Advertisement

Data-Specific Feature Selection Method Identification for Most Reproducible Connectomic Feature Discovery Fingerprinting Brain States

  • Nicolas Georges
  • Islem Rekik
  • for the Alzheimers’s Disease Neuroimaging Initiative
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11083)

Abstract

Machine learning methods present unprecedented opportunities to advance our understanding of the connectomics of brain disorders. With the proliferation of extremely high-dimensional connectomic data drawn from multiple neuroimaging sources (e.g., functional and structural MRIs), effective feature selection (FS) methods have become indispensable components for (i) disentangling brain states (e.g., early vs late mild cognitive impairment) and (ii) identifying connectional features that might serve as biomarkers for treatment. Strangely, despite the extensive work on identifying stable discriminative features using a particular FS method, the challenge of choosing the best one from a large pool of existing FS techniques for optimally achieving (i) and (ii) using a dataset of interest remains unexplored. In essence, the question that we aim to address in this work is: “Given a set of feature selection methods \(\{FS_1, \dots , FS_K \}\), and a dataset of interest, which FS method might produce the most reproducible and ‘trustworthy’ connectomic features that accurately differentiate between two brain states?” This paper is an attempt to address this question by evaluating the performance of a particular feature selection for a specific data type in fulfilling criteria (i) and (ii). To this aim, we propose to model the relationships between a set of FS methods using a multi-graph architecture, where each graph quantifies the feature reproducibility power between graph nodes at a fixed number of top ranked features. Next, we integrate the reproducibility graphs with a discrepancy graph which captures the difference in classification performance between FS methods. This allows to identify, for a dataset of interest, the ‘central’ node with the highest degree, which reveals the most reliable and reproducible FS method for the target brain state classification task along with the most discriminative features fingerprinting these brain states. We evaluated our method on multi-view brain connectomic data for late mild cognitive impairment vs Alzheimer’s disease classification. Our experiments give insights into reproducible connectional features fingerprinting late dementia brain states.

References

  1. 1.
    Fornito, A., Zalesky, A., Breakspear, M.: The connectomics of brain disorders. Nat. Rev. Neurosci. 16, 159 (2015)CrossRefGoogle Scholar
  2. 2.
    Mahjoub, I., Mahjoub, M.A., Rekik, I.: Brain multiplexes reveal morphological connectional biomarkers fingerprinting late brain dementia states. Sci. Rep. 8(1), 4103 (2018)CrossRefGoogle Scholar
  3. 3.
    Lisowska, A., Rekik, I.: Joint pairing and structured mapping of convolutional brain morphological multiplexes for early dementia diagnosis. Brain Connectivity (2018).  https://doi.org/10.1089/brain.2018.0578
  4. 4.
    Zhao, F., Zhang, H., Rekik, I., An, Z., Shen, D.: Diagnosis of autism spectrum disorders using multi-level high-order functional networks derived from resting-state functional MRI. Front. Hum. Neurosci. 12, 184 (2018).  https://doi.org/10.3389/fnhumCrossRefGoogle Scholar
  5. 5.
    Bullmore, E., Sporns, O.: Complex brain networks: graph theoretical analysis of structural and functional systems. Nat. Rev. Neurosci. 10, 186 (2009)CrossRefGoogle Scholar
  6. 6.
    Liu, H., Motoda, H.: Computational methods of feature selection (2007)Google Scholar
  7. 7.
    Van Essen, D.C., Glasser, M.F.: The human connectome project: progress and prospects. Cerebrum Dana Forum Brain Sci. 2016 (2016)Google Scholar
  8. 8.
    Lisowska, A., Rekik, I.: Pairing-based ensemble classifier learning using convolutional brain multiplexes and multi-view brain networks for early dementia diagnosis. In: Wu, G., Laurienti, P., Bonilha, L., Munsell, B.C. (eds.) CNI 2017. LNCS, vol. 10511, pp. 42–50. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67159-8_6CrossRefGoogle Scholar
  9. 9.
    Soussia, M., Rekik, I.: High-order connectomic manifold learning for autistic brain state identification. In: Wu, G., Laurienti, P., Bonilha, L., Munsell, B.C. (eds.) CNI 2017. LNCS, vol. 10511, pp. 51–59. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67159-8_7CrossRefGoogle Scholar
  10. 10.
    Wen, H., et al.: Combining disrupted and discriminative topological properties of functional connectivity networks as neuroimaging biomarkers for accurate diagnosis of early tourette syndrome children. Mol. Neurobiol. 55, 3251–3269 (2018)CrossRefGoogle Scholar
  11. 11.
    Kalousis, A., Prados, J., Hilario, M.: Stability of feature selection algorithms: a study on high-dimensional spaces. Knowl. Inf. Syst. 12, 95–116 (2007)CrossRefGoogle Scholar
  12. 12.
    Lustgarten, J.L., Gopalakrishnan, V., Visweswaran, S.: Measuring stability of feature selection in biomedical datasets. In: AMIA Annual Symposium Proceedings, vol. 2009, p. 406. American Medical Informatics Association (2009)Google Scholar
  13. 13.
    Chen, Y.W., Lin, C.J.: Combining SVMs with various feature selection strategies. In: Feature extraction, pp. 315–324. Springer, Heidelberg (2006).  https://doi.org/10.1007/978-3-540-35488-8_13
  14. 14.
    Mueller, S.G.: The alzheimer’s disease neuroimaging initiative. Neuroimaging Clin. North Am. 10, 869–877 (2005)CrossRefGoogle Scholar
  15. 15.
    Fischl, B.: Automatically parcellating the human cerebral cortex. Cereb. Cortex 14, 11–22 (2004)CrossRefGoogle Scholar
  16. 16.
    Roffo, G.: Feature selection library (MATLAB toolbox). arXiv preprint arXiv:1607.01327 (2016)
  17. 17.
    Kononenko, I., Šimec, E., Robnik-Šikonja, M.: Overcoming the myopia of inductive learning algorithms with RELIEFF. Appl. Intell. 7, 39–55 (1997)CrossRefGoogle Scholar
  18. 18.
    Estévez, P.A., Tesmer, M., Perez, C.A., Zurada, J.M.: Normalized mutual information feature selection. IEEE Trans. Neural Netw. 20, 189–201 (2009)CrossRefGoogle Scholar
  19. 19.
    He, X., Cai, D., Niyogi, P.: Laplacian score for feature selection. In: Advances in Neural Information Processing Systems, pp. 507–514 (2006)Google Scholar
  20. 20.
    Han, J., Sun, Z., Hao, H.: l0-norm based structural sparse least square regression for feature selection. Pattern Recogn. 48, 3927–3940 (2015)CrossRefGoogle Scholar
  21. 21.
    Yang, Y., Shen, H.T., Ma, Z., Huang, Z., Zhou, X.: l2, 1-norm regularized discriminative feature selection for unsupervised learning. In: IJCAI Proceedings-International Joint Conference on Artificial Intelligence, vol. 22, p. 1589 (2011)Google Scholar
  22. 22.
    Zeng, H., Cheung, Y.m.: Feature selection and kernel learning for local learning-based clustering. IEEE Trans. Patt. Anal. Mach. Intell. 33, 1532–1547 (2011)Google Scholar
  23. 23.
    Hall, M.A.: Correlation-based feature selection for machine learning (1999)Google Scholar
  24. 24.
    Wee, C.Y., Yap, P.T., Shen, D., Initiative, A.D.N.: Prediction of Alzheimer’s disease and mild cognitive impairment using cortical morphological patterns. Hum. Brain Mapp. 34, 3411–3425 (2013)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Nicolas Georges
    • 1
  • Islem Rekik
    • 1
  • for the Alzheimers’s Disease Neuroimaging Initiative
  1. 1.BASIRA lab, CVIP group, School of Science and Engineering, ComputingUniversity of DundeeDundeeUK

Personalised recommendations