Dynamic functional connectivity analysis with temporal convolutional network for attention deficit/hyperactivity disorder identification
IntroductionDynamic functional connectivity (dFC), which can capture the abnormality of brain activity over time in resting-state functional magnetic resonance imaging (rs-fMRI) data, has a natural advantage in revealing the abnormal mechanism of brain activity in patients with Attention Deficit/Hyp...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-12-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2023.1322967/full |
| _version_ | 1797397122018967552 |
|---|---|
| author | Mingliang Wang Mingliang Wang Mingliang Wang Lingyao Zhu Xizhi Li Yong Pan Long Li |
| author_facet | Mingliang Wang Mingliang Wang Mingliang Wang Lingyao Zhu Xizhi Li Yong Pan Long Li |
| author_sort | Mingliang Wang |
| collection | DOAJ |
| description | IntroductionDynamic functional connectivity (dFC), which can capture the abnormality of brain activity over time in resting-state functional magnetic resonance imaging (rs-fMRI) data, has a natural advantage in revealing the abnormal mechanism of brain activity in patients with Attention Deficit/Hyperactivity Disorder (ADHD). Several deep learning methods have been proposed to learn dynamic changes from rs-fMRI for FC analysis, and achieved superior performance than those using static FC. However, most existing methods only consider dependencies of two adjacent timestamps, which is limited when the change is related to the course of many timestamps.MethodsIn this paper, we propose a novel Temporal Dependence neural Network (TDNet) for FC representation learning and temporal-dependence relationship tracking from rs-fMRI time series for automated ADHD identification. Specifically, we first partition rs-fMRI time series into a sequence of consecutive and non-overlapping segments. For each segment, we design an FC generation module to learn more discriminative representations to construct dynamic FCs. Then, we employ the Temporal Convolutional Network (TCN) to efficiently capture long-range temporal patterns with dilated convolutions, followed by three fully connected layers for disease prediction.ResultsAs the results, we found that considering the dynamic characteristics of rs-fMRI time series data is beneficial to obtain better diagnostic performance. In addition, dynamic FC networks generated in a data-driven manner are more informative than those constructed by Pearson correlation coefficients.DiscussionWe validate the effectiveness of the proposed approach through extensive experiments on the public ADHD-200 database, and the results demonstrate the superiority of the proposed model over state-of-the-art methods in ADHD identification. |
| first_indexed | 2024-03-09T01:05:27Z |
| format | Article |
| id | doaj.art-2312275312cb480dbc26cf79e2d85094 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-03-09T01:05:27Z |
| publishDate | 2023-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-2312275312cb480dbc26cf79e2d850942023-12-11T09:33:33ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2023-12-011710.3389/fnins.2023.13229671322967Dynamic functional connectivity analysis with temporal convolutional network for attention deficit/hyperactivity disorder identificationMingliang Wang0Mingliang Wang1Mingliang Wang2Lingyao Zhu3Xizhi Li4Yong Pan5Long Li6School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, ChinaNanjing Xinda Institute of Safety and Emergency Management, Nanjing, ChinaMIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaSchool of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, ChinaSchool of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, ChinaSchool of Accounting, Nanjing University of Finance and Economics, Nanjing, ChinaTaian Tumor Prevention and Treatment Hospital, Taian, ChinaIntroductionDynamic functional connectivity (dFC), which can capture the abnormality of brain activity over time in resting-state functional magnetic resonance imaging (rs-fMRI) data, has a natural advantage in revealing the abnormal mechanism of brain activity in patients with Attention Deficit/Hyperactivity Disorder (ADHD). Several deep learning methods have been proposed to learn dynamic changes from rs-fMRI for FC analysis, and achieved superior performance than those using static FC. However, most existing methods only consider dependencies of two adjacent timestamps, which is limited when the change is related to the course of many timestamps.MethodsIn this paper, we propose a novel Temporal Dependence neural Network (TDNet) for FC representation learning and temporal-dependence relationship tracking from rs-fMRI time series for automated ADHD identification. Specifically, we first partition rs-fMRI time series into a sequence of consecutive and non-overlapping segments. For each segment, we design an FC generation module to learn more discriminative representations to construct dynamic FCs. Then, we employ the Temporal Convolutional Network (TCN) to efficiently capture long-range temporal patterns with dilated convolutions, followed by three fully connected layers for disease prediction.ResultsAs the results, we found that considering the dynamic characteristics of rs-fMRI time series data is beneficial to obtain better diagnostic performance. In addition, dynamic FC networks generated in a data-driven manner are more informative than those constructed by Pearson correlation coefficients.DiscussionWe validate the effectiveness of the proposed approach through extensive experiments on the public ADHD-200 database, and the results demonstrate the superiority of the proposed model over state-of-the-art methods in ADHD identification.https://www.frontiersin.org/articles/10.3389/fnins.2023.1322967/fullfunctional connectivitytemporal dependencedynamics characteristicsattention deficit/hyperactivity disordertemporal convolutional network |
| spellingShingle | Mingliang Wang Mingliang Wang Mingliang Wang Lingyao Zhu Xizhi Li Yong Pan Long Li Dynamic functional connectivity analysis with temporal convolutional network for attention deficit/hyperactivity disorder identification Frontiers in Neuroscience functional connectivity temporal dependence dynamics characteristics attention deficit/hyperactivity disorder temporal convolutional network |
| title | Dynamic functional connectivity analysis with temporal convolutional network for attention deficit/hyperactivity disorder identification |
| title_full | Dynamic functional connectivity analysis with temporal convolutional network for attention deficit/hyperactivity disorder identification |
| title_fullStr | Dynamic functional connectivity analysis with temporal convolutional network for attention deficit/hyperactivity disorder identification |
| title_full_unstemmed | Dynamic functional connectivity analysis with temporal convolutional network for attention deficit/hyperactivity disorder identification |
| title_short | Dynamic functional connectivity analysis with temporal convolutional network for attention deficit/hyperactivity disorder identification |
| title_sort | dynamic functional connectivity analysis with temporal convolutional network for attention deficit hyperactivity disorder identification |
| topic | functional connectivity temporal dependence dynamics characteristics attention deficit/hyperactivity disorder temporal convolutional network |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2023.1322967/full |
| work_keys_str_mv | AT mingliangwang dynamicfunctionalconnectivityanalysiswithtemporalconvolutionalnetworkforattentiondeficithyperactivitydisorderidentification AT mingliangwang dynamicfunctionalconnectivityanalysiswithtemporalconvolutionalnetworkforattentiondeficithyperactivitydisorderidentification AT mingliangwang dynamicfunctionalconnectivityanalysiswithtemporalconvolutionalnetworkforattentiondeficithyperactivitydisorderidentification AT lingyaozhu dynamicfunctionalconnectivityanalysiswithtemporalconvolutionalnetworkforattentiondeficithyperactivitydisorderidentification AT xizhili dynamicfunctionalconnectivityanalysiswithtemporalconvolutionalnetworkforattentiondeficithyperactivitydisorderidentification AT yongpan dynamicfunctionalconnectivityanalysiswithtemporalconvolutionalnetworkforattentiondeficithyperactivitydisorderidentification AT longli dynamicfunctionalconnectivityanalysiswithtemporalconvolutionalnetworkforattentiondeficithyperactivitydisorderidentification |