Local structural–functional coupling with counterfactual explanations for epilepsy prediction
The structural–functional brain connections coupling (SC–FC coupling) describes the relationship between white matter structural connections (SC) and the corresponding functional activation or functional connections (FC). It has been widely used to identify brain disorders. However, the existing res...
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/S1053811924004750 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590952848424960 |
|---|---|
| author | Jiashuang Huang Shaolong Wei Zhen Gao Shu Jiang Mingliang Wang Liang Sun Weiping Ding Daoqiang Zhang |
| author_facet | Jiashuang Huang Shaolong Wei Zhen Gao Shu Jiang Mingliang Wang Liang Sun Weiping Ding Daoqiang Zhang |
| author_sort | Jiashuang Huang |
| collection | DOAJ |
| description | The structural–functional brain connections coupling (SC–FC coupling) describes the relationship between white matter structural connections (SC) and the corresponding functional activation or functional connections (FC). It has been widely used to identify brain disorders. However, the existing research on SC–FC coupling focuses on global and regional scales, and few studies have investigated the impact of brain disorders on this relationship from the perspective of multi-brain region cooperation (i.e., local scale). Here, we propose the local SC–FC coupling pattern for brain disorders prediction. Compared with previous methods, the proposed patterns quantify the relationship between SC and FC in terms of subgraphs rather than whole connections or single brain regions. Specifically, we first construct structural and functional connections using diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (rs-fMRI) data, subsequently organizing them into a multimodal brain network. Then, we extract subgraphs from these multimodal brain networks and select them based on their frequencies to generate local SC–FC coupling patterns. Finally, we employ these patterns to identify brain disorders while refining abnormal patterns to generate counterfactual explanations. Results on a real epilepsy dataset suggest that the proposed method not only outperforms existing methods in accuracy but also provides insights into the local SC–FC coupling pattern and their changes in brain disorders. Code available at https://github.com/UAIBC-Brain/Local-SC-FC-coupling-pattern. |
| format | Article |
| id | doaj-art-50d963496e6845e6aee4783a7a56c3b2 |
| institution | Kabale University |
| issn | 1095-9572 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj-art-50d963496e6845e6aee4783a7a56c3b22025-01-23T05:26:19ZengElsevierNeuroImage1095-95722025-02-01306120978Local structural–functional coupling with counterfactual explanations for epilepsy predictionJiashuang Huang0Shaolong Wei1Zhen Gao2Shu Jiang3Mingliang Wang4Liang Sun5Weiping Ding6Daoqiang Zhang7School of Artificial Intelligence and Computer Science, Nantong University, Nantong, 226019, ChinaSchool of Artificial Intelligence and Computer Science, Nantong University, Nantong, 226019, ChinaAffiliated Hospital 2 of Nantong University, Nantong, 226001, ChinaSchool of Artificial Intelligence and Computer Science, Nantong University, Nantong, 226019, ChinaSchool of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, 210044, ChinaCollege of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, China; Shenzhen Research Institute, Nanjing University of Aeronautics and Astronautics, Shenzhen, 518038, China; Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing, 210016, ChinaSchool of Artificial Intelligence and Computer Science, Nantong University, Nantong, 226019, China; Corresponding authors.College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, China; Shenzhen Research Institute, Nanjing University of Aeronautics and Astronautics, Shenzhen, 518038, China; Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing, 210016, China; Corresponding authors.The structural–functional brain connections coupling (SC–FC coupling) describes the relationship between white matter structural connections (SC) and the corresponding functional activation or functional connections (FC). It has been widely used to identify brain disorders. However, the existing research on SC–FC coupling focuses on global and regional scales, and few studies have investigated the impact of brain disorders on this relationship from the perspective of multi-brain region cooperation (i.e., local scale). Here, we propose the local SC–FC coupling pattern for brain disorders prediction. Compared with previous methods, the proposed patterns quantify the relationship between SC and FC in terms of subgraphs rather than whole connections or single brain regions. Specifically, we first construct structural and functional connections using diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (rs-fMRI) data, subsequently organizing them into a multimodal brain network. Then, we extract subgraphs from these multimodal brain networks and select them based on their frequencies to generate local SC–FC coupling patterns. Finally, we employ these patterns to identify brain disorders while refining abnormal patterns to generate counterfactual explanations. Results on a real epilepsy dataset suggest that the proposed method not only outperforms existing methods in accuracy but also provides insights into the local SC–FC coupling pattern and their changes in brain disorders. Code available at https://github.com/UAIBC-Brain/Local-SC-FC-coupling-pattern.http://www.sciencedirect.com/science/article/pii/S1053811924004750SC-FC couplingStructural connectionsFunctional connectionsBrain disordersCounterfactual explanations |
| spellingShingle | Jiashuang Huang Shaolong Wei Zhen Gao Shu Jiang Mingliang Wang Liang Sun Weiping Ding Daoqiang Zhang Local structural–functional coupling with counterfactual explanations for epilepsy prediction NeuroImage SC-FC coupling Structural connections Functional connections Brain disorders Counterfactual explanations |
| title | Local structural–functional coupling with counterfactual explanations for epilepsy prediction |
| title_full | Local structural–functional coupling with counterfactual explanations for epilepsy prediction |
| title_fullStr | Local structural–functional coupling with counterfactual explanations for epilepsy prediction |
| title_full_unstemmed | Local structural–functional coupling with counterfactual explanations for epilepsy prediction |
| title_short | Local structural–functional coupling with counterfactual explanations for epilepsy prediction |
| title_sort | local structural functional coupling with counterfactual explanations for epilepsy prediction |
| topic | SC-FC coupling Structural connections Functional connections Brain disorders Counterfactual explanations |
| url | http://www.sciencedirect.com/science/article/pii/S1053811924004750 |
| work_keys_str_mv | AT jiashuanghuang localstructuralfunctionalcouplingwithcounterfactualexplanationsforepilepsyprediction AT shaolongwei localstructuralfunctionalcouplingwithcounterfactualexplanationsforepilepsyprediction AT zhengao localstructuralfunctionalcouplingwithcounterfactualexplanationsforepilepsyprediction AT shujiang localstructuralfunctionalcouplingwithcounterfactualexplanationsforepilepsyprediction AT mingliangwang localstructuralfunctionalcouplingwithcounterfactualexplanationsforepilepsyprediction AT liangsun localstructuralfunctionalcouplingwithcounterfactualexplanationsforepilepsyprediction AT weipingding localstructuralfunctionalcouplingwithcounterfactualexplanationsforepilepsyprediction AT daoqiangzhang localstructuralfunctionalcouplingwithcounterfactualexplanationsforepilepsyprediction |