Feature Space Clustering for Trabecular Bone Segmentation

Trabecular bone structure has been shown to impact bone strength and fracture risk. In vitro, this structure can be measured by micro-computed tomography (micro-CT). For clinical use, it would be valuable if multi-slice computed tomography (MSCT) could be used to analyse trabecular bone structure. One important step in the analysis is image volume segmentation. Previous segmentation techniques have either been computer resource intensive or produced suboptimal results when used on MSCT data. This paper proposes a new segmentation method that tries to balance good results against computational complexity.

[1]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[3]  Örjan Smedby,et al.  Analysis of Skeletal Microstructure with Clinical Multislice CT , 2006, MICCAI.

[4]  Örjan Smedby,et al.  Correlations between fabric tensors computed on cone beam and microcomputed tomography images , 2014 .

[5]  M. Borga,et al.  Anisotropy Estimation of Trabecular Bone in Gray-Scale: Comparison Between Cone Beam and Micro Computed Tomography Data , 2015 .

[6]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[7]  Renato Natal Jorge,et al.  Developments in Medical Image Processing and Computational Vision , 2015 .

[8]  Örjan Smedby,et al.  Trabecular bone structure parameters from 3D image processing of clinical multi-slice and cone-beam computed tomography data , 2014, Skeletal Radiology.

[9]  Sharmila Majumdar,et al.  Analysis of Trabecular Bone Structure with Multidetector Spiral Computed Tomography in a Simulated Soft-Tissue Environment , 2007, Calcified Tissue International.

[10]  S Prohaska,et al.  Stereological measures of trabecular bone structure: comparison of 3D micro computed tomography with 2D histological sections in human proximal tibial bone biopsies , 2005, Journal of microscopy.

[11]  R. Müller,et al.  Vertebral body bone strength: the contribution of individual trabecular element morphology , 2012, Osteoporosis International.

[12]  John A. Hartigan,et al.  Clustering Algorithms , 1975 .

[13]  Örjan Smedby,et al.  Predicting Trabecular Bone Stiffness from Clinical Cone-Beam CT and HR-pQCT Data; an In Vitro Study Using Finite Element Analysis , 2016, PloS one.

[14]  Sharmila Majumdar,et al.  Multicenter precision of cortical and trabecular bone quality measures assessed by high‐resolution peripheral quantitative computed tomography , 2013, Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research.

[15]  M. Kleerekoper,et al.  The role of three-dimensional trabecular microstructure in the pathogenesis of vertebral compression fractures , 1985, Calcified Tissue International.

[16]  Renato Perucchio,et al.  A topology-preserving parallel 3D thinning algorithm for extracting the curve skeleton , 2003, Pattern Recognit..

[17]  D. Bi,et al.  A comparison study of image segmentation by clustering techniques , 1996, Proceedings of Third International Conference on Signal Processing (ICSP'96).

[18]  Françoise Peyrin,et al.  Automated 3D region growing algorithm based on an assessment function , 2002, Pattern Recognit. Lett..

[19]  Ralph Müller,et al.  Guidelines for assessment of bone microstructure in rodents using micro–computed tomography , 2010, Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research.

[20]  L. Mosekilde.  Vertebral structure and strengthIn vivo andIn vitro , 2005, Calcified Tissue International.

[21]  O. Smedby,et al.  Trabecular bone histomorphometric measurements and contrast-to-noise ratio in CBCT. , 2014, Dento maxillo facial radiology.

[22]  P. Rüegsegger,et al.  The ability of three-dimensional structural indices to reflect mechanical aspects of trabecular bone. , 1999, Bone.