A novel CT image segmentation algorithm using PCNN and Sobolev gradient methods in GPU frameworks

  • Biswajit Biswas
  • Swarup Kr. GhoshEmail author
  • Anupam Ghosh
Theoretical advances


Accurate brain tumor segmentation plays a significant role in the area of radiotherapy diagnosis and in the proper treatment for brain tumor detection. Typically, the brain tumor has poor boundary and low contrast between normal and lesion soft tissues that makes segmentation of brain tumor in the CT images a challenging task. This paper presents a novel approach to brain image segmentation using pulse-coupled neural network (PCNN) and zero level set (ZL) with Sobolev gradient (SG) method. In this article, PCNN is designed to use as an edge mapper to provide a regional description for the ZL to segregate the CT images based on contour maps. The PCNN is used to estimate the exact threshold to obtain the prominent edges of the images. Resulting edges are utilized in the ZL to extract image contour from the source image. Due to the over-sensitivity of the ZL method on the initial contour, a level set with the SG has been equipped to overcome the limitation of the ZL method. The experimental results show satisfactory segmentation outcomes with excellent accuracy and acceleration in comparison with the state-of-the-art methods.


Image segmentation Level set Pulse-coupled neural network Sobolev gradient CT images 



  1. 1.
    Dora L, Agrawal S, Panda R, Abraham A (2017) State of the art methods for brain tissue segmentation: a review. IEEE Rev Bio Eng 10:235–249CrossRefGoogle Scholar
  2. 2.
    Eklund A, Dufort P, Forsberg D, LaConte SM (2013) Medical image processing on the GPU-past, present and future. Med Image Anal 17(8):1073–1094CrossRefGoogle Scholar
  3. 3.
    Hsieh J (2003) Computed tomography: principles, design, artifacts, and recent advances, vol 114. SPIE Press, BellinghamGoogle Scholar
  4. 4.
    Kak AC, Slaney M (2001) Principles of computerized tomographic imaging. Society for Industrial and Applied Mathematics, PhiladelphiazbMATHCrossRefGoogle Scholar
  5. 5.
    Wang Z, Ma Y, Cheng F, Yang L (2010) Review of pulse-coupled neural networks. Image Vis Comput 28(1):5–13CrossRefGoogle Scholar
  6. 6.
    Osher S, Sethian JA (1988) Fronts propagating with curvature-dependent speed: algorithms based on Hamilton–Jacobi formulations. J Comput Phys 79(1):12–49MathSciNetzbMATHCrossRefGoogle Scholar
  7. 7.
    Sui H, Peng F, Xu C, Sun K, Gong J (2012) GPU-accelerated MRF segmentation algorithm for SAR images. Comput Geosci 43:159–166CrossRefGoogle Scholar
  8. 8.
    Sanders J, Kandrot E (2010) CUDA by example: an introduction to general-purpose GPU programming, portable documents. Addison-Wesley Professional, BostonGoogle Scholar
  9. 9.
    Shattuck DW, Sandor-Leahy SR, Schaper KA, Rottenberg DA, Leahy RM (2001) Magnetic resonance image tissue classification using a partial volume model. NeuroImage 13(5):856–876CrossRefGoogle Scholar
  10. 10.
    Akgun D, Erdogmus P (2015) GPU accelerated training of image convolution filter weights using genetic algorithms. Appl Soft Comput 30:585–594CrossRefGoogle Scholar
  11. 11.
    Brodtkorb AR, Hagen TR, Saetra ML (2013) Graphics processing unit (GPU) programming strategies and trends in GPU computing. J Parallel Distrib Comput 73(1):4–13CrossRefGoogle Scholar
  12. 12.
    Kirk DB, Hwu WMW (2010) Programming massively parallel processors. Elsevier, AmsterdamGoogle Scholar
  13. 13.
    Massingill BL, Mattson TG, Sanders BA (2004) Patterns for parallel programming. The software patterns series. Addison-Wesley Professional, BostonGoogle Scholar
  14. 14.
    Vagli P, Turini F, Cerri F, Neri E (2008) Temporal bone. Image Process Radiol 12:137–149CrossRefGoogle Scholar
  15. 15.
    Yoo TS (2004) Insight into images: principles and practice for segmentation, registration, and image analysis. AK Peters Ltd, NatickCrossRefGoogle Scholar
  16. 16.
    Sonka M, Hlavac V, Boyle R (2014) Image processing, analysis, and machine vision. Cengage Learning, StamfordGoogle Scholar
  17. 17.
    Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Process 10(2):266–277zbMATHCrossRefGoogle Scholar
  18. 18.
    Neuberger JW (1997) Sobolev gradients and differential equations. Lecture notes in mathematics, vol 1670. Springer, BerlinCrossRefGoogle Scholar
  19. 19.
    Khadidos A, Sanchez V, Li CT (2017) Weighted level set evolution based on local edge features for medical image segmentation. IEEE Trans Image Process 26(4):1979–1991MathSciNetzbMATHCrossRefGoogle Scholar
  20. 20.
    Pratondo A, Chui CK, Ong SH (2016) Robust edge-stop functions for edge-based active contour models in medical image segmentation. IEEE Signal Process Lett 23(2):220–226CrossRefGoogle Scholar
  21. 21.
    Wei S, Qu H, Hou M (2011) Automatic image segmentation based on PCNN with adaptive threshold time constant. Neurocomputing 74:1485–1491CrossRefGoogle Scholar
  22. 22.
    Xie W, Li Y, Ma Y (2015) PCNN-based level set method of automatic mammographic image segmentation. Opt Int J Light Electron Opt 127(4):1644–1650CrossRefGoogle Scholar
  23. 23.
    Song E, Huang D, Hung C (2011) Semi-supervised multi-class adaboost by exploiting unlabeled data. Expert Syst Appl 38:6720–6726CrossRefGoogle Scholar
  24. 24.
    Konstantinos K, Christian L, Virginia FJN et al (2017) Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal 36:61–78CrossRefGoogle Scholar
  25. 25.
    Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for scene segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481–2495CrossRefGoogle Scholar
  26. 26.
    Litjens G, Kooi T, Bejnordi BE (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88CrossRefGoogle Scholar
  27. 27.
    Zhang H, Wang S, Xu X, Chow T, Jonathan Wu QMJ (2018) Tree2Vector: learning a vectorial representation for tree-structured data. IEEE Trans Neural Netw Learn Syst 29(11):C1–5173MathSciNetCrossRefGoogle Scholar
  28. 28.
    Smistad E, Falch TL, Bozorgi M et al (2015) Medical image segmentation on GPUs-A comprehensive review. Med Image Anal 20(1):1–18CrossRefGoogle Scholar
  29. 29.
    Renka RJ (2010) Geometric curve modeling with Sobolev gradients. In: Neuberger JW (ed) Sobolev gradients and differential equations. Springer, Berlin, pp 199–208CrossRefGoogle Scholar
  30. 30.
    Jaros M, Strakos P et al (2017) Implementation of K-means segmentation algorithm on Intel Xeon Phi and GPU: application in medical imaging. Adv Eng Softw 103:21–28CrossRefGoogle Scholar
  31. 31.
    Renka RJ (2005) Sobolev gradient method for construction of elastic curves in regular surfaces. Nonlinear Anal Theory Methods Appl 63(5):e1789–e1796zbMATHCrossRefGoogle Scholar
  32. 32.
    Caselles V, Kimmel R, Sapiro G (1997) Geodesic active contours. Int J Comput Vis 22(1):61–79zbMATHCrossRefGoogle Scholar
  33. 33.
  34. 34.
    Levine M, Nazif A (1985) Dynamic measurement of computer generated image segmentations. IEEE Trans Pattern Anal Mach Intell 7:155–164CrossRefGoogle Scholar
  35. 35.
    Lin L, Yang W et al (2016) Inference with collaborative model for interactive tumor segmentation in medical image sequences. IEEE Trans Cybern 46(12):2796–2809CrossRefGoogle Scholar
  36. 36.
    Liu B, Cheng HD, Huang J, Tian J, Tang X, Liu J (2010) Probability density difference-based active contour for ultrasound image segmentation. Pattern Recognit 43(6):2028–2042zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  • Biswajit Biswas
    • 1
  • Swarup Kr. Ghosh
    • 2
    Email author
  • Anupam Ghosh
    • 3
  1. 1.University of CalcuttaKolkataIndia
  2. 2.Brainware UniversityKolkataIndia
  3. 3.Netaji Subhash Engineering CollegeKolkataIndia

Personalised recommendations