Abstract
Autism Spectrum Disorder (ASD) is a neurological disorder that affects a person’s behavior and social interaction. Integrating machine learning algorithms with neuroimages a diagnosis method can be established to detect ASD subjects from typical control (TC) subjects. In this study, we develop autoencoder based ASD diagnosis methods. Firstly, we design an autoencoder to extract high-level features from raw features, which are defined based on eigenvalues and centralities of functional brain networks constructed with the entire Autism Brain Imaging Data Exchange 1 (ABIDE 1) dataset. Secondly, we use these high-level features to train several traditional machine learning methods (SVM, KNN, and subspace discriminant), which achieve the classification accuracy of 72.6% and the area under the receiving operating characteristic curve (AUC) of 79.0%. We also use these high-level features to train a deep neural network (DNN) which achieves the classification accuracy of 76.2% and the AUC of 79.7%. Thirdly, we combine the pre-trained autoencoder with the DNN to train it, which achieves the classification accuracy of 79.2%, and the AUC of 82.4%. Finally, we also train SVM, KNN, and subspace discriminant with the features extracted from the combination of the pre-trained autoencoder and the DNN which achieves the classification accuracy of 74.6% and the AUC of 78.7%. These results show that our proposed methods for diagnosis of ASD outperform state-of-the-art studies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hirvikoski, T., et al.: Premature mortality in autism spectrum disorder. Br. J. Psychiatry 208(3), 232–238 (2016)
Lord, C., et al.: Autism diagnostic observation schedule: a standardized observation of communicative and social behavior. J. Autism Dev. Disord. 19(2), 185–212 (1989). https://doi.org/10.1007/BF02211841
Lord, C., Rutter, M., Le Couteur, A.: Autism Diagnostic Interview-Revised: a revised version of a diagnostic interview for caregivers of individuals with possible pervasive developmental disorders. J. Autism Dev. Disord. 24(5), 659–685 (1994). https://doi.org/10.1007/BF02172145
Heinsfeld, A.S., et al.: Identification of autism spectrum disorder using deep learning and the ABIDE dataset. NeuroImage Clin. 17, 16–23 (2017)
Autism Brain Imaging Data Exchange I ABIDE I. http://fcon_1000.projects.nitrc.org/indi/abide/abide_I.html. Accessed 24 May 2019
Eslami, T., et al.: ASD-DiagNet: a hybrid learning approach for detection of Autism Spectrum Disorder using fMRI data. arXiv preprint arXiv:1904.07577v1
Wong, E., Anderson, J.S., Zielinski, B.A., Fletcher, P.T.: Riemannian regression and classification models of brain networks applied to autism. In: Wu, G., Rekik, I., Schirmer, M.D., Chung, A.W., Munsell, B. (eds.) CNI 2018. LNCS, vol. 11083, pp. 78–87. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00755-3_9
Kong, Y., et al.: Classification of autism spectrum disorder by combining brain connectivity and deep neural network classifier. Neurocomputing 324, 63–68 (2019)
Watanabe, T., Rees, G.: Brain network dynamics in high-functioning individuals with autism. Nat. Commun. 8(1), 16048 (2017)
Yahata, N., et al.: A small number of abnormal brain connections predicts adult autism spectrum disorder. Nat. Commun. 7(1), 11254 (2016)
Arbabshirani, M.R., et al.: Single subject prediction of brain disorders in neuroimaging: promises and pitfalls. Neuroimage 145, 137–165 (2017)
Mostafa, S., et al.: Diagnosis of autism spectrum disorder based on eigenvalues of brain networks. IEEE Access 7(1), 128474–128486 (2019)
Xing, X., et al.: Convolutional neural network with element-wise filters to extract hierarchical topological features for brain networks. In: 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018, Madrid, pp. 780–783. IEEE (2019)
Martino, A.D., et al.: The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol. Psychiatry 19(6), 659–667 (2014)
Cox, R.W.: AFNI: software for analysis and visualization of functional magnetic resonance neuroimages. Comput. Biomed. Res. 29(3), 162–173 (1996)
Jenkinson, M., et al.: FSL. Neuroimage 62(2), 782–790 (2012)
Power, J.D., et al.: Functional network organization of the human brain. Neuron 72(4), 665–678 (2011)
Mijalkov, M., et al.: BRAPH: a graph theory software for the analysis of brain connectivity. PLoS ONE 12(8), 0178798 (2017)
Hosseini-Asl, E., et al.: Alzheimer’s disease diagnostics by adaptation of 3D convolutional network. In: 2016 IEEE International Conference on Image Processing (ICIP), USA, pp. 126–130. IEEE (2016)
Han, K., et al.: Autoencoder feature selector. arXiv preprint arXiv:1710.08310v1
Train Classification Models in Classification Learner App - MATLAB & Simulink. https://www.mathworks.com/help/stats/train-classification-models-in-classification-learner-app.html. Accessed 24 July 2019
Acknowledgment
This work is supported by the Natural Science and Engineering Research Council of Canada (NSERC).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Mostafa, S., Yin, W., Wu, FX. (2020). Autoencoder Based Methods for Diagnosis of Autism Spectrum Disorder. In: Măndoiu, I., Murali, T., Narasimhan, G., Rajasekaran, S., Skums, P., Zelikovsky, A. (eds) Computational Advances in Bio and Medical Sciences. ICCABS 2019. Lecture Notes in Computer Science(), vol 12029. Springer, Cham. https://doi.org/10.1007/978-3-030-46165-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-46165-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-46164-5
Online ISBN: 978-3-030-46165-2
eBook Packages: Computer ScienceComputer Science (R0)