Constructing brain functional network by Adversarial Temporal-Spatial Aligned Transformer for early AD analysis
IntroductionThe brain functional network can describe the spontaneous activity of nerve cells and reveal the subtle abnormal changes associated with brain disease. It has been widely used for analyzing early Alzheimer's disease (AD) and exploring pathological mechanisms. However, the current me...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-11-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2022.1087176/full |
| _version_ | 1797986584995299328 |
|---|---|
| author | Qiankun Zuo Qiankun Zuo Libin Lu Lin Wang Lin Wang Jiahui Zuo Tao Ouyang |
| author_facet | Qiankun Zuo Qiankun Zuo Libin Lu Lin Wang Lin Wang Jiahui Zuo Tao Ouyang |
| author_sort | Qiankun Zuo |
| collection | DOAJ |
| description | IntroductionThe brain functional network can describe the spontaneous activity of nerve cells and reveal the subtle abnormal changes associated with brain disease. It has been widely used for analyzing early Alzheimer's disease (AD) and exploring pathological mechanisms. However, the current methods of constructing functional connectivity networks from functional magnetic resonance imaging (fMRI) heavily depend on the software toolboxes, which may lead to errors in connection strength estimation and bad performance in disease analysis because of many subjective settings.MethodsTo solve this problem, in this paper, a novel Adversarial Temporal-Spatial Aligned Transformer (ATAT) model is proposed to automatically map 4D fMRI into functional connectivity network for early AD analysis. By incorporating the volume and location of anatomical brain regions, the region-guided feature learning network can roughly focus on local features for each brain region. Also, the spatial-temporal aligned transformer network is developed to adaptively adjust boundary features of adjacent regions and capture global functional connectivity patterns of distant regions. Furthermore, a multi-channel temporal discriminator is devised to distinguish the joint distributions of the multi-region time series from the generator and the real sample.ResultsExperimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) proved the effectiveness and superior performance of the proposed model in early AD prediction and progression analysis.DiscussionTo verify the reliability of the proposed model, the detected important ROIs are compared with clinical studies and show partial consistency. Furthermore, the most significant altered connectivity reflects the main characteristics associated with AD.ConclusionGenerally, the proposed ATAT provides a new perspective in constructing functional connectivity networks and is able to evaluate the disease-related changing characteristics at different stages for neuroscience exploration and clinical disease analysis. |
| first_indexed | 2024-04-11T07:35:53Z |
| format | Article |
| id | doaj.art-0490ba91cb5341e186aee944f2b31198 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-04-11T07:35:53Z |
| publishDate | 2022-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-0490ba91cb5341e186aee944f2b311982022-12-22T04:36:44ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-11-011610.3389/fnins.2022.10871761087176Constructing brain functional network by Adversarial Temporal-Spatial Aligned Transformer for early AD analysisQiankun Zuo0Qiankun Zuo1Libin Lu2Lin Wang3Lin Wang4Jiahui Zuo5Tao Ouyang6School of Information Engineering, Hubei University of Economics, Wuhan, ChinaCAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, and the SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, ChinaSchool of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, ChinaCAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, and the SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, ChinaGuangdong-Hong Kong-Macau Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, ChinaState Key Laboratory of Petroleum Resource and Prospecting, and Unconventional Petroleum Research Institute, China University of Petroleum, Beijing, ChinaState Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan, ChinaIntroductionThe brain functional network can describe the spontaneous activity of nerve cells and reveal the subtle abnormal changes associated with brain disease. It has been widely used for analyzing early Alzheimer's disease (AD) and exploring pathological mechanisms. However, the current methods of constructing functional connectivity networks from functional magnetic resonance imaging (fMRI) heavily depend on the software toolboxes, which may lead to errors in connection strength estimation and bad performance in disease analysis because of many subjective settings.MethodsTo solve this problem, in this paper, a novel Adversarial Temporal-Spatial Aligned Transformer (ATAT) model is proposed to automatically map 4D fMRI into functional connectivity network for early AD analysis. By incorporating the volume and location of anatomical brain regions, the region-guided feature learning network can roughly focus on local features for each brain region. Also, the spatial-temporal aligned transformer network is developed to adaptively adjust boundary features of adjacent regions and capture global functional connectivity patterns of distant regions. Furthermore, a multi-channel temporal discriminator is devised to distinguish the joint distributions of the multi-region time series from the generator and the real sample.ResultsExperimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) proved the effectiveness and superior performance of the proposed model in early AD prediction and progression analysis.DiscussionTo verify the reliability of the proposed model, the detected important ROIs are compared with clinical studies and show partial consistency. Furthermore, the most significant altered connectivity reflects the main characteristics associated with AD.ConclusionGenerally, the proposed ATAT provides a new perspective in constructing functional connectivity networks and is able to evaluate the disease-related changing characteristics at different stages for neuroscience exploration and clinical disease analysis.https://www.frontiersin.org/articles/10.3389/fnins.2022.1087176/fullfunctional brain connectivitytemporal-spatial transformer alignmentgenerative adversarial learninggraph convolutional networkearly Alzheimer's disease |
| spellingShingle | Qiankun Zuo Qiankun Zuo Libin Lu Lin Wang Lin Wang Jiahui Zuo Tao Ouyang Constructing brain functional network by Adversarial Temporal-Spatial Aligned Transformer for early AD analysis Frontiers in Neuroscience functional brain connectivity temporal-spatial transformer alignment generative adversarial learning graph convolutional network early Alzheimer's disease |
| title | Constructing brain functional network by Adversarial Temporal-Spatial Aligned Transformer for early AD analysis |
| title_full | Constructing brain functional network by Adversarial Temporal-Spatial Aligned Transformer for early AD analysis |
| title_fullStr | Constructing brain functional network by Adversarial Temporal-Spatial Aligned Transformer for early AD analysis |
| title_full_unstemmed | Constructing brain functional network by Adversarial Temporal-Spatial Aligned Transformer for early AD analysis |
| title_short | Constructing brain functional network by Adversarial Temporal-Spatial Aligned Transformer for early AD analysis |
| title_sort | constructing brain functional network by adversarial temporal spatial aligned transformer for early ad analysis |
| topic | functional brain connectivity temporal-spatial transformer alignment generative adversarial learning graph convolutional network early Alzheimer's disease |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2022.1087176/full |
| work_keys_str_mv | AT qiankunzuo constructingbrainfunctionalnetworkbyadversarialtemporalspatialalignedtransformerforearlyadanalysis AT qiankunzuo constructingbrainfunctionalnetworkbyadversarialtemporalspatialalignedtransformerforearlyadanalysis AT libinlu constructingbrainfunctionalnetworkbyadversarialtemporalspatialalignedtransformerforearlyadanalysis AT linwang constructingbrainfunctionalnetworkbyadversarialtemporalspatialalignedtransformerforearlyadanalysis AT linwang constructingbrainfunctionalnetworkbyadversarialtemporalspatialalignedtransformerforearlyadanalysis AT jiahuizuo constructingbrainfunctionalnetworkbyadversarialtemporalspatialalignedtransformerforearlyadanalysis AT taoouyang constructingbrainfunctionalnetworkbyadversarialtemporalspatialalignedtransformerforearlyadanalysis |