Diagnosis of Autism Spectrum Disorder (ASD) by Dynamic Functional Connectivity Using GNN-LSTM
Early detection of autism spectrum disorder (ASD) is particularly important given its insidious qualities and the high cost of the diagnostic process. Currently, static functional connectivity studies have achieved significant results in the field of ASD detection. However, with the deepening of cli...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/1/156 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548958979063808 |
|---|---|
| author | Jun Tang Jie Chen Miaojun Hu Yao Hu Zixi Zhang Liuming Xiao |
| author_facet | Jun Tang Jie Chen Miaojun Hu Yao Hu Zixi Zhang Liuming Xiao |
| author_sort | Jun Tang |
| collection | DOAJ |
| description | Early detection of autism spectrum disorder (ASD) is particularly important given its insidious qualities and the high cost of the diagnostic process. Currently, static functional connectivity studies have achieved significant results in the field of ASD detection. However, with the deepening of clinical research, more and more evidence suggests that dynamic functional connectivity analysis can more comprehensively reveal the complex and variable characteristics of brain networks and their underlying mechanisms, thus providing more solid scientific support for computer-aided diagnosis of ASD. To overcome the lack of time-scale information in static functional connectivity analysis, in this paper, we proposes an innovative GNN-LSTM model, which combines the advantages of long short-term memory (LSTM) and graph neural networks (GNNs). The model captures the spatial features in fMRI data by GNN and aggregates the temporal information of dynamic functional connectivity using LSTM to generate a more comprehensive spatio-temporal feature representation of fMRI data. Further, a dynamic graph pooling method is proposed to extract the final node representations from the dynamic graph representations for classification tasks. To address the variable dependence of dynamic feature connectivity on time scales, the model introduces a jump connection mechanism to enhance information extraction between internal units and capture features at different time scales. The model achieves remarkable results on the ABIDE dataset, with accuracies of 80.4% on the ABIDE I and 79.63% on the ABIDE II, which strongly demonstrates the effectiveness and potential of the model for ASD detection. This study not only provides new perspectives and methods for computer-aided diagnosis of ASD but also provides useful references for research in related fields. |
| format | Article |
| id | doaj-art-f7f2a62fcb804b8bbbff57ce1b5c6c42 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-f7f2a62fcb804b8bbbff57ce1b5c6c422025-01-10T13:21:03ZengMDPI AGSensors1424-82202024-12-0125115610.3390/s25010156Diagnosis of Autism Spectrum Disorder (ASD) by Dynamic Functional Connectivity Using GNN-LSTMJun Tang0Jie Chen1Miaojun Hu2Yao Hu3Zixi Zhang4Liuming Xiao5School of Educational Sciences, Hunan Normal University, Changsha 410081, ChinaSchool of Educational Sciences, Hunan Normal University, Changsha 410081, ChinaCollege of Information Science and Engineering, Hunan Normal University, Changsha 410081, ChinaCollege of Information Science and Engineering, Hunan Normal University, Changsha 410081, ChinaCollege of Information Science and Engineering, Hunan Normal University, Changsha 410081, ChinaCollege of Information Science and Engineering, Hunan Normal University, Changsha 410081, ChinaEarly detection of autism spectrum disorder (ASD) is particularly important given its insidious qualities and the high cost of the diagnostic process. Currently, static functional connectivity studies have achieved significant results in the field of ASD detection. However, with the deepening of clinical research, more and more evidence suggests that dynamic functional connectivity analysis can more comprehensively reveal the complex and variable characteristics of brain networks and their underlying mechanisms, thus providing more solid scientific support for computer-aided diagnosis of ASD. To overcome the lack of time-scale information in static functional connectivity analysis, in this paper, we proposes an innovative GNN-LSTM model, which combines the advantages of long short-term memory (LSTM) and graph neural networks (GNNs). The model captures the spatial features in fMRI data by GNN and aggregates the temporal information of dynamic functional connectivity using LSTM to generate a more comprehensive spatio-temporal feature representation of fMRI data. Further, a dynamic graph pooling method is proposed to extract the final node representations from the dynamic graph representations for classification tasks. To address the variable dependence of dynamic feature connectivity on time scales, the model introduces a jump connection mechanism to enhance information extraction between internal units and capture features at different time scales. The model achieves remarkable results on the ABIDE dataset, with accuracies of 80.4% on the ABIDE I and 79.63% on the ABIDE II, which strongly demonstrates the effectiveness and potential of the model for ASD detection. This study not only provides new perspectives and methods for computer-aided diagnosis of ASD but also provides useful references for research in related fields.https://www.mdpi.com/1424-8220/25/1/156autism spectrum disorder (ASD)dynamic functional connectivitygraph neural networks (GNNs)long short-term memory (LSTM) |
| spellingShingle | Jun Tang Jie Chen Miaojun Hu Yao Hu Zixi Zhang Liuming Xiao Diagnosis of Autism Spectrum Disorder (ASD) by Dynamic Functional Connectivity Using GNN-LSTM Sensors autism spectrum disorder (ASD) dynamic functional connectivity graph neural networks (GNNs) long short-term memory (LSTM) |
| title | Diagnosis of Autism Spectrum Disorder (ASD) by Dynamic Functional Connectivity Using GNN-LSTM |
| title_full | Diagnosis of Autism Spectrum Disorder (ASD) by Dynamic Functional Connectivity Using GNN-LSTM |
| title_fullStr | Diagnosis of Autism Spectrum Disorder (ASD) by Dynamic Functional Connectivity Using GNN-LSTM |
| title_full_unstemmed | Diagnosis of Autism Spectrum Disorder (ASD) by Dynamic Functional Connectivity Using GNN-LSTM |
| title_short | Diagnosis of Autism Spectrum Disorder (ASD) by Dynamic Functional Connectivity Using GNN-LSTM |
| title_sort | diagnosis of autism spectrum disorder asd by dynamic functional connectivity using gnn lstm |
| topic | autism spectrum disorder (ASD) dynamic functional connectivity graph neural networks (GNNs) long short-term memory (LSTM) |
| url | https://www.mdpi.com/1424-8220/25/1/156 |
| work_keys_str_mv | AT juntang diagnosisofautismspectrumdisorderasdbydynamicfunctionalconnectivityusinggnnlstm AT jiechen diagnosisofautismspectrumdisorderasdbydynamicfunctionalconnectivityusinggnnlstm AT miaojunhu diagnosisofautismspectrumdisorderasdbydynamicfunctionalconnectivityusinggnnlstm AT yaohu diagnosisofautismspectrumdisorderasdbydynamicfunctionalconnectivityusinggnnlstm AT zixizhang diagnosisofautismspectrumdisorderasdbydynamicfunctionalconnectivityusinggnnlstm AT liumingxiao diagnosisofautismspectrumdisorderasdbydynamicfunctionalconnectivityusinggnnlstm |