Paracelsus Medical Univ. Salzburg (Austria)
Sharmila Majumdar, Univ. of California, San Francisco (United States)
Thomas M. Link, Univ. of California, San Francisco (United States)
Axel Wismüller, Univ. of Rochester Medical Ctr. (United States)


Published in SPIE Proceedings Vol. 8315:
Medical Imaging 2012: Computer-Aided Diagnosis
Bram van Ginneken; Carol L. Novak, Editor(s)

© SPIE. Terms of Use
Back to Top