Estimation of Brain Network Atlases Using Diffusive-Shrinking Graphs: Application to Developing Brains

  • Islem Rekik
  • Gang Li
  • Weili Lin
  • Dinggang ShenEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10265)


Many methods have been developed to spatially normalize a population of brain images for estimating a mean image as a population- average atlas. However, methods for deriving a network atlas from a set of brain networks sitting on a complex manifold are still absent. Learning how to average brain networks across subjects constitutes a key step in creating a reliable mean representation of a population of brain networks, which can be used to spot abnormal deviations from the healthy network atlas. In this work, we propose a novel network atlas estimation framework, which guarantees that the produced network atlas is clean (for tuning down noisy measurements) and well-centered (for being optimally close to all subjects and representing the individual traits of each subject in the population). Specifically, for a population of brain networks, we first build a tensor, where each of its frontal-views (i.e., frontal matrices) represents a connectivity network matrix of a single subject in the population. Then, we use tensor robust principal component analysis for jointly denoising all subjects’ networks through cleaving a sparse noisy network population tensor from a clean low-rank network tensor. Second, we build a graph where each node represents a frontal-view of the unfolded clean tensor (network), to leverage the local manifold structure of these networks when fusing them. Specifically, we progressively shrink the graph of networks towards the centered mean network atlas through non-linear diffusion along the local neighbors of each of its nodes. Our evaluation on the developing functional and morphological brain networks at 1, 3, 6, 9 and 12 months of age has showed a better centeredness of our network atlases, in comparison with the baseline network fusion method. Further cleaning of the population of networks produces even more centered atlases, especially for the noisy functional connectivity networks.


Functional Connectivity Brain Network Brain Connectivity Individual Network Global Center 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This work is also supported in part by National Institutes of Health grants (MH100217, MH108914 and MH107815) a grant from NIH (1U01MH110274) and UNC/UMN Baby Connectome Project Consortium.


  1. 1.
    Brown, C., Hamarneh, G.: Machine learning on human connectome data from MRI arXiv:1611.08699v1 (2016)
  2. 2.
    Miller, K., Alfaro-Almagro, F., Bangerter, N., Thomas, D., et al.: Multimodal population brain imaging in the UK Biobank prospective epidemiological study. Nat. Neurosci. 19, 1523–1536 (2016)CrossRefGoogle Scholar
  3. 3.
    Fallik, D.: The human connectome project turns to mapping brain development, from birth through early childhood. Neurol. Today 16, 7–9 (2016)Google Scholar
  4. 4.
    Glasser, M., Coalson, T., Robinson, E., Hacker, C.D., et al.: A multi-modal parcellation of human cerebral cortex. Nature 536, 171–178 (2016)CrossRefGoogle Scholar
  5. 5.
    Wassermann, D., Mazauric, D., Gallardo-Diez, G., Deriche, R.: Extracting the core structural connectivity network: guaranteeing network connectedness through a graph-theoretical approach. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9900, pp. 89–96. Springer, Cham (2016). doi: 10.1007/978-3-319-46720-7_11 CrossRefGoogle Scholar
  6. 6.
    Chen, X., Zhang, H., Shen, D.: Ensemble hierarchical high-order functional connectivity networks for MCI classification. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 18–25. Springer, Cham (2016). doi: 10.1007/978-3-319-46723-8_3 CrossRefGoogle Scholar
  7. 7.
    Wu, G., Jia, H., Wang, Q., Shen, D.: SharpMean: groupwise registration guided by sharp mean image and tree-based registration. NeuroImage 56, 1968–1981 (2011)CrossRefGoogle Scholar
  8. 8.
    Lu, C., Feng, J., Chen, Y., Liu, W., et al.: Tensor robust principal component analysis: exact recovery of corrupted low-rank tensors via convex optimization. In: CVPR, pp. 5249–5257 (2016)Google Scholar
  9. 9.
    Wang, B., Mezlini, A., Demir, F., Fiume, M., et al.: Similarity network fusion for aggregating data types on a genomic scale. Nat. Methods 11, 333–337 (2014)CrossRefGoogle Scholar
  10. 10.
    Ying, S., Wu, G., Wang, Q., Shen, D.: Hierarchical unbiased graph shrinkage (HUGS): a novel groupwise registration for large data set. Neuroimage 1, 626–638 (2014)CrossRefGoogle Scholar
  11. 11.
    Frey, B., Dueck, D.: Clustering by passing messages between data points. Science 315, 972–976 (2007)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Li, G., Wang, L., Shi, F., et al.: Simultaneous and consistent labeling of longitudinal dynamic developing cortical surfaces in infants. Med. Image Anal. 18, 1274–1289 (2014)CrossRefGoogle Scholar
  13. 13.
    Wang, L., Shi, F., Lin, W., Gilmore, J.H., Shen, D.: Automatic segmentation of neonatal images using convex optimization and coupled level sets. NeuroImage 58(3), 805–817 (2011)CrossRefGoogle Scholar
  14. 14.
    Li, G., Nie, J., Wang, L., Shi, F., Gilmore, J.H., Lin, W., Shen, D.: NeuroImage 90, 266–279 (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Islem Rekik
    • 1
  • Gang Li
    • 2
  • Weili Lin
    • 2
  • Dinggang Shen
    • 2
    Email author
  1. 1.CVIP, Computing, School of Science and EngineeringUniversity of DundeeDundeeUK
  2. 2.Department of Radiology and BRICUniversity of North Carolina at Chapel HillChapel HillUSA

Personalised recommendations