Statistical and Physical Micro-feature-Based Segmentation of Cortical Bone Images Using Artificial Intelligence

  • Ilige S. Hage
  • Ramsey F. Hamade
Conference paper
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 21)


At the micro scale, dense cortical bone is structurally comprised mainly of Osteon units that contain Haversian canals, lacunae, and concentric lamellae solid matrix. Osteons are separated from each other by cement lines. These micro-features of cortical bone are typically captured in digital histological images. In this work, we aim to automatically segment these features utilizing optimized pulse coupled neural networks (PCNN). These networks are artificially intelligent (AI) tools that can model neural activity and produce a series of binary pulses (images) representing the segmentations of an image. The methodology proposed combines three separately used methods for image segmentation which are: pulse coupled neural network (PCNN), particle swarm optimization (PSO) and adaptive threshold (AT). Two segmentation attributes were used: one statistical and another based on the physical attributes of the micro-features. The first, statistical-based segmentation method, where cost functions based on entropy (probability of gray values) considerations are calculated. For the physical-based segmentation method, cost functions based on geometrical attributes associated with micro-features such as relative size (i.e., elliptical) are used as targets for the fitness function of network optimization. Both of these methods were found to result in good quality segregation of the micro-features of micro-images of bovine cortical bone.


Bone image segmentation Micro-structure Neural networks Optimization Geometry Statistics 


  1. 1.
    Zoroofi R A, Nishii T, Sato Y, Sugano N, Yoshikawa H, Tamura S (2001) Segmentation of avascular necrosis of the femoral head using 3-D MR images. Comput Med Imaging Graph 25: 511Google Scholar
  2. 2.
    Zoroofi R A, Sato Y, Nishii T, Sugano N, Yoshikawa H, Tamura S (2004) Automated segmentation of necrotic femoral head from 3D MR data. Comput Med Imaging Graph 28: 267–278Google Scholar
  3. 3.
    Bourgeat P, Fripp J, Stanwell P, Ramadan S, Ourselin S (2007) MR image segmentation of the knee bone using phase information. Med Image Anal 11: 325–335Google Scholar
  4. 4.
    Calder J, Tahmasebi A M, Mansouri A (2011) A variational approach to bone segmentation in CT images. SPIE Medical Imaging 79620B-79620B-15Google Scholar
  5. 5.
    Zhang J, Yan C, Chui C, Ong S, Fast segmentation of bone in CT images using 3D adaptive thresholding. Comput Biol Med, 40: 231–236Google Scholar
  6. 6.
    Cernazanu-glavan C, Holban S (2013) Segmentation of Bone Structure in X-ray Images using Convolutional Neural Network. Advances in Electrical and Computer Engineering 13: 87–94Google Scholar
  7. 7.
    Jiang Y, Babyn P (2004) X-ray bone fracture segmentation by incorporating global shape model priors into geodesic active contours. Int Congr Ser 1268: 219–224Google Scholar
  8. 8.
    Morris D T, Walshaw C F (1994) Segmentation of the finger bones as a prerequisite for the determination of bone age. Image Vision Comput 12: 239–245Google Scholar
  9. 9.
    Xiao Z, Shi J, Chang Q (2009) Automatic image segmentation algorithm based on PCNN and fuzzy mutual information. Computer and Information Technology 241–245Google Scholar
  10. 10.
    Cai H, Zhang X Y, Dai H T and Zhou D M (2012) An Image Segmentation Method Using Image Enhancement and PCNN with Adaptive Parameters. Advanced Materials Research 490: 1251–1255Google Scholar
  11. 11.
    Wei S, Hong Q, Hou M (2011) Automatic image segmentation based on PCNN with adaptive threshold time constant. Neurocomputing 74: 1485–1491.Google Scholar
  12. 12.
    Gao K, Dong M, Jia F, Gao M (2012) OTSU image segmentation algorithm with immune computation optimized PCNN parameters. Engineering and Technology (S-CET) 1–4Google Scholar
  13. 13.
    Du F (2005) Infrared image segmentation with 2-D maximum entropy method based on particle swarm optimization (PSO).Pattern Recognition Letters 26: 597–603.Google Scholar
  14. 14.
    Hage I, Hamade R (2013) Smart segmentation of Bone histology slides using Pulse coupled neural networks (PCNN) optimized by particle-swarm optimization (PSO). In: 6th ECCOMAS Conference on Smart Structures and Materials, SMART2013, Politecnico di Torino, 24–26 June 2013Google Scholar
  15. 15.
    Hage I, Hamade R (2013) Structural Feature-attribute-based Segmentation of Optical Images of Bone Slices Using Optimized Pulse Coupled Neural Networks (PCNN). In: Proceedings of the ASME 2013 International Mechanical Engineering Congress & Exposition IMECE 2013, San Diego, California, USA, 12–15 November 2013Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Mechanical EngineeringAmerican University of Beirut (AUB)BeirutLebanon

Personalised recommendations