Multimodal Autism Spectrum Disorder Method Using GCN With Dual Transformers
Autism spectrum disorder (ASD) presents diagnostic challenges due to its heterogeneous nature, necessitating advanced methods for accurate identification. This study proposes a novel diagnostic approach that integrates Graph convolutional networks (GCN) with dual transformer architectures, optimized...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10848112/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583253246083072 |
|---|---|
| author | Tianming Song Zhe Ren Jian Zhang Yawei Qu Yingying Cui Zhengda Liang |
| author_facet | Tianming Song Zhe Ren Jian Zhang Yawei Qu Yingying Cui Zhengda Liang |
| author_sort | Tianming Song |
| collection | DOAJ |
| description | Autism spectrum disorder (ASD) presents diagnostic challenges due to its heterogeneous nature, necessitating advanced methods for accurate identification. This study proposes a novel diagnostic approach that integrates Graph convolutional networks (GCN) with dual transformer architectures, optimized through a Co-training strategy. The first Transformer is dedicated to extracting intricate temporal features from fMRI data, which are crucial for understanding brain activity over time. The second Transformer is employed to enhance the fusion of these temporal features with spatial features learned by the GCN, effectively combining both dimensions of the neuroimaging data. Co-training is introduced to simultaneously harness both functional magnetic resonance imaging and structural magnetic resonance imaging data, improving the model’s capacity to generalize across different datasets. This comprehensive method was rigorously evaluated using the ABIDE-I and ABIDE-II datasets, with performance assessed through nested ten-fold cross-validation and leave-one-out cross-validation. The experimental results reveal that our approach significantly outperforms existing baseline and state-of-the-art models. The method achieves 79.47% of accuracy, 78.97% precision, 82.11% recall, and 0.85 of AUC metrics. These findings highlight the robustness of combining dual transformer models with GCNs and Co-training, providing a powerful framework for ASD classification. |
| format | Article |
| id | doaj-art-bb1e58d293b648789c792aee89683747 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-bb1e58d293b648789c792aee896837472025-01-29T00:01:14ZengIEEEIEEE Access2169-35362025-01-0113163241633710.1109/ACCESS.2025.353230210848112Multimodal Autism Spectrum Disorder Method Using GCN With Dual TransformersTianming Song0Zhe Ren1Jian Zhang2Yawei Qu3Yingying Cui4Zhengda Liang5https://orcid.org/0009-0005-7937-0286School of Integrated Circuit, Wuxi Vocational College of Science and Technology, Wuxi, ChinaSchool of Integrated Circuit, Wuxi Vocational College of Science and Technology, Wuxi, ChinaSchool of Integrated Circuit, Wuxi Vocational College of Science and Technology, Wuxi, ChinaDepartment of Control Science and Engineering, Harbin Institute of Technology, Harbin, Heilongjiang, ChinaGastroenterology Department, Beijing Mentougou District Hospital, Beijing, ChinaSchool of Clinical Medicine, Qilu Medical University, Zibo, Shandong, ChinaAutism spectrum disorder (ASD) presents diagnostic challenges due to its heterogeneous nature, necessitating advanced methods for accurate identification. This study proposes a novel diagnostic approach that integrates Graph convolutional networks (GCN) with dual transformer architectures, optimized through a Co-training strategy. The first Transformer is dedicated to extracting intricate temporal features from fMRI data, which are crucial for understanding brain activity over time. The second Transformer is employed to enhance the fusion of these temporal features with spatial features learned by the GCN, effectively combining both dimensions of the neuroimaging data. Co-training is introduced to simultaneously harness both functional magnetic resonance imaging and structural magnetic resonance imaging data, improving the model’s capacity to generalize across different datasets. This comprehensive method was rigorously evaluated using the ABIDE-I and ABIDE-II datasets, with performance assessed through nested ten-fold cross-validation and leave-one-out cross-validation. The experimental results reveal that our approach significantly outperforms existing baseline and state-of-the-art models. The method achieves 79.47% of accuracy, 78.97% precision, 82.11% recall, and 0.85 of AUC metrics. These findings highlight the robustness of combining dual transformer models with GCNs and Co-training, providing a powerful framework for ASD classification.https://ieeexplore.ieee.org/document/10848112/Autism spectrum disordergraph convolutional networkmultimodalmedical artificial intelligencetransformer |
| spellingShingle | Tianming Song Zhe Ren Jian Zhang Yawei Qu Yingying Cui Zhengda Liang Multimodal Autism Spectrum Disorder Method Using GCN With Dual Transformers IEEE Access Autism spectrum disorder graph convolutional network multimodal medical artificial intelligence transformer |
| title | Multimodal Autism Spectrum Disorder Method Using GCN With Dual Transformers |
| title_full | Multimodal Autism Spectrum Disorder Method Using GCN With Dual Transformers |
| title_fullStr | Multimodal Autism Spectrum Disorder Method Using GCN With Dual Transformers |
| title_full_unstemmed | Multimodal Autism Spectrum Disorder Method Using GCN With Dual Transformers |
| title_short | Multimodal Autism Spectrum Disorder Method Using GCN With Dual Transformers |
| title_sort | multimodal autism spectrum disorder method using gcn with dual transformers |
| topic | Autism spectrum disorder graph convolutional network multimodal medical artificial intelligence transformer |
| url | https://ieeexplore.ieee.org/document/10848112/ |
| work_keys_str_mv | AT tianmingsong multimodalautismspectrumdisordermethodusinggcnwithdualtransformers AT zheren multimodalautismspectrumdisordermethodusinggcnwithdualtransformers AT jianzhang multimodalautismspectrumdisordermethodusinggcnwithdualtransformers AT yaweiqu multimodalautismspectrumdisordermethodusinggcnwithdualtransformers AT yingyingcui multimodalautismspectrumdisordermethodusinggcnwithdualtransformers AT zhengdaliang multimodalautismspectrumdisordermethodusinggcnwithdualtransformers |