Principal Subspace of Dynamic Functional Connectivity for Diagnosis of Autism Spectrum Disorder
The study of functional connectivity (FC) of the brain using resting-state functional magnetic resonance imaging (rs-fMRI) has gained traction for uncovering FC patterns related to autism spectrum disorder (ASD). It is believed that the neurodynamic components of neuroimaging data enhance the measur...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/18/9339 |
| _version_ | 1827663651408969728 |
|---|---|
| author | Mohammed Isam Al-Hiyali Norashikin Yahya Ibrahima Faye Maged S. Al-Quraishi Abdulhakim Al-Ezzi |
| author_facet | Mohammed Isam Al-Hiyali Norashikin Yahya Ibrahima Faye Maged S. Al-Quraishi Abdulhakim Al-Ezzi |
| author_sort | Mohammed Isam Al-Hiyali |
| collection | DOAJ |
| description | The study of functional connectivity (FC) of the brain using resting-state functional magnetic resonance imaging (rs-fMRI) has gained traction for uncovering FC patterns related to autism spectrum disorder (ASD). It is believed that the neurodynamic components of neuroimaging data enhance the measurement of the FC of brain nodes. Hence, methods based on linear correlations of rs-fMRI may not accurately represent the FC patterns of brain nodes in ASD patients. In this study, we proposed a new biomarker for ASD detection based on wavelet coherence and singular value decomposition. In essence, the proposed method provides a novel feature-vector based on extraction of the principal component of the neuronal dynamic FC patterns of rs-fMRI BOLD signals. The method, known as principal wavelet coherence (PWC), is implemented by applying singular value decomposition (SVD) on wavelet coherence (WC) and extracting the first principal component. ASD biomarkers are selected by analyzing the relationship between ASD severity scores and the amplitude of wavelet coherence fluctuation (WCF). The experimental rs-fMRI dataset is obtained from the publicly available Autism Brain Image Data Exchange (ABIDE), and includes 505 ASD patients and 530 normal control subjects. The data are randomly divided into 90% for training and cross-validation and the remaining 10% unseen data used for testing the performance of the trained network. With 95.2% accuracy on the ABIDE database, our ASD classification technique has better performance than previous methods. The results of this study illustrate the potential of PWC in representing FC dynamics between brain nodes and opens up possibilities for its clinical application in diagnosis of other neuropsychiatric disorders. |
| first_indexed | 2024-03-10T00:47:43Z |
| format | Article |
| id | doaj.art-191fc2df4eae4b82bba4e8c3821c2ee0 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T00:47:43Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-191fc2df4eae4b82bba4e8c3821c2ee02023-11-23T14:56:59ZengMDPI AGApplied Sciences2076-34172022-09-011218933910.3390/app12189339Principal Subspace of Dynamic Functional Connectivity for Diagnosis of Autism Spectrum DisorderMohammed Isam Al-Hiyali0Norashikin Yahya1Ibrahima Faye2Maged S. Al-Quraishi3Abdulhakim Al-Ezzi4Centre for Intelligent Signal and Imaging Research (CISIR), Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak, MalaysiaCentre for Intelligent Signal and Imaging Research (CISIR), Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak, MalaysiaCentre for Intelligent Signal and Imaging Research (CISIR), Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak, MalaysiaCentre for Intelligent Signal and Imaging Research (CISIR), Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak, MalaysiaNeurosciences, Huntington Medical Research Institutes, Pasadena, CA 91105, USAThe study of functional connectivity (FC) of the brain using resting-state functional magnetic resonance imaging (rs-fMRI) has gained traction for uncovering FC patterns related to autism spectrum disorder (ASD). It is believed that the neurodynamic components of neuroimaging data enhance the measurement of the FC of brain nodes. Hence, methods based on linear correlations of rs-fMRI may not accurately represent the FC patterns of brain nodes in ASD patients. In this study, we proposed a new biomarker for ASD detection based on wavelet coherence and singular value decomposition. In essence, the proposed method provides a novel feature-vector based on extraction of the principal component of the neuronal dynamic FC patterns of rs-fMRI BOLD signals. The method, known as principal wavelet coherence (PWC), is implemented by applying singular value decomposition (SVD) on wavelet coherence (WC) and extracting the first principal component. ASD biomarkers are selected by analyzing the relationship between ASD severity scores and the amplitude of wavelet coherence fluctuation (WCF). The experimental rs-fMRI dataset is obtained from the publicly available Autism Brain Image Data Exchange (ABIDE), and includes 505 ASD patients and 530 normal control subjects. The data are randomly divided into 90% for training and cross-validation and the remaining 10% unseen data used for testing the performance of the trained network. With 95.2% accuracy on the ABIDE database, our ASD classification technique has better performance than previous methods. The results of this study illustrate the potential of PWC in representing FC dynamics between brain nodes and opens up possibilities for its clinical application in diagnosis of other neuropsychiatric disorders.https://www.mdpi.com/2076-3417/12/18/9339autism spectrum disorderresting state fMRIBOLD signaldynamic functional connectivitySVDprincipal component |
| spellingShingle | Mohammed Isam Al-Hiyali Norashikin Yahya Ibrahima Faye Maged S. Al-Quraishi Abdulhakim Al-Ezzi Principal Subspace of Dynamic Functional Connectivity for Diagnosis of Autism Spectrum Disorder Applied Sciences autism spectrum disorder resting state fMRI BOLD signal dynamic functional connectivity SVD principal component |
| title | Principal Subspace of Dynamic Functional Connectivity for Diagnosis of Autism Spectrum Disorder |
| title_full | Principal Subspace of Dynamic Functional Connectivity for Diagnosis of Autism Spectrum Disorder |
| title_fullStr | Principal Subspace of Dynamic Functional Connectivity for Diagnosis of Autism Spectrum Disorder |
| title_full_unstemmed | Principal Subspace of Dynamic Functional Connectivity for Diagnosis of Autism Spectrum Disorder |
| title_short | Principal Subspace of Dynamic Functional Connectivity for Diagnosis of Autism Spectrum Disorder |
| title_sort | principal subspace of dynamic functional connectivity for diagnosis of autism spectrum disorder |
| topic | autism spectrum disorder resting state fMRI BOLD signal dynamic functional connectivity SVD principal component |
| url | https://www.mdpi.com/2076-3417/12/18/9339 |
| work_keys_str_mv | AT mohammedisamalhiyali principalsubspaceofdynamicfunctionalconnectivityfordiagnosisofautismspectrumdisorder AT norashikinyahya principalsubspaceofdynamicfunctionalconnectivityfordiagnosisofautismspectrumdisorder AT ibrahimafaye principalsubspaceofdynamicfunctionalconnectivityfordiagnosisofautismspectrumdisorder AT magedsalquraishi principalsubspaceofdynamicfunctionalconnectivityfordiagnosisofautismspectrumdisorder AT abdulhakimalezzi principalsubspaceofdynamicfunctionalconnectivityfordiagnosisofautismspectrumdisorder |