Skip to main content

Medical image segmentation with deformable models on graphics processing units


In this work, the parallel implementation of a segmentation algorithm based on the gradient vector flow (GVF) deformable model in a graphics processing unit (GPU) is presented. The proposed implementation focuses on the parallelization of the computation of the GVF field. In order to make a performance comparison of the proposed GPU algorithm, an OpenMP-based implementation is presented too. We also present an analysis of the textures and global memory performance in the computing of the GVF field. To improve the efficiency and the performance of the active contour segmentation, a novel snaxel reallocation method is proposed. The main advantage of the reallocation process is the small linear system needed to perform the segmentation and its low computational load. To assure the convergence of the active contour deformation, we propose a stopping criterion based on the root mean square error for the iterative solution of the evolution equations.

This is a preview of subscription content, access via your institution.

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


  1. Dhawan AP, Huang HK, Kim DS (2008) Principles and advanced methods in medical imaging and image analysis. World Scientific Publishing Co. Pte, Ltd, Singapore

  2. González RC, Woods RE (2002) Digital image processing, 2nd edn. Prentice Hall, Englewood Cliffs

  3. He L, Peng Z, Everding B, Wang X, Han CY, Weiss KL, Wee WG (2008) A comparative study of deformable contour methods on medical image segmentation. Image Vis Comput 26(2):141–163

    Article  Google Scholar 

  4. Li B, Acton ST (2007) Active contour external force using vector field convolution for image segmentation. IEEE Trans Image Process 16(8):2096–2106

    Article  MathSciNet  Google Scholar 

  5. Wang Y, Liu L, Zhang H, Cao Z, Lu S (2010) Image segmentation using active contours with normally biased GVF external force. IEEE Signal Process Lett 17(10):875–878

    Article  Google Scholar 

  6. Terzopoulos D, McInerney T (1996) Deformable models in medical image analysis: a survey. Med Image Anal 1(2):91–108

    Article  Google Scholar 

  7. Suri JS, Farag AA (eds) (2007) Deformable models II: theory and biomaterial applications. Springer, Berlin

  8. Mahmoud MKA, Al-Jumaily A (2011) Segmentation of skin cancer images based on gradient vector flow (GVF) snake. In: IEEE international conference on mechatronics and automation. Beijing, China, pp 216–220

  9. He Z, Kuester F (2006) GPU-based active contour segmentation using gradient vector flow. In: Advances in visual computing second international symposium, ISVC 2006. Lake Tahoe, NV, USA, pp 191–201

  10. Zheng Z, Zhang R (2011) A GPU-accelerated GVF snake algorithm. In: Proceedings of the 2011 workshop on digital media and digital content management, DMDCM ’11. Hangzhou, China, pp 233–236

  11. Perrot G, Domas S, Couturier R, Bertaux N (2011) GPU implementation of a region based algorithm for large images segmentation. In: 11th IEEE international conference on computer and information technology. Belfort, France, pp 291–298

  12. Li T, Krupa A, Collewet C (2011) A robust parametric active contour based on Fourier descriptors. In: 18th IEEE international conference on image processing. Brussels, Belguim, pp 1037–1040

  13. Smistad E, Elster AC, Lindseth F (2012) Real-time gradient vector flow on GPUs using OpenCL. J Real Time Image Process. doi:10.1007/s11554-012-0257-6

  14. Kienel E, Brunnett G (2009) GPU-accelerated contour extraction on large images using snakes. Technical Report. CSR-09-02, Chemnitz University of Technology, Germany

  15. Češnovar R, Risojević V, Babić Z, Dobravec T, Bulić P (2013) A GPU implementation of a structural-similarity-based aerial-image classification. J Supercomput 65:978–996

    Article  Google Scholar 

  16. Valero P, Sánchez JL, Cazorla D, Arias E (2011) A GPU-based implementation of the MRF algorithm in ITK package. J Supercomput 58:403–410

    Article  Google Scholar 

  17. Reyes R, López I, Fumero JJ, de Sande F (2013) A preliminary evaluation of OpenACC implementations. J Supercomput 65:1063–1075

    Article  Google Scholar 

  18. Lenkiewicz P, Pereira M, Freire MM, Fernandes J (2009) A new 3D image segmentation method for parallel architectures. In: IEEE International conference on multimedia and expo, 2009. New York, USA, pp 1813–1816

  19. Schellmann M, Gorlatch S, Meiländer D, Kösters T, Schäfers K, Wübbeling F, Burger M (2011) Parallel medical image reconstruction: from graphics processing units (GPU) to grids. J Supercomput 57:151–160

    Article  Google Scholar 

  20. Pallipuram VK, Bhuiyan M, Smith MC (2012) A comparative study of GPU programming models and architectures using neural networks. J Supercomput 61:673–718

    Article  Google Scholar 

  21. Belloch JA, González A, Martínez-Saldívar F, Vidal AM (2011) Real-time massive convolution for audio applications on GPU. J Supercomput 58:449–457

    Article  Google Scholar 

  22. Xu C, Prince JL (1998) Snakes, shapes, and gradient vector flow. IEEE Trans Image Process 7(3):359–369

    Article  MATH  MathSciNet  Google Scholar 

  23. Terzopoulos D (1986) On matching deformable models to images. Technical Repprt 60, Schlumberger Palo Alto Research, USA

  24. Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis 1(4):321–331

    Article  Google Scholar 

  25. Terzopoulos D, Platt J, Barr A, Fleischer K (1987) Elastically deformable models. SIGGRAPH 21(4):205–214

    Article  Google Scholar 

  26. Davatzikosa C, Prince JL (1996) Convexity analysis of active contour problems. In: IEEE conference on computer vision and pattern recognition, CVPR ’96. San Francisco, USA, pp 674–679

  27. Mishra AK, Fieguth PW, Clausi DA (2011) Decoupled active contour (DAC) for boundary detection. IEEE Trans Pattern Anal Mach Intell 33(2):310–324

    Article  Google Scholar 

  28. Boukerroui D (2009) Efficient numerical schemes for gradient vector flow. In: 16th IEEE international conference on image processing (ICIP). Cairo, Egypt, pp 4057–4060

  29. Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698

    Article  Google Scholar 

  30. Huang S, Wang B, Huang X (2006) Using GVF snake to segment liver from CT images. In: 3rd IEEE/EMBS International Summer School on Medical Devices and Biosensors, 2006. Cambridge, USA, pp 145–148

  31. Wagner S, Steinmetz M, Bode A, Muller M (2010) High performance computing in science and engineering. Springer, Berlin

  32. Kirk DB, Wen-mei WH (2010) In Praise of Programming massively parallel processors: a hands-on approach. Elsevier, Amsterdam

  33. Cook S (2013) CUDA programming: a developer’s guide to parallel computing with GPUs. Elsevier, Amsterdam

  34. nVIDIA (2013) NVIDIA CUDA C programming guide

  35. Farber R (2011) CUDA application design and development. Elsevier Inc., Amsterdam

  36. nVIDIA (2013) CUDA C best practices guide

  37. Chapman B, Jost G, van der Pas R (2008) Using OpenMP: portable shared memory parallel programming. The MIT press, Cambridge

  38. The cancer imaging archive (2012) Accessed 15 Jan 2012

  39. Patient contributed image repository (2012) Accessed 15 Jan 2012

  40. Dicom sample image sets (2013) Accessed 15 Jun 2013

Download references


This work has been partially supported by COFAA-IPN, and by Grant IPN-SIP-20120606.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Juan J. Tapia.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Alvarado, R., Tapia, J.J. & Rolón, J.C. Medical image segmentation with deformable models on graphics processing units. J Supercomput 68, 339–364 (2014).

Download citation

  • Published:

  • Issue Date:

  • DOI:


  • GPU
  • CUDA
  • Deformable models
  • Segmentation
  • Snaxel reallocation
  • Medical image
  • OpenMP