Barik, Kasturi; Dey, Spandan; Watanabe, Katsumi; Hirosawa, Tetsu; Yoshimura, Yuki; Kikuchi, Mitsuru; Bhattacharya, Joydeep and Saha, Goutam. 2024. Self-Supervised Machine Learning Approach for Autism Detection in Young Children using MEG Signal. Biomedical Signal Processing and Control, 98, 106671. ISSN 1746-8094 [Article]

No full text available

Text SSL_Revised_Manuscript_Minor_final.pdf - Accepted Version Permissions: Administrator Access Only until 17 August 2025. Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (2MB)

Abstract or Description

Objective: Autism spectrum disorder (ASD) encompasses a broad spectrum of developmental disabilities and is associated with aberrant anatomical and functional neural activity patterns. Early detection of autism in young children is crucial for managing its impact effectively, but obtaining brain data from ASD children presents significant challenges. This study aims to develop an automatic and non-invasive method for detecting autism using magnetoencephalogram (MEG) signals from 30 children (4-7 years) with ASD and 30 age-matched typically developing (TD) children.

Methods: We employed a self-supervised learning (SSL) based machine learning framework, which has been successfully used in diverse domains. Specifically, we utilized a cross-domain (speech signal) pre-trained SSL architecture (wav2vec 2.0), leveraging the outputs of its final transformer layer as an embedding extractor for features in our classification. These SSL embedding (SSLE) features were then applied to artificial neural networks and support vector machine classifiers to distinguish between ASD and TD children.

Results: Our results show that the SSLE features yielded an overall classification accuracy of 88.39% attained by neural networks, exceeding the performance of commonly used hand-crafted features extracted from broadband brain oscillations.

Conclusion: The results show that even without in-domain pre-training, SSLE representations effectively discriminate between ASD and TD classes in this experiment. Pretrained SSL architectures, requiring minimal labeled data, outperformed conventional supervised models trained with much larger labelled data. Therefore, the proposed novel approach based on SSLE features shows promise for future autism detection research, especially in scenarios where collection of large data sets may be difficult.

Item Type:	Article
Identification Number (DOI):	https://doi.org/10.1016/j.bspc.2024.106671
Additional Information:	Funding: This work was partially supported by JSPS KAKENHI 22H00090.
Data Access Statement:	Availability of data and material: The codes would be made available at a reasonable request made to the corresponding author.
Keywords:	Autism Spectrum Disorder, Brain Oscillations, Magnetoencephalography, Self-Supervised Learning, wav2vec 2.0
Departments, Centres and Research Units:	Psychology
Dates:	Date Event 31 July 2024 Accepted 17 August 2024 Published Online December 2024 Published
Item ID:	37417
Date Deposited:	12 Aug 2024 15:00
Last Modified:	28 Aug 2024 09:13
Peer Reviewed:	Yes, this version has been peer-reviewed.
URI:	https://research.gold.ac.uk/id/eprint/37417

View statistics for this item...

Edit Record (login required)