Abstract
Alzheimer’s disease (AD) is a common neurodegenerative brain disease, which seriously affects the quality of life. Predicting its early stage (e.g., mild cognitive impairment (MCI) and significant memory concern (SMC)) has great significance for early diagnosis. As the vague imaging features of MCI and SMC, graph convolution network (GCN) has been widely used as its advantage of fusing phenotypic information (e.g., gender and age) and establishing relationship between subjects for filtering. Graph U-Net can integrate GCN into U-Net structure with promising classification performance, but it ignores the structure information of graph in the pooling process and leads to the loss of important nodes. To capture the high-order information in the graph, and integrate the structure and node feature information in its pooling operation, a structure and feature based graph U-Net (SFG U-Net) is proposed to predict MCI and SMC in this paper. Firstly, we use the sliding window method to construct dynamic functional connection network (FCN) based on functional magnetic resonance imaging (fMRI). Secondly, we combine image information and phenotypic information to construct functional graph. Thirdly, the structure and the feature of the node in graph are considered in the adaptive pooling layer. Lastly, we get the final diagnosis result by inputting the graph into SFG U-Net. The proposed method is validated on the public data set of the Alzheimer’s Disease Neuroimaging Initiative (ADNI), which achieves a mean classification accuracy of 83.69%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alzheimer's Association: 2019 Alzheimer’s disease facts and figures. Alzheimer’s Dement. 15, 321–387 (2019)
Risacher, S.L., Kim, S., Nho, K., Foroud, T., Shen, L., Petersen, R.C., et al.: APOE effect on Alzheimer’s disease biomarkers in older adults with significant memory concern. Alzheimer’s Dement. 11, 1417–1429 (2015)
Gauthier, S., Reisberg, B., Zaudig, M., Petersen, R.C., Ritchie, K., Broich, K., et al.: Mild cognitive impairment. Lancet 367, 1262–1270 (2006)
Hampel, H., Lista, S.J.: The rising global tide of cognitive impairment. Nat. Rev. Neurol. 12, 131–132 (2016)
Li, Y., Liu, J., Tang, Z., Lei, B.J.: Deep spatial-temporal feature fusion from adaptive dynamic functional connectivity for MCI identification. IEEE Trans. Med. Imaging 39, 2818–2830 (2020)
Li, Y., Liu, J., Gao, X., Jie, B., Kim, M., Yap, P.-T., et al.: Multimodal hyper-connectivity of functional networks using functionally-weighted LASSO for MCI classification. Med. Image Anal. 52, 80–96 (2019)
Lei, B., Yang, P., Wang, T., Chen, S., Ni, D.: Relational-regularized discriminative sparse learning for Alzheimer’s disease diagnosis. IEEE Trans. Cybern. 47, 1102–1113 (2017)
Yang, P., Zhou, F., Ni, D., Xu, Y., Lei, B.J.: Fused sparse network learning for longitudinal analysis of mild cognitive impairment. IEEE Trans. Cybern. 47, 1–14 (2019)
Huettel, S.A., Song, A.W., McCarthy, G.: Functional Magnetic Resonance Imaging, vol. 1. Sinauer Associates, Sunderland (2004)
Chen, B., Wang, S., Sun, W., Shang, X., Liu, H., Liu, G., et al.: Functional and structural changes in gray matter of Parkinson’s disease patients with mild cognitive impairment. Eur. J. Radiol. 93, 16–23 (2017)
Uddin, L.Q., Clare Kelly, A., Biswal, B.B., Xavier Castellanos, F., Milham, M.P.J.: Functional connectivity of default mode network components: correlation, anticorrelation, and causality. Hum. Brain Mapp. 30, 625–637 (2009)
Arbabshirani, M.R., Damaraju, E., Phlypo, R., Plis, S., Allen, E., Ma, S., et al.: Impact of autocorrelation on functional connectivity. Neuroimage 102, 294–308 (2014)
Mu, Y., Liu, X., Wang, L.J.: A Pearson’s correlation coefficient based decision tree and its parallel implementation. Inf. Sci. 435, 40–58 (2018)
Schwab, S., Harbord, R., Zerbi, V., Elliott, L., Afyouni, S., Smith, J.Q., et al.: Directed functional connectivity using dynamic graphical models. Neuroimage 175, 340–353 (2018)
Song, X., et al.: Graph convolution network with similarity awareness and adaptive calibration for disease-induced deterioration prediction. Med. Image Anal. 69, 101947 (2021)
Gao, H., Ji, S.: Graph U-Nets. In: International Conference on Machine Learning, pp. 2083–2092 (2019)
Lostar, M., Rekik, I.J.: Deep Hypergraph U-Net for Brain Graph Embedding and Classification. arXiv preprint arXiv:13118 (2020)
Wang, J., Ma, A., Chang, Y., Gong, J., Jiang, Y., Qi, R., et al.: scGNN is a novel graph neural network framework for single-cell RNA-Seq analyses. Nat. Commun. 12, 1–11 (2021)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234–241 (2015)
Kipf, T.N., Welling, M.J.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:02907 (2016)
Parisot, S., Ktena, S.I., Ferrante, E., Lee, M., Guerrero, R., Glocker, B., et al.: Disease prediction using graph convolutional networks: application to autism spectrum disorder and Alzheimer’s disease. Med. Image Anal. 48, 117–130 (2018)
Feng, Y., You, H., Zhang, Z., Ji, R., Gao, Y.: Hypergraph neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3558–3565 (2019)
Farris, J.S., Kallersjo, M., Kluge, A.G., Bult, C.J.: Constructing a significance test for incongruence. Syst. Biol. 44, 570–572 (1995)
Chertkow, H., Bub, D.J.: Semantic memory loss in dementia of Alzheimer’s type: what do various measures measure? Brain 113, 397–417 (1990)
Zhang, Y., Simon-Vermot, L., Caballero, M.Á.A., Gesierich, B., Taylor, A.N., Duering, M., et al.: Enhanced resting-state functional connectivity between core memory-task activation peaks is associated with memory impairment in MCI. Neurobiol. Aging 45, 43–49 (2016)
Zanchi, D., Giannakopoulos, P., Borgwardt, S., Rodriguez, C., Haller, S.J.: Hippocampal and amygdala gray matter loss in elderly controls with subtle cognitive decline. Front. Aging Neurosci. 9, 50 (2017)
Lin, F., Ren, P., Lo, R.Y., Chapman, B.P., Jacobs, A., Baran, T.M., et al.: Insula and inferior frontal gyrus’ activities protect memory performance against Alzheimer’s disease pathology in old age. J. Alzheimer’s Dis. 55, 669–678 (2017)
Acknowledgement
This work was supported partly by National Natural Science Foundation of China (Nos. 6210010638), China Postdoctoral Science Foundation (Nos. 2019M653014).
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
Zhu, Y., Song, X., Qiu, Y., Zhao, C., Lei, B. (2021). Structure and Feature Based Graph U-Net for Early Alzheimer’s Disease Prediction. In: Syeda-Mahmood, T., et al. Multimodal Learning for Clinical Decision Support. ML-CDS 2021. Lecture Notes in Computer Science(), vol 13050. Springer, Cham. https://doi.org/10.1007/978-3-030-89847-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-89847-2_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89846-5
Online ISBN: 978-3-030-89847-2
eBook Packages: Computer ScienceComputer Science (R0)
