Abstract
How to use frequent and discriminative pattern for identifying brain disease is a hot topic in the area of brain functional network topology analysis. Most of the existing researches mine discriminative sub-network from frequent patterns, thus ignoring the underlying comparison relationship of the discriminative patterns within different groups. To solve this problem, we propose a discriminative sub-network pair (DSP) to represent both the intra-group commonality and inter-group specificity of networks. The DSP consists of a paired frequent sub-network mined from the brain networks of different groups within the same or similar node-set and different edge-set. Specifically, the signals are decomposed into multiple frequency bands, then the multi-frequency network is constructed to model the brain activities. We construct the DSP with the most significant distinguishing ability from the frequent patterns that frequently appear in each group. A feature vector is constructed for each subject based on these pairs by drawing on the network motif idea and the classifier is used to detect Alzheimer’s disease (AD). Comprehensive experiments on ADNI public datasets demonstrate the effectiveness of DSP in the tasks of AD classification, with an accuracy of 83.33%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Achard, S., Salvador, R., Whitcher, B., et al.: A resilient, low-frequency, small-world human brain functional network with highly connected association cortical hubs. J. Neurosci. 26(1), 63–72 (2006)
Battiston, F., Nicosia, V., Chavez, M., et al.: Multi-layer motif analysis of brain networks. Chaos Interdiscip. J. Nonlinear Sci. 27(4), 047404 (2017). https://doi.org/10.1063/1.4979282
Brookes, M.J., Tewarie, P.K., Hunt, B.A., et al.: A multi-layer network approach to MEG connectivity analysis. Neuroimage 132, 425–438 (2016)
De Vos, F., Koini, M., Schouten, T.M., et al.: A comprehensive analysis of resting state fMRI measures to classify individual patients with Alzheimer’s disease. Neuroimage 167, 62–72 (2018). https://doi.org/10.1016/j.neuroimage.2017.11.025
Du, J., Wang, L., Jie, B., et al.: Network-based classification of ADHD patients using discriminative sub-network selection and graph kernel PCA. Comput. Med. Imaging Graph. 52, 82–88 (2016)
Gifford, G., Crossley, N., Kempton, M.J., et al.: Resting state fMRI based multi-layer network configuration in patients with schizophrenia. NeuroImage Clin. 25, 102169 (2020). https://doi.org/10.1016/j.nicl.2020.102169
Guo, H., Qin, M., Chen, J., et al.: Machine-learning classifier for patients with major depressive disorder: Multi-feature approach based on a high-order minimum spanning tree functional brain network. Comput. Math. Methods Med. 2017, 4820935 (2017). https://doi.org/10.1155/2017/4820935
Hämäläinen, A., Pihlajamäki, M., Tanila, H., et al.: Increased fMRI responses during encoding in mild cognitive impairment. Neurobiol. Aging 28(12), 1889–1903 (2007). https://doi.org/10.1016/j.neurobiolaging.2006.08.008
Huang, G., Zhu, Q., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70(1), 489–501 (2006)
Kong, X., Yu, P.S.: Brain network analysis: a data mining perspective. ACM SIGKDD Explor. Newsl. 15(2), 30–38 (2014)
Li, W., Antuono, P.G., Xie, C., et al.: Aberrant functional connectivity in papez circuit correlates with memory performance in cognitively intact middle-aged APOE4 carriers. Cortex 57, 167–176 (2014). https://doi.org/10.1016/j.cortex.2014.04.006
Mallat, S.G.: A theory for multi-resolution signal decomposition: the wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. 11(7), 674–693 (1989). https://doi.org/10.1109/34.192463
Martinez-Murcia, F.J., Ortiz, A., Gorriz, J.M., et al.: Studying the manifold structure of Alzheimer’s disease: a deep learning approach using convolutional autoencoders. IEEE J. Biomed. Health Inform. 24(1), 17–26 (2019)
Peng, C., Wu, X., Yuan, W., et al.: MGRFE: Multi-layer recursive feature elimination based on an embedded genetic algorithm for cancer classification. IEEE/ACM Trans. Comput. Biol. Bioinf. 18(2), 621–632 (2019)
Perea, R.D., Rabin, J.S., Fujiyoshi, M.G., et al.: Connectome-derived diffusion characteristics of the fornix in Alzheimer’s disease. NeuroImage Clin. 19, 331–342 (2018). https://doi.org/10.1016/j.nicl.2018.04.029
Preti, G., De, G., Riondato, M.: MaNIACS: approximate mining of frequent subgraph patterns through sampling. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1348–1358 (2021)
Sasai, S., Koike, T., Sugawara, S.K., et al.: Frequency-specific task modulation of human brain functional networks: a fast fMRI study. Neuroimage 224, 117375 (2021). https://doi.org/10.1016/j.neuroimage.2020.117375
Sharma, S., Mandal, P.K.: A comprehensive report on machine learning-based early detection of Alzheimer’s disease using multi-modal neuroimaging data. ACM Comput. Surv. 55(2), 1–44 (2022). https://doi.org/10.1145/3492865
Thomas, A.W., Heekeren, H.R., Müller, K.R., et al.: Analyzing neuroimaging data through recurrent deep learning models. Front. Neurosci. 13, 1321 (2019)
Ting, C.M., Samdin, S.B., Tang, M., et al.: Detecting dynamic community structure in functional brain networks across individuals: a multi-layer approach. IEEE Trans. Med. Imaging 40(2), 468–480 (2020)
Tokuda, T., Yamashita, O., Yoshimoto, J.: Multiple clustering for identifying subject clusters and brain sub-networks using functional connectivity matrices without vectorization. Neural Netw. 142, 269–287 (2021)
Tzourio-Mazoyer, N., Landeau, B., Papathanassiou, D., et al.: Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. Neuroimage 15(1), 273–289 (2002)
Van Snellenberg, J.X., Slifstein, M., Read, C., et al.: Dynamic shifts in brain network activation during supracapacity working memory task performance. Hum. Brain Mapp. 36(4), 1245–1264 (2015). https://doi.org/10.1002/hbm.22699
Wang, L., Schwedt, T.J., Chong, C.D., et al.: Discriminant subgraph learning from functional brain sensory data. IISE Trans. 54(11), 1084–1097 (2022)
Wu, C.W., Gu, H., Lu, H., et al.: Frequency specificity of functional connectivity in brain networks. Neuroimage 42(3), 1047–1055 (2008)
Wu, D., et al.: Multi-frequency analysis of brain connectivity networks in migraineurs: a magnetoencephalography study. J. Headache Pain 17(1), 1–10 (2016). https://doi.org/10.1186/s10194-016-0636-7
Yan, C., Wang, X., Zuo, X., et al.: DPABI: data processing & analysis for (resting-state) brain imaging. Neuroinformatics 14(3), 339–351 (2016)
Yan, X., Han, J.: gSpan: graph-based substructure pattern mining. In: 2002 IEEE International Conference on Data Mining (ICDM), pp. 721–724. IEEE (2002)
Zanin, M., Sousa, P., Papo, D., et al.: Optimizing functional network representation of multivariate time series. Sci. Rep. 2(1), 1–6 (2012)
Acknowledgements
This work was supported by National Natural Science Foundation of China (62072089); Fundamental Research Funds for the Central Universities of China (N2116016, N2104001, N2019007).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, J., Xin, J., Wang, Z., Wang, X., Dong, S., Wang, Z. (2023). Mining Discriminative Sub-network Pairs in Multi-frequency Brain Functional Networks. In: Wang, X., et al. Database Systems for Advanced Applications. DASFAA 2023. Lecture Notes in Computer Science, vol 13945. Springer, Cham. https://doi.org/10.1007/978-3-031-30675-4_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-30675-4_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30674-7
Online ISBN: 978-3-031-30675-4
eBook Packages: Computer ScienceComputer Science (R0)