Advertisement

On the Role of Patch Spaces in Patch-Based Label Fusion

  • Oualid M. BenkarimEmail author
  • Gemma Piella
  • Miguel Angel González Ballester
  • Gerard Sanroma
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10530)

Abstract

Multi-atlas segmentation has shown promising results in the segmentation of biomedical images. In the most common approach, registration is used to warp the atlases to the target space and then the warped atlas labelmaps are fused into a consensus segmentation. Label fusion in target space has shown to produce very accurate segmentations although at the expense of registering all atlases to each target image. Moreover, appearance and label information used by label fusion is extracted from the warped atlases, which are subject to interpolation errors. This work explores the role of extracting this information from the native spaces and adapt two label fusion approaches to this scheme. Results on the segmentation of subcortical brain structures indicate that using atlases in their native space yields superior performance than warping the atlases to the target. Moreover, using the native space lessens the computational requirements in terms of number of registrations and learning.

Keywords

Label fusion MRI Multiatlas segmentation Patch space 

Notes

Acknowledgments

This work is co-financed by the Marie Curie FP7-PEOPLE-2012-COFUND Action, Grant agreement no: 600387.

References

  1. 1.
    Aljabar, P., Heckemann, R., Hammers, A., Hajnal, J., Ruecker, D.: Multi-atlas based segmentation of brain images: atlas selection and its effect on accuracy. NeuroImage 46(3), 726–738 (2009)CrossRefGoogle Scholar
  2. 2.
    Avants, B.B., Epstein, C.L., Grossman, M., Gee, J.C.: Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Med. Image Anal. 12(1), 26–41 (2008)CrossRefGoogle Scholar
  3. 3.
    Bai, W., Shi, W., Ledig, C., Rueckert, D.: Multi-atlas segmentation with augmented features for cardiac MR images. Med. Image Anal. 19(1), 98–109 (2015)CrossRefGoogle Scholar
  4. 4.
    Coupé, P., Manjón, J.V., Fonov, V., Pruessner, J., Robles, M., Collins, D.L.: Patch-based segmentation using expert priors: application to hippocampus and ventricle segmentation. NeuroImage 54(2), 940–954 (2011)CrossRefGoogle Scholar
  5. 5.
    Hao, Y., Wang, T., Zhang, X., Duan, Y., Yu, C., Jiang, T., Fan, Y., for the Alzheimer’s Disease Neuroimaging Initiative: Local label learning (LLL) for subcortical structure segmentation: application to hippocampus segmentation. Hum. Brain Mapp. 35(6), 2674–2697 (2014)Google Scholar
  6. 6.
    Rousseau, F., Habas, P.A., Studholme, C.: A supervised patch-based approach for human brain labeling. IEEE Trans. Med. Imaging 30(10), 1852–1862 (2011)CrossRefGoogle Scholar
  7. 7.
    Sanroma, G., Benkarim, O.M., Piella, G., Wu, G., Zhu, X., Shen, D., Ballester, M.Á.G.: Discriminative dimensionality reduction for patch-based label fusion. In: Bhatia, K.K., Lombaert, H. (eds.) MLMMI 2015. LNCS, vol. 9487, pp. 94–103. Springer, Cham (2015). doi: 10.1007/978-3-319-27929-9_10 CrossRefGoogle Scholar
  8. 8.
    Tong, T., Wolz, R., Coup, P., Hajnal, J.V., Rueckert, D.: Segmentation of MR images via discriminative dictionary learning and sparse coding: application to hippocampus labeling. NeuroImage 76, 11–23 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Oualid M. Benkarim
    • 1
    Email author
  • Gemma Piella
    • 1
  • Miguel Angel González Ballester
    • 1
    • 2
  • Gerard Sanroma
    • 1
  1. 1.Universitat Pompeu FabraBarcelonaSpain
  2. 2.ICREABarcelonaSpain

Personalised recommendations