Advertisement

Riemannian Regression and Classification Models of Brain Networks Applied to Autism

  • Eleanor Wong
  • Jeffrey S. Anderson
  • Brandon A. Zielinski
  • P. Thomas Fletcher
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11083)

Abstract

Functional connectivity from resting-state functional MRI (rsfMRI) is typically represented as a symmetric positive definite (SPD) matrix. Analysis methods that exploit the Riemannian geometry of SPD matrices appropriately adhere to the positive definite constraint, unlike Euclidean methods. Recently proposed approaches for rsfMRI analysis have achieved high accuracy on public datasets, but are computationally intensive and difficult to interpret. In this paper, we show that we can get comparable results using connectivity matrices under the log-Euclidean and affine-invariant Riemannian metrics with relatively simple and interpretable models. On ABIDE Preprocessed dataset, our methods classify autism versus control subjects with 71.1% accuracy. We also show that Riemannian methods beat baseline in regressing connectome features to subject autism severity scores.

References

  1. 1.
    Abraham, A., et al.: Deriving reproducible biomarkers from multi-site resting-state data: an autism-based example. NeuroImage 147, 736–745 (2017)CrossRefGoogle Scholar
  2. 2.
    Anirudh, R., Thiagarajan, J.J.: Bootstrapping graph convolutional neural networks for autism spectrum disorder classification. arXiv preprint arXiv:1704.07487 (2017)
  3. 3.
    Arsigny, V., Fillard, P., Pennec, X., Ayache, N.: Log-Euclidean metrics for fast and simple calculus on diffusion tensors. Magn. Reson. Med. 56(2), 411–421 (2006)CrossRefGoogle Scholar
  4. 4.
    Arsigny, V., Fillard, P., Pennec, X., Ayache, N.: Geometric means in a novel vector space structure on symmetric positive-definite matrices. SIAM J. Matrix Anal. Appl. 29(1), 328–347 (2007)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Assaf, M., Jagannathan, K., Calhoun, V.D., Miller, L., Stevens, M.C., et al.: Abnormal functional connectivity of default mode subnetworks in autism spectrum disorder patients. NeuroImage 53(1), 247–256 (2010)CrossRefGoogle Scholar
  6. 6.
    Cornea, E., Zhu, H., Kim, P., Ibrahim, J.G., Alzheimers Disease Neuroimaging Initiative: Regression models on Riemannian symmetric spaces. Stat. Methodol. 79(2), 463–482 (2017)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Craddock, C., et al.: The neuro bureau preprocessing initiative: open sharing of preprocessed neuroimaging data and derivativesGoogle Scholar
  8. 8.
    Dodero, L., Minh, H.Q., San Biagio, M., Murino, V., Sona, D.: Kernel-based classification for brain connectivity graphs on the Riemannian manifold of positive definite matrices. In: Biomedical Imaging (ISBI), pp. 42–45. IEEE (2015)Google Scholar
  9. 9.
    Dvornek, N.C., Ventola, P., Pelphrey, K.A., Duncan, J.S.: Identifying autism from resting-state fMRI using long short-term memory networks. In: Wang, Q., Shi, Y., Suk, H.-I., Suzuki, K. (eds.) MLMI 2017. LNCS, vol. 10541, pp. 362–370. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67389-9_42CrossRefGoogle Scholar
  10. 10.
    Fletcher, P.T., Lu, C., Pizer, S.M., Joshi, S.: Principal geodesic analysis for the study of nonlinear statistics of shape. TMI 23(8), 995–1005 (2004)Google Scholar
  11. 11.
    Sólon Heinsfeld, A., Franco, A.R., Craddock, R.C., Buchweitz, A., Meneguzzi, F.: Identification of autism spectrum disorder using deep learning and the abide dataset. NeuroImage Clin. 17, 16–23 (2018)CrossRefGoogle Scholar
  12. 12.
    Huang, Z., Van Gool, L.J.: A Riemannian network for SPD matrix learning (2017)Google Scholar
  13. 13.
    Ionescu, C., Vantzos, O., Sminchisescu, C.: Matrix backpropagation for deep networks with structured layers. In: ICCV, pp. 2965–2973 (2015)Google Scholar
  14. 14.
    Kim, H.J., et al.: Multivariate general linear models (MGLM) on Riemannian manifolds with applications to statistical analysis of diffusion weighted images. In: CVPR, pp. 2705–2712 (2014)Google Scholar
  15. 15.
    Meszlényi, R.J., Buza, K., Vidnyánszky, Z.: Resting state fMRI functional connectivity-based classification using a convolutional neural network architecture. Front. Neuroinformatics 11, 61 (2017)CrossRefGoogle Scholar
  16. 16.
    Ng, B., Dressler, M., Varoquaux, G., Poline, J.B., Greicius, M., Thirion, B.: Transport on Riemannian manifold for functional connectivity-based classification. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8674, pp. 405–412. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10470-6_51CrossRefGoogle Scholar
  17. 17.
    Parisot, S., et al.: Spectral graph convolutions for population-based disease prediction. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 177–185. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66179-7_21CrossRefGoogle Scholar
  18. 18.
    Pennec, X., Arsigny, V., Fillard, P., Ayache, N.: Fast and simple computations on tensors with log-Euclidean metrics (2005)Google Scholar
  19. 19.
    Smith, S.M., Fox, P.T., Miller, K.L., et al.: Correspondence of the brain’s functional architecture during activation and rest. PNAS 106(31), 13040–13045 (2009)CrossRefGoogle Scholar
  20. 20.
    Varoquaux, G., Baronnet, F., Kleinschmidt, A., Fillard, P., Thirion, B.: Detection of brain functional-connectivity difference in post-stroke patients using group-level covariance modeling. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6361, pp. 200–208. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15705-9_25CrossRefGoogle Scholar
  21. 21.
    Weng, S., et al.: Alterations of resting state functional connectivity in the default network in adolescents with autism spectrum disorders. Brain Res. 1313, 202–214 (2010)CrossRefGoogle Scholar
  22. 22.
    Yerys, B.E., Gordon, E.M., Abrams, D.N., Satterthwaite, T.D., et al.: Default mode network segregation and social deficits in autism spectrum disorder: evidence from non-medicated children. NeuroImage Clin. 9, 223–232 (2015)CrossRefGoogle Scholar
  23. 23.
    Young, J., Lei, D., Mechelli, A.: Discriminative log-Euclidean kernels for learning on brain networks. In: Wu, G., Laurienti, P., Bonilha, L., Munsell, B.C. (eds.) CNI 2017. LNCS, vol. 10511, pp. 25–34. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67159-8_4CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Eleanor Wong
    • 1
  • Jeffrey S. Anderson
    • 1
  • Brandon A. Zielinski
    • 1
  • P. Thomas Fletcher
    • 1
  1. 1.University of UtahSalt Lake CityUSA

Personalised recommendations