Advertisement

Optimized PatchMatch for Near Real Time and Accurate Label Fusion

  • Vinh-Thong Ta
  • Rémi Giraud
  • D. Louis Collins
  • Pierrick Coupé
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8675)

Abstract

Automatic segmentation methods are important tools for quantitative analysis of magnetic resonance images. Recently, patch- based label fusion approaches demonstrated state-of-the-art segmentation accuracy. In this paper, we introduce a new patch-based method using the PatchMatch algorithm to perform segmentation of anatomical structures. Based on an Optimized PAtchMatch Label fusion (OPAL) strategy, the proposed method provides competitive segmentation accuracy in near real time. During our validation on hippocampus segmentation of 80 healthy subjects, OPAL was compared to several state-of-the-art methods. Results show that OPAL obtained the highest median Dice coefficient (89.3%) in less than 1 sec per subject. These results highlight the excellent performance of OPAL in terms of computation time and segmentation accuracy compared to recently published methods.

Keywords

PatchMatch Patch-based Segmentation Hippocampus 

References

  1. 1.
    Collins, D.L., et al.: Automatic 3-D model-based neuroanatomical segmentation. Human Brain Mapping 3(3), 190–208 (1995)CrossRefGoogle Scholar
  2. 2.
    Heckemann, R.A., et al.: Automatic anatomical brain MRI segmentation combining label propagation and decision fusion. NeuroImage 33(1), 115–126 (2006)CrossRefGoogle Scholar
  3. 3.
    Lötjönen, J.M., et al.: Fast and robust multi-atlas segmentation of brain magnetic resonance images. Neuroimage 49(3), 2352–2365 (2010)CrossRefGoogle Scholar
  4. 4.
    Collins, D.L., Pruessner, J.C.: Towards accurate, automatic segmentation of the hippocampus and amygdala from mri by augmenting animal with a template library and label fusion. Neuroimage 52(4), 1355–1366 (2010)CrossRefGoogle Scholar
  5. 5.
    Coupé, P., et al.: Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation. NeuroImage 54(2), 940–954 (2011)CrossRefGoogle Scholar
  6. 6.
    Rousseau, F., Habas, P.A., Studholme, C.: A supervised patch-based approach for human brain labeling. IEEE Transactions on Medical Imaging 30(10), 1852–1862 (2011)CrossRefGoogle Scholar
  7. 7.
    Eskildsen, S.F., et al.: BEaST: Brain extraction based on nonlocal segmentation technique. NeuroImage 59(3), 2362–2373 (2012)CrossRefGoogle Scholar
  8. 8.
    Tong, T., et al.: Segmentation of MR images via discriminative dictionary learning and sparse coding: Application to hippocampus labeling. NeuroImage 76, 11–23 (2013)CrossRefGoogle Scholar
  9. 9.
    Wu, G., et al.: A generative probability model of joint label fusion for multi-atlas based brain segmentation. Medical Image Analysis (2013)Google Scholar
  10. 10.
    Barnes, C., et al.: Patchmatch: A randomized correspondence algorithm for structural image editing. In: ACM SIGGRAPH 2009 Papers, pp. 24:1–24:11 (2009)Google Scholar
  11. 11.
    Shi, W., et al.: Cardiac image super-resolution with global correspondence using multi-atlas patchmatch. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part III. LNCS, vol. 8151, pp. 9–16. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  12. 12.
    Barnes, C., Shechtman, E., Goldman, D.B., Finkelstein, A.: The generalized patchmatch correspondence algorithm. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 29–43. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  13. 13.
    Pruessner, J., et al.: Volumetry of hippocampus and amygdala with high-resolution MRI and three-dimensional analysis software: minimizing the discrepancies between laboratories. Cerebral Cortex 10(4), 433–442 (2000)CrossRefGoogle Scholar
  14. 14.
    Coupé, P., et al.: Robust Rician noise estimation for MR images. Medical Image Analysis 14(4), 483–493 (2010)CrossRefGoogle Scholar
  15. 15.
    Coupé, P., et al.: An optimized blockwise nonlocal means denoising filter for 3-D magnetic resonance images. IEEE Transactions on Medical Imaging 27(4), 425–441 (2008)CrossRefGoogle Scholar
  16. 16.
    Sled, J.G., et al.: A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Transactions on Medical Imaging 17(1), 87–97 (1998)CrossRefGoogle Scholar
  17. 17.
    Collins, D.L., et al.: Automatic 3D intersubject registration of MR volumetric data in standardized talairach space. Journal of Computer Assisted Tomography 18(2), 192–205 (1994)CrossRefGoogle Scholar
  18. 18.
    Manjón, J.V., et al.: Robust MRI brain tissue parameter estimation by multistage outlier rejection. Magnetic Resonance in Medicine 59(4), 866–873 (2008)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Vinh-Thong Ta
    • 1
    • 2
    • 3
  • Rémi Giraud
    • 1
    • 2
    • 3
  • D. Louis Collins
    • 4
  • Pierrick Coupé
    • 1
    • 2
  1. 1.LaBRI, UMR 5800, PICTURAUniv. BordeauxTalenceFrance
  2. 2.CNRS, LaBRI, UMR 5800, PICTURATalenceFrance
  3. 3.IPB, LaBRI, UMR 5800, PICTURAPessacFrance
  4. 4.McConnell Brain Imaging Centre, Montreal Neurological InstituteMcGill UniversityMontrealCanada

Personalised recommendations