Skip to main content
SpringerLink
Log in

Geometric-attributes-based segmentation of cortical bone slides using optimized neural networks

  • Original Article
  • Published:
Journal of Bone and Mineral Metabolism Aims and scope Submit manuscript

Abstract

In cortical bone, solid (lamellar and interstitial) matrix occupies space left over by porous microfeatures such as Haversian canals, lacunae, and canaliculi-containing clusters. In this work, pulse-coupled neural networks (PCNN) were used to automatically distinguish the microfeatures present in histology slides of cortical bone. The networks’ parameters were optimized using particle swarm optimization (PSO). When forming the fitness functions for the PSO, we considered the microfeatures’ geometric attributes—namely, their size (based on measures of elliptical perimeter or area), shape (based on measures of compactness or the ratio of minor axis length to major axis length), and a two-way combination of these two geometric attributes. This hybrid PCNN–PSO method was further enhanced for pulse evaluation by combination with yet another method, adaptive threshold (AT), where the PCNN algorithm is repeated until the best threshold is found corresponding to the maximum variance between two segmented regions. Together, this framework of using PCNN–PSO–AT constitutes, we believe, a novel framework in biomedical imaging. Using this framework and extracting microfeatures from only one training image, we successfully extracted microfeatures from other test images. The high fidelity of all resultant segments was established using quantitative metrics such as precision, specificity, and Dice indices.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Zoroofi RA, 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 6:511

    Article  Google Scholar 

  2. Zoroofi RA, 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 5:267–278

    Article  Google Scholar 

  3. Liu Z, Liew HL, Clement JG, Thomas CDL (1999) Bone image segmentation. Biomed Eng IEEE Trans 5:565–573

    Google Scholar 

  4. Kai Z, Bin K, Yan K, Hong Z (2010) Auto-threshold bone segmentation based on CT image and its application on CTA bone-subtraction. In: 2010 symposium on photonics and optoelectronic (SOPO 2010). IEEE, Piscataway

  5. Polak SJ, Candido S, Levengood SKL, Wagoner Johnson AJ (2012) Automated segmentation of micro-CT images of bone formation in calcium phosphate scaffolds. Comput Med Imaging Graph 1:54–65

    Article  Google Scholar 

  6. Kim Y, Kim D (2009) A fully automatic vertebra segmentation method using 3D deformable fences. Comput Med Imaging Graph 5:343–352

    Article  Google Scholar 

  7. Jatti A, Prasannakumar S, Kumar R (2012) Segmentation and analysis of microscopic osteosarcoma bone images. Int J Electron Commun Electr Eng 2:1–10

    Google Scholar 

  8. Jatti A (2011) Segmentation and analysis of osteosarcoma cancerous bone micro array images-1. Int J Inf Technol 1:195–200

    Google Scholar 

  9. Wu Y, Bergot C, Jolivet E, Zhou L, Laredo J, Bousson V (2009) Cortical bone mineralization differences between hip-fractured females and controls. A microradiographic study. Bone 2:207–212

    Article  Google Scholar 

  10. Britz HM, Thomas CDL, Clement JG, Cooper DM (2009) The relation of femoral osteon geometry to age, sex, height and weight. Bone 1:77–83

    Article  Google Scholar 

  11. Bergot C, Wu Y, Jolivet E, Zhou L, Laredo J, Bousson V (2009) The degree and distribution of cortical bone mineralization in the human femoral shaft change with age and sex in a microradiographic study. Bone 3:435–442

    Article  Google Scholar 

  12. Boukala N, Favier E, Laget B, Radeva P (2004) Active shape model based segmentation of bone structures in hip radiographs. In: IEEE ICIT’04. 2004 IEEE international conference on industrial technology. IEEE, Piscataway, pp 1682–1687

  13. Fripp J, Bourgeat P, Crozier S, Ourselin S (2007) Shape-based segmentation of MRIs of the bones in the knee using phase and intensity information. Proc SPIE 6512:651212

  14. Hage IS, Hamade RF (2012) Structural micro processing of Haversian systems of a cortical bovine femur using optical stereomicroscope and MATLAB. In: ASME 2012 international mechanical engineering congress and exposition. Volume 2: biomedical and biotechnology. American Society of Mechanical Engineers, New York, pp 595–601

  15. Hage IS, Hamade RF (2013) Segmentation of histology slides of cortical bone using pulse coupled neural networks optimized by particle-swarm optimization. Comput Med Imaging Graph 7:466–474

    Article  Google Scholar 

  16. Sharma N, Aggarwal LM (2010) Automated medical image segmentation techniques. J Med Phys 35:3–14

    Google Scholar 

  17. Zhang D, Mabu S, Hirasawa K (2010) Noise reduction using genetic algorithm based PCNN method. In: 2010 IEEE international conference on systems, man, and cybernetics (SMC). IEEE, Piscataway, pp 2627–2633

  18. Tu Y, Li S, Wang M (2008) Mixed-noise removal for color images using modified PCNN model. In: IITA’08. 2008 second international symposium on intelligent information technology application. IEEE, Piscataway, pp 347–351

  19. Xiao Z, Shi J, Chang Q (2009) Automatic image segmentation algorithm based on PCNN and fuzzy mutual information. In: CIT’09. Ninth IEEE international conference on computer and information technology, 2009. IEEE, Piscataway, pp 241–245

  20. Cai H, Zhang XY, Dai HT, Zhou DM (2012) An image segmentation method using image enhancement and PCNN with adaptive parameters. Adv Mater Res 490–495:1251–1255

  21. Wei S, Hong Q, Hou M (2011) Automatic image segmentation based on PCNN with adaptive threshold time constant. Neurocomputing 9:1485–1491

    Article  Google Scholar 

  22. Gao K, Dong M, Jia F, Gao M (2012) OTSU image segmentation algorithm with immune computation optimized PCNN parameters. In: 2012 Spring congress on engineering and technology (S-CET). IEEE, Piscataway

  23. Ranganath H, Kuntimad G, Johnson J (1995) Pulse coupled neural networks for image processing. In: Proceedings IEEE Southeastcon '95. Visualize the future. IEEE, Piscataway, pp 37–43

  24. Zhang Y, Wu L, Wang S, Wei G (2010) Color Image Enhancement based on HVS and PCNN. Sci China Inf Sci 10:1963–1976

    Article  Google Scholar 

  25. Cheng W, Shao-Fa L (2008) An adaptive method of car plate image enhancement based on a simplified pulse coupled neural network. In: ISCSCT’08. International symposium on computer science and computational technology, 2008. IEEE, Piscataway, pp 277–279

  26. Li H, Xu D, Zong R (2009) Face recognition based on unit-linking PCNN time signature. In: ICACC’09. International conference on advanced computer control, 2009. IEEE, Piscataway, pp 360–364

  27. Hongzhao Y, Guifa H, Yong L (2009) Pulse coupled neural network algorithm for object detection in infrared image. In: CNMT 2009. International symposium on computer network and multimedia technology, 2009. IEEE, Piscataway

  28. Edmondson R, Rodgers M, Banish M (2008) Using a genetic algorithm to find an optimized pulse coupled neural network solution. Proc SPIE 6979:69790M

  29. Xu X, Ding S, Shi Z, Zhu H, Zhao Z (2011) Particle swarm optimization for automatic parameters determination of pulse coupled neural network. J Comput 8:1546–1553

    Google Scholar 

  30. Wang Z, Ma Y, Gu J (2010) Multi-focus image fusion using PCNN. Pattern Recognit 6:2003–2016

    Article  Google Scholar 

  31. Trelea IC (2003) The particle swarm optimization algorithm: convergence analysis and parameter selection. Inf Process Lett 6:317–325

    Article  Google Scholar 

  32. Shi Y, Eberhart R (1998) A modified particle swarm optimizer. In: IEEE world congress on computational intelligence. The 1998 IEEE international conference on evolutionary computation proceedings, 1998. IEEE, Piscataway, pp 69–73

  33. Poli R, Kennedy J, Blackwell T (2007) Particle swarm optimization. Swarm Intell 1:33–57

    Article  Google Scholar 

  34. Lindblad T, Kinser JM (2005) Image processing using pulse-coupled neural networks. Springer, Heidelberg

  35. Chen Y, Han C (2005) Adaptive wavelet threshold for image denoising. Electron Lett 10:586–587

    Article  Google Scholar 

  36. Satheesh S, Prasad K (2011) Medical image denoising using adaptive threshold based on contourlet transform. Adv Comput 2:52–58

  37. Zhang X, Desai MD (2001) Segmentation of bright targets using wavelets and adaptive thresholding. IEEE Trans Image Process 7:1020–1030

    Article  Google Scholar 

  38. Chan FH, Lam F, Zhu H (1998) Adaptive thresholding by variational method. IEEE Trans Image Process 3:468–473

    Article  Google Scholar 

  39. Jiang X, Mojon D (2003) Adaptive local thresholding by verification-based multithreshold probing with application to vessel detection in retinal images. IEEE Trans Pattern Anal Mach Intell 1:131–137

    Article  Google Scholar 

  40. Otsu N (1975) A threshold selection method from gray-level histograms. Automatica 285–296:23–27

    Google Scholar 

  41. Gao K, Dong M, Jia F, Gao M (2012) OTSU image segmentation algorithm with immune computation optimized PCNN parameters pp 1–4

  42. Sýkora S (2005) Approximations of ellipse perimeters and of the complete elliptic integral E(x). Review of known formulae. http://www.ebyte.it/library/docs/math05a/EllipsePerimeterApprox05.html. Accessed 25 Apr 2014

  43. Pierce R (2014) Perimeter of an ellipse. http://www.mathsisfun.com/geometry/ellipse-perimeter.html. Accessed 3 May 2014

  44. Dhawan AP (2011) Medical image analysis. Wiley, Hoboken

  45. Montero RS, Bribiesca E (2009) State of the art of compactness and circularity measures. Int Math Forum 25–28:1305–1335

    Google Scholar 

  46. Dawant BM, Hartmann SL, Thirion J, Maes F, Vandermeulen D, Demaerel P (1999) Automatic 3-D segmentation of internal structures of the head in MR images using a combination of similarity and free-form transformations. I. Methodology and validation on normal subjects. Med Imaging IEEE Trans 10:909–916

    Article  Google Scholar 

  47. Conte D, Foggia P, Tufano F, Vento M (2011) An enhanced level set algorithm for wrist bone segmentation. In: Ho P-G (ed) Image segmentation. InTech, Rijeka, pp 293–308

    Google Scholar 

  48. Calder J, Tahmasebi AM, Mansouri A (2011) A variational approach to bone segmentation in CT images. Proc SPIE 7962:79620B

  49. Mahendran S, Baboo SS (2011) Enhanced automatic x-ray bone image segmentation using wavelets and morphological operators. In: 2011 international conference on information and electronics engineering. IACSIT Press, Singapore, pp 125–129

  50. Bourgeat P, Fripp J, Stanwell P, Ramadan S, Ourselin S (2007) MR image segmentation of the knee bone using phase information. Med Image Anal 4:325–335

    Article  Google Scholar 

  51. Rusu A, Stillfried DIG, Institutsdirektor D, Hirzinger G (2011) Segmentation of bone structures in magnetic resonance images (MRI) for human hand skeletal kinematics modelling. MSc thesis, German Aerospace Center, Oberpfaffenhofen. http://elib.dlr.de/74593/1/RUSU_Alexandru_-_Master_thesis.pdf

Download references

Acknowledgments

The authors acknowledge Charbel Seif, an instructor in the Mechanical Engineering Department of the American University of Beirut, and Ziad Al Baff, a technician in the Surgical Pathology Department of American University of Beirut Medical Center for their work in bone specimen preparation for microscope imaging. The authors acknowledge the support of the Lebanese National Council for Scientific Research for support of the first author through the CNRS-L/AUB PhD Awards Program. Also acknowledged is the financial support of the University Research Board of the American University of Beirut.

Conflict of interest

The authors have no conflict of interest including financial and personal relationships with other people or organizations that could inappropriately influence (bias) this work.

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering, American University of Beirut, Riad El-Solh, Beirut, 1107 2020, Lebanon

    Ilige S. Hage & Ramsey F. Hamade

Authors
  1. Ilige S. Hage
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ramsey F. Hamade
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ramsey F. Hamade.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hage, I.S., Hamade, R.F. Geometric-attributes-based segmentation of cortical bone slides using optimized neural networks. J Bone Miner Metab 34, 251–265 (2016). https://doi.org/10.1007/s00774-015-0668-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00774-015-0668-0

Keywords

Search

Navigation