Deep Causality Variational Autoencoder Network for Identifying the Potential Biomarkers of Brain Disorders
Identifying causality from observational time-series data is a key problem in dealing with complex dynamic systems. Inferring the direction of connection between brain regions (i.e., causality) has become the central topic in the domain of fMRI. The purpose of this study is to obtain causal graphs t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10366289/ |
| _version_ | 1827381178731069440 |
|---|---|
| author | Amani Alfakih Zhengwang Xia Bahzar Ali Saqib Mamoon Jianfeng Lu |
| author_facet | Amani Alfakih Zhengwang Xia Bahzar Ali Saqib Mamoon Jianfeng Lu |
| author_sort | Amani Alfakih |
| collection | DOAJ |
| description | Identifying causality from observational time-series data is a key problem in dealing with complex dynamic systems. Inferring the direction of connection between brain regions (i.e., causality) has become the central topic in the domain of fMRI. The purpose of this study is to obtain causal graphs that characterize the causal relationship between brain regions based on time series data. To address this issue, we designed a novel model named deep causal variational autoencoder (CVAE) to estimate the causal relationship between brain regions. This network contains a causal layer that can estimate the causal relationship between different brain regions directly. Compared with previous approaches, our method relaxes many constraints on the structure of underlying causal graph. Our proposed method achieves excellent performance on both the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Autism Brain Imaging Data Exchange 1 (ABIDE1) databases. Moreover, the experimental results show that deep CVAE has promising applications in the field of brain disease identification. |
| first_indexed | 2024-03-08T13:52:28Z |
| format | Article |
| id | doaj.art-9e76daecdb354316a425ffb90f4044a9 |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-08T13:52:28Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-9e76daecdb354316a425ffb90f4044a92024-01-16T00:00:40ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102024-01-013211212110.1109/TNSRE.2023.334499510366289Deep Causality Variational Autoencoder Network for Identifying the Potential Biomarkers of Brain DisordersAmani Alfakih0https://orcid.org/0009-0005-0168-0567Zhengwang Xia1https://orcid.org/0000-0002-6815-5856Bahzar Ali2https://orcid.org/0009-0006-4311-1212Saqib Mamoon3https://orcid.org/0000-0002-8392-5118Jianfeng Lu4https://orcid.org/0000-0002-9190-507XSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, ChinaIdentifying causality from observational time-series data is a key problem in dealing with complex dynamic systems. Inferring the direction of connection between brain regions (i.e., causality) has become the central topic in the domain of fMRI. The purpose of this study is to obtain causal graphs that characterize the causal relationship between brain regions based on time series data. To address this issue, we designed a novel model named deep causal variational autoencoder (CVAE) to estimate the causal relationship between brain regions. This network contains a causal layer that can estimate the causal relationship between different brain regions directly. Compared with previous approaches, our method relaxes many constraints on the structure of underlying causal graph. Our proposed method achieves excellent performance on both the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Autism Brain Imaging Data Exchange 1 (ABIDE1) databases. Moreover, the experimental results show that deep CVAE has promising applications in the field of brain disease identification.https://ieeexplore.ieee.org/document/10366289/Causal inferencefMRIautoencoderAlzheimer’s disease (AD)autism spectrum disorder (ASD) |
| spellingShingle | Amani Alfakih Zhengwang Xia Bahzar Ali Saqib Mamoon Jianfeng Lu Deep Causality Variational Autoencoder Network for Identifying the Potential Biomarkers of Brain Disorders IEEE Transactions on Neural Systems and Rehabilitation Engineering Causal inference fMRI autoencoder Alzheimer’s disease (AD) autism spectrum disorder (ASD) |
| title | Deep Causality Variational Autoencoder Network for Identifying the Potential Biomarkers of Brain Disorders |
| title_full | Deep Causality Variational Autoencoder Network for Identifying the Potential Biomarkers of Brain Disorders |
| title_fullStr | Deep Causality Variational Autoencoder Network for Identifying the Potential Biomarkers of Brain Disorders |
| title_full_unstemmed | Deep Causality Variational Autoencoder Network for Identifying the Potential Biomarkers of Brain Disorders |
| title_short | Deep Causality Variational Autoencoder Network for Identifying the Potential Biomarkers of Brain Disorders |
| title_sort | deep causality variational autoencoder network for identifying the potential biomarkers of brain disorders |
| topic | Causal inference fMRI autoencoder Alzheimer’s disease (AD) autism spectrum disorder (ASD) |
| url | https://ieeexplore.ieee.org/document/10366289/ |
| work_keys_str_mv | AT amanialfakih deepcausalityvariationalautoencodernetworkforidentifyingthepotentialbiomarkersofbraindisorders AT zhengwangxia deepcausalityvariationalautoencodernetworkforidentifyingthepotentialbiomarkersofbraindisorders AT bahzarali deepcausalityvariationalautoencodernetworkforidentifyingthepotentialbiomarkersofbraindisorders AT saqibmamoon deepcausalityvariationalautoencodernetworkforidentifyingthepotentialbiomarkersofbraindisorders AT jianfenglu deepcausalityvariationalautoencodernetworkforidentifyingthepotentialbiomarkersofbraindisorders |