Advertisement

Journal of Real-Time Image Processing

, Volume 12, Issue 1, pp 15–29 | Cite as

GPU-accelerated level-set segmentation

  • Julián Lamas-Rodríguez
  • Dora B. Heras
  • Francisco Argüello
  • Dagmar Kainmueller
  • Stefan Zachow
  • Montserrat Bóo
Original Research Paper

Abstract

The level-set method, a technique for the computation of evolving interfaces, is a solution commonly used to segment images and volumes in medical applications. GPUs have become a commodity hardware with hundreds of cores that can execute thousands of threads in parallel, and they are nowadays ideal platforms to execute computational intensive tasks, such as the 3D level-set-based segmentation, in real time. In this paper, we propose two GPU implementations of the level-set-based segmentation method called Fast Two-Cycle. Our proposals perform computations in independent domains called tiles and modify the structure of the original algorithm to better exploit the features of the GPU. The implementations were tested with real images of brain vessels and a synthetic MRI image of the brain. Results show that they execute faster than a CPU-sequential implementation of the same method, without any significant loss of the segmentation quality and without requiring distributed parallel computer infrastructures.

Keywords

Level-set Segmentation GPU CUDA GPGPU 

Notes

Acknowledgments

This work was supported in part by the Ministry of Science and Innovation, Government of Spain, and FEDER funds under contract TIN 2010-17541, and by the Xunta de Galicia under contracts 08TIC001206PR and 2010/28. Julián Lamas-Rodríguez acknowledges financial support from the Ministry of Science and Innovation, Government of Spain, under a MICINN-FPI grant.

References

  1. 1.
    Adalsteinsson, D., Sethian, J.A.: A fast level set method for propagating interfaces. J Computational Phys 118(2), 269–277 (1995)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    BrainWeb simulated brain database. http://www.bic.mni.mcgill.ca/brainweb/
  3. 3.
    Bridson, R.E. (ed.): Computational aspects of dynamic surfaces. Ph.D. thesis, Standford University, Standford (2003)Google Scholar
  4. 4.
  5. 5.
    Courant, R., Isaacson, E., Rees, M.: On the solution of nonlinear hyperbolic differential equations by finite differences. Commun Pure Appl Math 5(3), 243–255 (1952)MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)CrossRefGoogle Scholar
  7. 7.
  8. 8.
  9. 9.
  10. 10.
    Harris, M., Segupta, S., Owens, J.D.: GPU Gems 3, chap. Parallel prefix sum (scan) with CUDA. Addison Wesley (2007)Google Scholar
  11. 11.
    Intel Corporation, Santa Clara, California, USA. Intel 64 and IA-32 Architectures Software Developer’s Manual, System Programming Guide (2011)Google Scholar
  12. 12.
    Jeong, W.K., Beyer, J., Hadwiger, M., Vazquez, A., Pfister, H., Whitaker, R.T.: Scalable and interactive segmentation and visualization of neural processes in EM datasets. IEEE Trans Visual Comp Graph 15(6), 1505–1514 (2009)CrossRefGoogle Scholar
  13. 13.
    Kirk, D.B., Hwu, W.M.W.: Programming massively parallel processors: a hands-on approach. Elsevier, Massachussets (2010)Google Scholar
  14. 14.
    Jalba, A.C., van der Laan, W.J., Roerdink, J.B.T.M.: Fast sparse level-set on graphics hardware. IEEE Trans Visual Comp Graph 99 (2012). PrePrintsGoogle Scholar
  15. 15.
    van der Laan W.J., Jalba A.C., Roerdink J.B.T.M.: A memory and computation efficient sparse level-set method. J Sci Comp 46(2), 1–22 (2011) MathSciNetzbMATHGoogle Scholar
  16. 16.
    Landis, J.R., Koch, G.G.: The measurement of observer agreement for categorical data. Biometrics 33(1), 159–174 (1977)MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Lefohn, A.E., Cates, J.E., Whitaker, R.T.: Interactive, GPU-based level sets for 3D brain tumor segmentation. Tech. rep., University of Utah, School of Computing (2003)Google Scholar
  18. 18.
    Lefohn, A.E., Kniss, J.M., Hansen, C.D., Whitaker, R.T.: A streaming narrow-band algorithm: Interactive computation and visualization of level sets. IEEE Trans Visual Comp Graph 10(4), 422–433 (2004)CrossRefGoogle Scholar
  19. 19.
    Lindholm, E., Nickolls, J., Oberman, S., Montrym, J.: NVIDIA Tesla: a unified graphics and computing architecture. IEEE Micro 28(2), 39–55 (2008)CrossRefGoogle Scholar
  20. 20.
    Lucas, B.C., Kazhdan, M., Taylor, R.H.: Multi-object geodesic active contours (MOGAC): a parallel sparse-field algorithm for image segmentation. Tech. rep., Johns Hopkins University, Department of Computer Science (2012)Google Scholar
  21. 21.
    Min C.: Local level set method in high dimension and codimension. J Comput Phys 200(1), 368–382 (2004)MathSciNetCrossRefzbMATHGoogle Scholar
  22. 22.
    Nickolls, J., Dally, W.J.: The GPU computing era. IEEE Micro 30(2), 56–69 (2010)CrossRefGoogle Scholar
  23. 23.
    NVIDIA GeForce GTX 580 GPU datasheet, NVIDIA, Santa Clara (2010)Google Scholar
  24. 24.
    CUDA C best practices guide (version 4.0), NVIDIA, Santa Clara (2011)Google Scholar
  25. 25.
    CUDA C programming guide (version 4.0), NVIDIA, Santa Clara (2011)Google Scholar
  26. 26.
    OpenCL: the open standard for parallel programming of heterogeneous systems. http://www.khronos.org/opencl/
  27. 27.
    Osher, S., Paragios, N.: Geometric level set methods in imaging, vision, and graphics. Springer-Verlag New York, Inc., Secaucus (2003)Google Scholar
  28. 28.
    Osher, S., Sethian, J.A.: Fronts propagating with curvature-dependent speed: Algorithms based on Hamilton–Jacobi formulations. J Comput Phys 79, 12–49 (1988)MathSciNetCrossRefzbMATHGoogle Scholar
  29. 29.
    Owens, J.D., Houston, M., Luebke, D., Green, S., Stone, J.E., Phillips, J.C.: GPU computing. Proc IEEE 96(5):879–899 (2008)Google Scholar
  30. 30.
    Parallel programming and computing platform, CUDA, NVIDIA. http://www.nvidia.com/object/cuda_home_new.html
  31. 31.
    Peng, D., Merriman, B., Osher, S., Zhao, H., Kang, M.: A PDE-based fast local level set method. J Comput Phys 155(2), 410–438 (1999)MathSciNetCrossRefzbMATHGoogle Scholar
  32. 32.
    Roberts, M., Packer, J., Sousa, M.C., Mitchell, J.R.: A work-efficient GPU algorithm for level set segmentation. In: Proceedings of the Conference on High Performance Graphics, HPG ’10. pp. 123–132. Eurographics Association, Saarbrucken (2010)Google Scholar
  33. 33.
    Rumpf, M., Strzodka, R.: Level set segmentation in graphics hardware. In: Proceedings of IEEE International Conference on Image Processing, ICIP’ 01. pp. 1103–1106. IEEE, Thessaloníki (2001)Google Scholar
  34. 34.
    Sethian, J.A.: Level set methods and fast marching methods: evolving interfaces in computational fluid mechanics, computer vision, and materials science. Cambridge University Press, Cambridge (1996)Google Scholar
  35. 35.
    Shi, Y., Karl, W.C.: A real-time algorithm for the approximation of level-set-based curve evolution. IEEE Trans Image Process 17(5), 645–656 (2008)MathSciNetCrossRefGoogle Scholar
  36. 36.
    Strain, J.: Semi-Lagrangian methods for level set equations. J Comput Phys 151(2), 498–533 (1999)MathSciNetCrossRefzbMATHGoogle Scholar
  37. 37.
    Strain, J.: Tree methods for moving interfaces. J Comput Phys 151(2), 616–648 (1999)MathSciNetCrossRefzbMATHGoogle Scholar
  38. 38.
    Strain, J.: A fast modular semi-Lagrangian method for moving interfaces. J Comput Phys 161(2), 512–536 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  39. 39.
    The Stanford 3D scanning repository. http://graphics.stanford.edu/data/3Dscanrep/
  40. 40.
  41. 41.
    Tornai, G.J., Cserey, G.: 2D and 3D level-set algorithms on GPU. In: Proceedings of the 12th International Workshop on Cellular Nanoscale and their Applications, pp. 1–5. CNNA ’10. IEEE, Berkeley (2010)Google Scholar
  42. 42.
    Whitaker, R.T.: Volumetric deformable models: active blobs. In: Visualization in Biomedical Computing 1994, Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series. pp. 122–134. SPIE, Rochester (1994)Google Scholar
  43. 43.
    Whitaker, R.T.: A level-set approach to 3D reconstruction from range data. Intern J Comp Vis 29(3), 203–231 (1998)CrossRefGoogle Scholar
  44. 44.
    ZibAmira: Amira for research partners. http://amira.zib.de/
  45. 45.
    Zijdenbos, A.P., Dawant, B.M., Mangolin, R.A., Palmer, A.C.: Morphometric analysis of white matter lesions in MR images: method and validation. IEEE Trans Med Imag 13(4), 716–724 (1994)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Julián Lamas-Rodríguez
    • 1
  • Dora B. Heras
    • 1
  • Francisco Argüello
    • 2
  • Dagmar Kainmueller
    • 3
  • Stefan Zachow
    • 3
  • Montserrat Bóo
    • 2
  1. 1.Centro de Investigación en Tecnoloxías da Información da Universidade de Santiago de Compostela (CITIUS)Santiago de CompostelaSpain
  2. 2.Department of Electronics and Computer ScienceUniversity of Santiago de CompostelaSantiago de CompostelaSpain
  3. 3.Department of Visualization and Data AnalysisKonrad-Zuse-Zentrum für InformationstechnikBerlinGermany

Personalised recommendations