Prob-sparse self-attention extraction of time-aligned dynamic functional connectivity for ASD diagnosis
Dynamic functional connectivity (DFC) has shown promise in the diagnosis of Autism Spectrum Disorder (ASD). However, extracting highly discriminative information from the complex DFC matrix remains a challenging task. In this paper, we propose an ASD classification framework PSA-FCN which is based o...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024171514 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526229566488576 |
|---|---|
| author | Hongwu Chen Fan Feng Pengwei Lou Ying Li MingLi Zhang Feng Zhao |
| author_facet | Hongwu Chen Fan Feng Pengwei Lou Ying Li MingLi Zhang Feng Zhao |
| author_sort | Hongwu Chen |
| collection | DOAJ |
| description | Dynamic functional connectivity (DFC) has shown promise in the diagnosis of Autism Spectrum Disorder (ASD). However, extracting highly discriminative information from the complex DFC matrix remains a challenging task. In this paper, we propose an ASD classification framework PSA-FCN which is based on time-aligned DFC and Prob-Sparse Self-Attention to address this problem. Specifically, we introduce Prob-Sparse Self-Attention to selectively extract global features, and use self-attention distillation as a transition at each layer to capture local patterns and reduce dimensionality. Additionally, we construct a time-aligned DFC matrix to mitigate the time sensitivity of DFC and extend the dataset, thereby alleviating model overfitting. Our model is evaluated on fMRI data from the ABIDE NYU site, and the experimental results demonstrate that the model outperforms other methods in the paper with a classification accuracy of 81.8 %. Additionally, our research findings reveal significant variability in the DFC connections of brain regions of ASD patients, including Cuneus (CUN), Lingual gyrus (LING), Superior occipital gyrus (SOG), Posterior cingulate gyrus (PCG), and Precuneus (PCUN), which is consistent with prior research. In summary, our proposed PSA framework shows potential in ASD diagnosis as well as automatic discovery of critical ASD-related biomarkers. |
| format | Article |
| id | doaj-art-d22a46e840e6470c85f8287405db2972 |
| institution | Kabale University |
| issn | 2405-8440 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-d22a46e840e6470c85f8287405db29722025-01-17T04:50:12ZengElsevierHeliyon2405-84402025-01-01111e41120Prob-sparse self-attention extraction of time-aligned dynamic functional connectivity for ASD diagnosisHongwu Chen0Fan Feng1Pengwei Lou2Ying Li3MingLi Zhang4Feng Zhao5School Hospital, Shandong Technology and Business University, Yantai, ChinaSchool of Computer Science and Technology, Shandong Technology and Business University, Yantai, ChinaKey Laboratory of Xinjiang Coal Resources Green Mining, Ministry of Education, Xinjiang, China; College of Information Engineering, Xinjiang Institute of Engineering, Xinjiang, ChinaSchool of Computer Science and Technology, Shandong Technology and Business University, Yantai, ChinaSchool of Computer Science and Technology, Shandong Technology and Business University, Yantai, ChinaSchool of Computer Science and Technology, Shandong Technology and Business University, Yantai, China; Key Laboratory of Xinjiang Coal Resources Green Mining, Ministry of Education, Xinjiang, China; College of Information Engineering, Xinjiang Institute of Engineering, Xinjiang, China; Corresponding author. School of Computer Science and Technology, Shandong Technology and Business University, Yantai, China.Dynamic functional connectivity (DFC) has shown promise in the diagnosis of Autism Spectrum Disorder (ASD). However, extracting highly discriminative information from the complex DFC matrix remains a challenging task. In this paper, we propose an ASD classification framework PSA-FCN which is based on time-aligned DFC and Prob-Sparse Self-Attention to address this problem. Specifically, we introduce Prob-Sparse Self-Attention to selectively extract global features, and use self-attention distillation as a transition at each layer to capture local patterns and reduce dimensionality. Additionally, we construct a time-aligned DFC matrix to mitigate the time sensitivity of DFC and extend the dataset, thereby alleviating model overfitting. Our model is evaluated on fMRI data from the ABIDE NYU site, and the experimental results demonstrate that the model outperforms other methods in the paper with a classification accuracy of 81.8 %. Additionally, our research findings reveal significant variability in the DFC connections of brain regions of ASD patients, including Cuneus (CUN), Lingual gyrus (LING), Superior occipital gyrus (SOG), Posterior cingulate gyrus (PCG), and Precuneus (PCUN), which is consistent with prior research. In summary, our proposed PSA framework shows potential in ASD diagnosis as well as automatic discovery of critical ASD-related biomarkers.http://www.sciencedirect.com/science/article/pii/S2405844024171514Autism spectrum disorderProb-sparse attentionSliding windowTime alignment |
| spellingShingle | Hongwu Chen Fan Feng Pengwei Lou Ying Li MingLi Zhang Feng Zhao Prob-sparse self-attention extraction of time-aligned dynamic functional connectivity for ASD diagnosis Heliyon Autism spectrum disorder Prob-sparse attention Sliding window Time alignment |
| title | Prob-sparse self-attention extraction of time-aligned dynamic functional connectivity for ASD diagnosis |
| title_full | Prob-sparse self-attention extraction of time-aligned dynamic functional connectivity for ASD diagnosis |
| title_fullStr | Prob-sparse self-attention extraction of time-aligned dynamic functional connectivity for ASD diagnosis |
| title_full_unstemmed | Prob-sparse self-attention extraction of time-aligned dynamic functional connectivity for ASD diagnosis |
| title_short | Prob-sparse self-attention extraction of time-aligned dynamic functional connectivity for ASD diagnosis |
| title_sort | prob sparse self attention extraction of time aligned dynamic functional connectivity for asd diagnosis |
| topic | Autism spectrum disorder Prob-sparse attention Sliding window Time alignment |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024171514 |
| work_keys_str_mv | AT hongwuchen probsparseselfattentionextractionoftimealigneddynamicfunctionalconnectivityforasddiagnosis AT fanfeng probsparseselfattentionextractionoftimealigneddynamicfunctionalconnectivityforasddiagnosis AT pengweilou probsparseselfattentionextractionoftimealigneddynamicfunctionalconnectivityforasddiagnosis AT yingli probsparseselfattentionextractionoftimealigneddynamicfunctionalconnectivityforasddiagnosis AT minglizhang probsparseselfattentionextractionoftimealigneddynamicfunctionalconnectivityforasddiagnosis AT fengzhao probsparseselfattentionextractionoftimealigneddynamicfunctionalconnectivityforasddiagnosis |