Abstract
Autism spectrum disorder (ASD) is a neurodevelopmental disorder closely related to potential dysfunction of the brain. Although multiple functional connectivity (FC) features such as low-order functional connectivity (LOFC) and high-order functional connectivity (HOFC) provide complementary knowledge to each other, it is still challenging to find interpretable LOFC and HOFC features for multi-center ASD diagnosis. To this end, we develop a novel interpretable feature learning method based on multi-output TSK fuzzy system (MO-TSK-FS) for multi-center ASD diagnosis. Specifically, both the LOFC and HOFC features are first mapped to a high-dimensional space using the premise part of MO-TSK-FS, which shares the common knowledge across multiple centers. Then, the mapped features are transformed to a low-dimensional feature space using a transformation matrix. A novel unsupervised learning problem is formulated to find the optimal transformation matrix. Finally, a multi-modality support vector classifier (M2SVC) is constructed for classification. The experimental results show that the proposed interpretable feature learning method for multi-center ASD classification can effectively extract important features from the original LOFC and HOFC features, resulting in an efficient M2SVC for multi-center ASD classification.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anagnostou, E., Taylor, M.J.: Review of neuroimaging in autism spectrum disorders: what have we learned and where we go from here. Mol. Autism 2, 1–9 (2011)
Zhang, H., Chen, X., Shi, F., et al.: Topographical information-based high-order functional connectivity and its application in abnormality detection for mild cognitive impairment. J. Alzheimer’s Dis. 54(3), 1095–1112 (2016)
Wang, J., Wang, Q., Zhang, H., et al.: Sparse multiview task-centralized ensemble learning for ASD diagnosis based on age-and sex-related functional connectivity patterns. IEEE Trans. Cybern. 49(8), 3141–3154 (2019)
Zhang, D., Wang, Y., Zhou, L., et al.: Multimodal classification of Alzheimer’s disease and mild cognitive impairment. Neuroimage 55, 856–867 (2011)
Cameron, C., Yassine, B., Chu, C., et al.: The neuro Bureau Preprocessing Initiative: open sharing of preprocessed neuroimaging data and derivatives. Front. Neuroinformatics 7, 37–53 (2013)
Yan, C.G., Zang, Y.F.: DPARSF: A MATLAB toolbox for “Pipeline” data analysis of resting-state fMRI. Front. Syst. Neurosci. 4, 13 (2010)
Preprocessed Connectomes Project: ABIDE Preprocessed. http://preprocessed-connectomes-project.org/abide
Powers, D.M.W.: Visualization of Tradeoff in Evaluation: from Precision-Recall & PN to LIFT, ROC & BIRD, Computer Science (2015)
Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27 (2011)
Acknowledgements.
This work was supported in part by the Natural Science Foundation of Jiangsu Province (BK20151299, BK20151358, BK20161268 and BK20181339).
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
Wang, J. et al. (2019). Interpretable Feature Learning Using Multi-output Takagi-Sugeno-Kang Fuzzy System for Multi-center ASD Diagnosis. 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_88
Download citation
DOI: https://doi.org/10.1007/978-3-030-32248-9_88
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)