TY - JOUR
T1 - Multi-site diagnostic classification of Autism spectrum disorder using adversarial deep learning on resting-state fMRI
AU - Tang, Yan
AU - Tong, Gan
AU - Xiong, Xing
AU - Zhang, Chengyuan
AU - Zhang, Hao
AU - Yang, Yuan
N1 - Funding Information:
This work was supported in part by the High Performance Computing Center of Central South University. The author would like to thank the 2020 Key Project of Research on Postgraduate Education and Teaching Reform of Central South University [grant numbers 2020JGA011] and the Research Fund of the Guangxi Key Lab of Multi-source Information Mining and Security [grant number MIMS20-08] for their supports.
Funding Information:
This work was supported in part by the High Performance Computing Center of Central South University. The author would like to thank the 2020 Key Project of Research on Postgraduate Education and Teaching Reform of Central South University [grant numbers 2020JGA011] and the Research Fund of the Guangxi Key Lab of Multi-source Information Mining and Security [grant number MIMS20-08] for their supports. The dataset of this paper was obtained from Autism Brain Imaging Data Exchange (ABIDE) (https://fcon_1000.projects.nitrc.org/indi/abide/). Our work was finished by the custom code, which will be available to share upon the request. Ethical Approval This study was approved by the Research Ethics Committee of Central South University and New York University Langone Medical Center. Consent to Participate The authors have agreed to participate in this work. Consent for Publication The publication of this work was approved by Central South University, China and New York University Langone Medical Center, United States.
Publisher Copyright:
© 2023 Elsevier Ltd
PY - 2023/8
Y1 - 2023/8
N2 - Existing imaging studies in Autism spectrum disorder (ASD) mainly focused on single-site resting-state functional magnetic resonance imaging (rs-fMRI) data, which may contain limited samples and suffer from geographic bias. The lack of effective detection in information mining of rs-fMRI is a main reason for affecting the recognition rate of multi-site diagnostic. This study aims to propose a two-stage adversarial learning model with sliding window that integrates information from multi-site rs-fMRI data at the cost of minimal information loss. First, single rs-fMRI data is sampled with a sliding window to preserve both the spatial and temporal information of original data. And then, site-shared features of these samples are extracted through an adversarial learning model. Finally, the model is fine-tuned to learn discriminative disease-related features. Experimental results show that through adversarial learning, the heterogeneity problem among multi-site data is solved. Furthermore, the spatial–temporal information on rs-fMRI is effectively extracted and yields better classification performance (0.80 accuracy, 0.81 sensitivity, 0.80 specificity) than the state-of-the-art methods. Our results demonstrate the feasibility of the proposed method in the ASD classification task and the importance of fully exploiting the site-shared and spatial–temporal information in rs-fMRI data for multi-site ASD study.
AB - Existing imaging studies in Autism spectrum disorder (ASD) mainly focused on single-site resting-state functional magnetic resonance imaging (rs-fMRI) data, which may contain limited samples and suffer from geographic bias. The lack of effective detection in information mining of rs-fMRI is a main reason for affecting the recognition rate of multi-site diagnostic. This study aims to propose a two-stage adversarial learning model with sliding window that integrates information from multi-site rs-fMRI data at the cost of minimal information loss. First, single rs-fMRI data is sampled with a sliding window to preserve both the spatial and temporal information of original data. And then, site-shared features of these samples are extracted through an adversarial learning model. Finally, the model is fine-tuned to learn discriminative disease-related features. Experimental results show that through adversarial learning, the heterogeneity problem among multi-site data is solved. Furthermore, the spatial–temporal information on rs-fMRI is effectively extracted and yields better classification performance (0.80 accuracy, 0.81 sensitivity, 0.80 specificity) than the state-of-the-art methods. Our results demonstrate the feasibility of the proposed method in the ASD classification task and the importance of fully exploiting the site-shared and spatial–temporal information in rs-fMRI data for multi-site ASD study.
KW - Adversarial learning
KW - Multi-site ASD classification
KW - rs-fMRI analysis
KW - Sliding window
UR - http://www.scopus.com/inward/record.url?scp=85151422268&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85151422268&partnerID=8YFLogxK
U2 - 10.1016/j.bspc.2023.104892
DO - 10.1016/j.bspc.2023.104892
M3 - Article
AN - SCOPUS:85151422268
SN - 1746-8094
VL - 85
JO - Biomedical Signal Processing and Control
JF - Biomedical Signal Processing and Control
M1 - 104892
ER -