Abstract
Diffusion MRI-derived brain structural connectomes or brain networks are widely used in the brain research. However, constructing brain networks is highly dependent on various tractography algorithms, which leads to difficulties in deciding the optimal view concerning the downstream analysis. In this paper, we propose to learn a unified representation from multi-view brain networks. Particularly, we expect the learned representations to convey the information from different views fairly and in a disentangled sense. We achieve the disentanglement via an approach using unsupervised variational graph auto-encoders. We achieve the view-wise fairness, i.e. proportionality, via an alternative training routine. More specifically, we construct an analogy between training the deep network and the network flow problem. Based on the analogy, the fair representations learning is attained via a network scheduling algorithm aware of proportionality. The experimental results demonstrate that the learned representations fit various downstream tasks well. They also show that the proposed approach effectively preserves the proportionality.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: OSDI, pp. 265–283 (2016)
Aganj, I., et al.: A Hough transform global probabilistic approach to multiple-subject diffusion MRI tractography. Med. Image Anal. 15(4), 414–425 (2011)
Aminmansour, F. et al.: Learning macroscopic brain connectomes via group-sparse factorization. In: Advances in Neural Information Processing Systems, pp. 8847–8857 (2019)
Bengio, Y., et al.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013)
Bullmore, E., et al.: Complex brain networks: graph theoretical analysis of structural and functional systems. Nat. Rev. Neurosci. 10(3), 186–198 (2009)
Bullmore, E.T., Bassett, D.S.: Brain graphs: graphical models of the human brain connectome. Ann. Rev. Clin. Psychol. 7, 113–140 (2011)
Caspell-Garcia, C., et al.: Multiple modality biomarker prediction of cognitive impairment in prospectively followed de novo Parkinson disease. PLoS ONE 12(5), e0175674 (2017)
Higgins, I., et al.: beta-VAE: learning basic visual concepts with a constrained variational framework. ICLR 2(5), 6 (2017)
Huang, F., Chen, S.: Learning dynamic conditional gaussian graphical models. IEEE Trans. Knowl. Data Eng. 30(4), 703–716 (2017)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016)
Ktena, S.I., et al.: Distance metric learning using graph convolutional networks: application to functional brain networks. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 469–477. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66182-7_54
Kumar, A., Rai, P., Daume, H.: Co-regularized multi-view spectral clustering. In: Advances in Neural Information Processing Systems, pp. 1413–1421 (2011)
Kushner, H.J., et al.: Convergence of proportional-fair sharing algorithms under general conditions. IEEE Trans. Wirel. Commun. 3(4), 1250–1259 (2004)
Liu, J., Wang, C., Gao, J., Han, J.: Multi-view clustering via joint nonnegative matrix factorization. In: SIAM International Conference on Data Mining, pp. 252–260. SIAM (2013)
Luo, L., Xu, J., Deng, C., Huang, H.: Robust metric learning on Grassmann manifolds with generalization guarantees. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4480–4487 (2019)
Moyer, D., Ver Steeg, G., Tax, C.M., Thompson, P.M.: Scanner invariant representations for diffusion MRI harmonization. Magn. Reson. Med. 84(4), 2174–2189 (2020)
Neher, P.F., Götz, M., Norajitra, T., Weber, C., Maier-Hein, K.H.: A machine learning based approach to fiber tractography using classifier voting. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 45–52. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24553-9_6
Parker, G.J., et al.: A framework for a streamline-based probabilistic index of connectivity (PICo) using a structural interpretation of MRI diffusion measurements. J. Magn. Reson. Imaging 18(2), 242–254 (2003)
Paszke, A. et al.: Automatic differentiation in PyTorch (2017)
Poulin, P., et al.: Learn to track: deep learning for tractography. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 540–547. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66182-7_62
Wang, Q., et al.: The added value of diffusion-weighted MRI-derived structural connectome in evaluating mild cognitive impairment: a multi-cohort validation. J. Alzheimer’s Dis. 64(1), 149–169 (2018)
Wang, Q., Sun, M., Zhan, L., Thompson, P., Ji, S., Zhou, J.: Multi-modality disease modeling via collective deep matrix factorization. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1155–1164 (2017)
Wang, Q., Zhan, L., Thompson, P.M., Dodge, H.H., Zhou, J.: Discriminative fusion of multiple brain networks for early mild cognitive impairment detection. In: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), pp. 568–572. IEEE (2016)
Zhan, L., et al.: Comparison of nine tractography algorithms for detecting abnormal structural brain networks in Alzheimer’s disease. Front. Aging Neurosci. 7, 48 (2015)
Zhang, X., et al.: Multi-view graph convolutional network and its applications on neuroimage analysis for Parkinson’s disease. In: AMIA Annual Symposium Proceedings, vol. 2018, p. 1147 (2018)
Zhang, Y., Huang, H.: New graph-blind convolutional network for brain connectome data analysis. In: Chung, A.C.S., Gee, J.C., Yushkevich, P.A., Bao, S. (eds.) IPMI 2019. LNCS, vol. 11492, pp. 669–681. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20351-1_52
Zhang, Y., Zhan, L., Cai, W., Thompson, P., Huang, H.: Integrating heterogeneous brain networks for predicting brain disease conditions. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 214–222. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32251-9_24
Zhang, Y., Zhan, L., Thompson, P.M., Huang, H.: Biological knowledge guided deep neural network for brain genotype-phenotype association study. In: Zhu, D., et al. (eds.) MBIA/MFCA -2019. LNCS, vol. 11846, pp. 84–92. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-33226-6_10
Acknowledgements
This work was partially supported by NSF IIS 1845666, 1852606, 1838627, 1837956, 1956002, 2045848, IIA 2040588, and NIH U01AG068057, R01AG049371, R01AG071243, RF1MH125928.
The NACC database was funded by NIA U01AG016976. The ADNI data were funded by the Alzheimer’s Disease Metabolomics Consortium (NIA R01AG046171, RF1AG051550 and 3U01AG024904-09S4). The PPMI data were obtained from the Parkinson’s Progression Markers Initiative (PPMI) database.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, Y., Zhan, L., Wu, S., Thompson, P., Huang, H. (2021). Disentangled and Proportional Representation Learning for Multi-view Brain Connectomes. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12907. Springer, Cham. https://doi.org/10.1007/978-3-030-87234-2_48
Download citation
DOI: https://doi.org/10.1007/978-3-030-87234-2_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87233-5
Online ISBN: 978-3-030-87234-2
eBook Packages: Computer ScienceComputer Science (R0)