Abstract
Mounting evidence shows that many neuro-disorders can be understood as a dysfunction syndrome where the structural and functional connectivities of the large-scale network are progressively disrupted. In this regard, the subject-specific longitudinal pattern of network alterations is often more putative than other biomarkers discovered from cross-sectional network data. However, current computational approaches for brain network analysis are mainly designed for cross-sectional data, lacking the capability to accurately characterize the longitudinal brain network changes. To address this limitation, we propose to jointly estimate the brain networks at all time points by hierarchically regularizing temporal consistency in a local to a global manner, where we not only penalize the neurologically unreasonable longitudinal changes at each connection but also encourage maintaining the network geometry along time. By integrating this domain knowledge, we present a group-wise graph learning approach to construct longitudinal networks, which allows us to enhance the statistical power and replicability in network analyses. We present promising group comparison results in a longitudinal study of Alzheimer’s disease using structural neuroimaging data from the ADNI database, compared with the conventional cross-sectional network analysis approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sporns, O.: Structure and function of complex brain networks. Dialogues Clin. Neurosci. 15(3), 247–262 (2013)
Zalesky, A., Fornito, A., Bullmore, E.: Network-based statistic: identifying differences in brain networks. Neuroimage 53(4), 1197–1207 (2010)
Mori, S., Zijl, P.: Fiber tracking: principles and strategies - a technical review. NMR Biomed. 15(7–8), 468–480 (2002)
Nie, F., Wang, X., Huang, H.: Clustering and projected clustering with adaptive neighbors. In: Proceedings of the \(20^{th}\) ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 977–986. ACM, New York (2014). https://doi.org/10.1145/2623330.2623726
Destrieux, C., Fischl, B., Dale, A., Halgren, E.: Automatic parcellation of human cortical gyri and sulci using standard anatomical nomenclature. NeuroImage 53(1), 1–15 (2010). https://doi.org/10.1016/j.neuroimage
Narasimhan, M., Jojic, N., Bilmes, J.A.: Q-clustering. In: Weiss, Y., Schölkopf, B., Platt, J.C. (eds.) Advances in Neural Information Processing Systems, vol. 18, pp. 979–986. MIT Press, Cambridge (2006)
Meila, M.: Comparing clusterings. In: Proceedings of 16th Annual Conference on Learning Theory (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Turja, M.A., Zsembik, L.C.P., Wu, G., Styner, M. (2019). Constructing Consistent Longitudinal Brain Networks by Group-Wise Graph Learning. In: Shen, D., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11766. Springer, Cham. https://doi.org/10.1007/978-3-030-32248-9_73
Download citation
DOI: https://doi.org/10.1007/978-3-030-32248-9_73
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32247-2
Online ISBN: 978-3-030-32248-9
eBook Packages: Computer ScienceComputer Science (R0)