Skip to main content

Sparsity-Learning-Based Longitudinal MR Image Registration for Early Brain Development

  • Conference paper
Machine Learning in Medical Imaging (MLMI 2014)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 8679))

Included in the following conference series:

Abstract

Longitudinal sequences of infant brain MR images are increasingly applied in early brain development studies, while their registration are highly challenging as rapid brain development causes drastic image appearance changes. To this end, we propose a novel sparsity-learning-based strategy to tackle the longitudinal registration of infant subject. First, we prepare a set of intermediate sequences, whose longitudinal (voxel-to-voxel) correspondences are established in advance. For each time point of the subject, we then utilize sparsity learning to identify its correspondences in the intermediate images at the same age and thus of similar appearances. Next, the intermediate sequences are used to bridge the temporal “gaps” between different subject time points, while the sparsity-learning-based correspondence detection is jointly conducted for all subject images to impose the temporal consistency. Finally, the deformation field of each subject time point is reconstructed from the spatio-temporal correspondences. Experimental results show that our method is able to achieve the longitudinal registration of the infant subject despite its varying appearances along time.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Knickmeyer, R.C., Gouttard, S., Kang, C., Evans, D., Wilber, K., Smith, J.K., Hamer, R.M., Lin, W., Gerig, G., Gilmore, J.H.: A structural mri study of human brain development from birth to 2 years. The Journal of Neuroscience 28(47), 12176–12182 (2008)

    Article  Google Scholar 

  2. Aubert-Broche, B., Fonov, V.S., García-Lorenzo, D., Mouiha, A., Guizard, N., Coupé, P., Eskildsen, S.F., Collins, D.L.: A new method for structural volume analysis of longitudinal brain mri data and its application in studying the growth trajectories of anatomical brain structures in childhood. NeuroImage 82, 393–402 (2013)

    Article  Google Scholar 

  3. Durrleman, S., Pennec, X., Trouvé, A., Gerig, G., Ayache, N.: Spatiotemporal atlas estimation for developmental delay detection in longitudinal datasets. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009, Part I. LNCS, vol. 5761, pp. 297–304. Springer, Heidelberg (2009)

    Chapter  Google Scholar 

  4. Holland, D., Dale, A.M.: Nonlinear registration of longitudinal images and measurement of change in regions of interest. Medical Image Analysis 15(4), 489–497 (2011)

    Article  Google Scholar 

  5. Qiu, A., Albert, M., Younes, L., Miller, M.I.: Time sequence diffeomorphic metric mapping and parallel transport track time-dependent shape changes. NeuroImage 45(1), S51–S60 (2009)

    Google Scholar 

  6. Serag, A., Aljabar, P., Counsell, S., Boardman, J., Hajnal, J.V., Rueckert, D.: Lisa: Longitudinal image registration via spatio-temporal atlases. In: 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), pp. 334–337. IEEE (2012)

    Google Scholar 

  7. Studholme, C., Drapaca, C., Iordanova, B., Cardenas, V.: Deformation-based mapping of volume change from serial brain mri in the presence of local tissue contrast change. IEEE Transactions on Medical Imaging 25(5), 626–639 (2006)

    Article  Google Scholar 

  8. Csapo, I., Davis, B., Shi, Y., Sanchez, M., Styner, M., Neithammer, M.: Longitudinal image registration with temporally-dependent image similarity measure. IEEE Transactions on Medical Imaging (2013)

    Google Scholar 

  9. Wang, L., Shi, F., Yap, P.T., Gilmore, J.H., Lin, W., Shen, D.: 4D multi-modality tissue segmentation of serial infant images. PloS One 7(9), e44596 (2012)

    Google Scholar 

  10. Shen, D., Davatzikos, C.: Measuring temporal morphological changes robustly in brain mr images via 4-dimensional template warping. NeuroImage 21(4), 1508–1517 (2004)

    Article  Google Scholar 

  11. Jenkinson, M., Smith, S.: A global optimisation method for robust affine registration of brain images. Medical Image Analysis 5(2), 143–156 (2001)

    Article  Google Scholar 

  12. Wu, G., Wang, Q., Shen, D.: Registration of longitudinal brain image sequences with implicit template and spatial–temporal heuristics. Neuroimage 59(1), 404–421 (2012)

    Article  Google Scholar 

  13. Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Diffeomorphic demons: Efficient non-parametric image registration. NeuroImage 45(1), S61–S72 (2009)

    Google Scholar 

  14. Wright, J., Ma, Y., Mairal, J., Sapiro, G., Huang, T.S., Yan, S.: Sparse representation for computer vision and pattern recognition. Proceedings of the IEEE 98(6), 1031–1044 (2010)

    Article  Google Scholar 

  15. Wang, Q., Kim, M., Wu, G., Shen, D.: Joint learning of appearance and transformation for predicting brain MR image registration. In: Gee, J.C., Joshi, S., Pohl, K.M., Wells, W.M., Zöllei, L. (eds.) IPMI 2013. LNCS, vol. 7917, pp. 499–510. Springer, Heidelberg (2013)

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer International Publishing Switzerland

About this paper

Cite this paper

Wang, Q., Wu, G., Wang, L., Shi, P., Lin, W., Shen, D. (2014). Sparsity-Learning-Based Longitudinal MR Image Registration for Early Brain Development. In: Wu, G., Zhang, D., Zhou, L. (eds) Machine Learning in Medical Imaging. MLMI 2014. Lecture Notes in Computer Science, vol 8679. Springer, Cham. https://doi.org/10.1007/978-3-319-10581-9_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-10581-9_1

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-10580-2

  • Online ISBN: 978-3-319-10581-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics