Multi-channel spatio-temporal graph attention contrastive network for brain disease diagnosis
Dynamic brain networks (DBNs) can capture the intricate connections and temporal evolution among brain regions, becoming increasingly crucial in the diagnosis of neurological disorders. However, most existing researches tend to focus on isolated brain network sequence segmented by sliding windows, a...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811925000138 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087777635729408 |
|---|---|
| author | Chaojun Li Kai Ma Shengrong Li Xiangshui Meng Ran Wang Daoqiang Zhang Qi Zhu |
| author_facet | Chaojun Li Kai Ma Shengrong Li Xiangshui Meng Ran Wang Daoqiang Zhang Qi Zhu |
| author_sort | Chaojun Li |
| collection | DOAJ |
| description | Dynamic brain networks (DBNs) can capture the intricate connections and temporal evolution among brain regions, becoming increasingly crucial in the diagnosis of neurological disorders. However, most existing researches tend to focus on isolated brain network sequence segmented by sliding windows, and they are difficult to effectively uncover the higher-order spatio-temporal topological pattern in DBNs. Meantime, it remains a challenge to utilize the structure connectivity prior in the DBNs analysis. To address these problems, we propose a multi-channel spatio-temporal graph attention contrastive network for DBNs analysis. Specifically, we first construct dynamic brain functional networks from fMRI data with sliding windows, and embed the structural connectivity derived from diffusion tensor imaging (DTI) to the dynamic functional connectivity graph representation to construct multi-modal brain network. Second, we develop a multi-channel spatial attention contrastive network to extract topological features from the brain network within each time window. This network incorporates an intra-window graph contrastive constraint to enhance the discriminative ability of the extracted features. Moreover, temporal dependencies across windows are captured by integrating feature embeddings through a self-attention mechanism, and the inter-window recurrent contrastive constraint is devised to extract higher-order spatio-temporal topological features. Finally, a multi-layer perceptron (MLP) is used to classify the brain networks. Experiments on epilepsy and ADNI datasets show that our method outperforms several state-of-the-art approaches in diagnosing performance, and it provides discriminative graph features for related brain diseases. |
| format | Article |
| id | doaj-art-9307ffc452e14235948c99461e110e6b |
| institution | Kabale University |
| issn | 1095-9572 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj-art-9307ffc452e14235948c99461e110e6b2025-02-06T05:11:05ZengElsevierNeuroImage1095-95722025-02-01307121013Multi-channel spatio-temporal graph attention contrastive network for brain disease diagnosisChaojun Li0Kai Ma1Shengrong Li2Xiangshui Meng3Ran Wang4Daoqiang Zhang5Qi Zhu6College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China; Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, ChinaSchool of Computer, Jiangsu University of Science and Technology, Zhenjiang, 212100, China; Corresponding authors.College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China; Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, ChinaDepartment of Radiology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Qingdao, 266035, ChinaCollege of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, ChinaCollege of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China; Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, ChinaCollege of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China; Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China; Corresponding authors.Dynamic brain networks (DBNs) can capture the intricate connections and temporal evolution among brain regions, becoming increasingly crucial in the diagnosis of neurological disorders. However, most existing researches tend to focus on isolated brain network sequence segmented by sliding windows, and they are difficult to effectively uncover the higher-order spatio-temporal topological pattern in DBNs. Meantime, it remains a challenge to utilize the structure connectivity prior in the DBNs analysis. To address these problems, we propose a multi-channel spatio-temporal graph attention contrastive network for DBNs analysis. Specifically, we first construct dynamic brain functional networks from fMRI data with sliding windows, and embed the structural connectivity derived from diffusion tensor imaging (DTI) to the dynamic functional connectivity graph representation to construct multi-modal brain network. Second, we develop a multi-channel spatial attention contrastive network to extract topological features from the brain network within each time window. This network incorporates an intra-window graph contrastive constraint to enhance the discriminative ability of the extracted features. Moreover, temporal dependencies across windows are captured by integrating feature embeddings through a self-attention mechanism, and the inter-window recurrent contrastive constraint is devised to extract higher-order spatio-temporal topological features. Finally, a multi-layer perceptron (MLP) is used to classify the brain networks. Experiments on epilepsy and ADNI datasets show that our method outperforms several state-of-the-art approaches in diagnosing performance, and it provides discriminative graph features for related brain diseases.http://www.sciencedirect.com/science/article/pii/S1053811925000138Brain disease diagnosisDynamic brain networksSpatio-temporal featuresGraph contrastive learning |
| spellingShingle | Chaojun Li Kai Ma Shengrong Li Xiangshui Meng Ran Wang Daoqiang Zhang Qi Zhu Multi-channel spatio-temporal graph attention contrastive network for brain disease diagnosis NeuroImage Brain disease diagnosis Dynamic brain networks Spatio-temporal features Graph contrastive learning |
| title | Multi-channel spatio-temporal graph attention contrastive network for brain disease diagnosis |
| title_full | Multi-channel spatio-temporal graph attention contrastive network for brain disease diagnosis |
| title_fullStr | Multi-channel spatio-temporal graph attention contrastive network for brain disease diagnosis |
| title_full_unstemmed | Multi-channel spatio-temporal graph attention contrastive network for brain disease diagnosis |
| title_short | Multi-channel spatio-temporal graph attention contrastive network for brain disease diagnosis |
| title_sort | multi channel spatio temporal graph attention contrastive network for brain disease diagnosis |
| topic | Brain disease diagnosis Dynamic brain networks Spatio-temporal features Graph contrastive learning |
| url | http://www.sciencedirect.com/science/article/pii/S1053811925000138 |
| work_keys_str_mv | AT chaojunli multichannelspatiotemporalgraphattentioncontrastivenetworkforbraindiseasediagnosis AT kaima multichannelspatiotemporalgraphattentioncontrastivenetworkforbraindiseasediagnosis AT shengrongli multichannelspatiotemporalgraphattentioncontrastivenetworkforbraindiseasediagnosis AT xiangshuimeng multichannelspatiotemporalgraphattentioncontrastivenetworkforbraindiseasediagnosis AT ranwang multichannelspatiotemporalgraphattentioncontrastivenetworkforbraindiseasediagnosis AT daoqiangzhang multichannelspatiotemporalgraphattentioncontrastivenetworkforbraindiseasediagnosis AT qizhu multichannelspatiotemporalgraphattentioncontrastivenetworkforbraindiseasediagnosis |