Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network
The accurate diagnosis of autism spectrum disorder (ASD) is of great practical significance in clinical practice. The spontaneous hemodynamic fluctuations were collected by functional near-infrared spectroscopy (fNIRS) from the bilateral frontal and temporal cortices of typically developing (TD) chi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-03-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2023.1132231/full |
| _version_ | 1827993967845703680 |
|---|---|
| author | Haoran Zhang Lingyu Xu Lingyu Xu Jie Yu Jun Li Jun Li Jinhong Wang |
| author_facet | Haoran Zhang Lingyu Xu Lingyu Xu Jie Yu Jun Li Jun Li Jinhong Wang |
| author_sort | Haoran Zhang |
| collection | DOAJ |
| description | The accurate diagnosis of autism spectrum disorder (ASD) is of great practical significance in clinical practice. The spontaneous hemodynamic fluctuations were collected by functional near-infrared spectroscopy (fNIRS) from the bilateral frontal and temporal cortices of typically developing (TD) children and children with ASD. Since traditional machine learning and deep learning methods cannot make full use of the potential spatial dependence between variable pairs, and require a long time series to diagnose ASD. Therefore, we use adaptive spatiotemporal graph convolution network (ASGCN) and short time series to classify ASD and TD. To capture spatial and temporal features of fNIRS multivariable time series without the pre-defined graph, we combined the improved adaptive graph convolution network (GCN) and gated recurrent units (GRU). We conducted a series of experiments on the fNIRS dataset, and found that only using 2.1 s short time series could achieve high precision classification, with an accuracy of 95.4%. This suggests that our approach may have the potential to detect pathological signals in autism patients within 2.1 s. In different brain regions, the left frontal lobe has the best classification effect, and the abnormalities occur more frequently in left hemisphere and frontal lobe region. Moreover, we also found that there were correlations between multiple channels, which had different degrees of influence on the classification of ASD. From this, we can also generalize to a wider range, there may be potential correlations between different brain regions. This may help to better understand the cortical mechanism of ASD. |
| first_indexed | 2024-04-10T04:33:34Z |
| format | Article |
| id | doaj.art-12156f60b28a4f1486a3aee890c0ae1a |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-04-10T04:33:34Z |
| publishDate | 2023-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-12156f60b28a4f1486a3aee890c0ae1a2023-03-10T04:40:45ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2023-03-011710.3389/fnins.2023.11322311132231Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution networkHaoran Zhang0Lingyu Xu1Lingyu Xu2Jie Yu3Jun Li4Jun Li5Jinhong Wang6School of Computer Engineering and Science, Shanghai University, Shanghai, ChinaSchool of Computer Engineering and Science, Shanghai University, Shanghai, ChinaShanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, ChinaSchool of Computer Engineering and Science, Shanghai University, Shanghai, ChinaSouth China Academy of Advanced Optoelectronics, South China Normal University, Guangzhou, ChinaKey Lab for Behavioral Economic Science & Technology, South China Normal University, Guangzhou, ChinaDepartment of Medical Imaging Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaThe accurate diagnosis of autism spectrum disorder (ASD) is of great practical significance in clinical practice. The spontaneous hemodynamic fluctuations were collected by functional near-infrared spectroscopy (fNIRS) from the bilateral frontal and temporal cortices of typically developing (TD) children and children with ASD. Since traditional machine learning and deep learning methods cannot make full use of the potential spatial dependence between variable pairs, and require a long time series to diagnose ASD. Therefore, we use adaptive spatiotemporal graph convolution network (ASGCN) and short time series to classify ASD and TD. To capture spatial and temporal features of fNIRS multivariable time series without the pre-defined graph, we combined the improved adaptive graph convolution network (GCN) and gated recurrent units (GRU). We conducted a series of experiments on the fNIRS dataset, and found that only using 2.1 s short time series could achieve high precision classification, with an accuracy of 95.4%. This suggests that our approach may have the potential to detect pathological signals in autism patients within 2.1 s. In different brain regions, the left frontal lobe has the best classification effect, and the abnormalities occur more frequently in left hemisphere and frontal lobe region. Moreover, we also found that there were correlations between multiple channels, which had different degrees of influence on the classification of ASD. From this, we can also generalize to a wider range, there may be potential correlations between different brain regions. This may help to better understand the cortical mechanism of ASD.https://www.frontiersin.org/articles/10.3389/fnins.2023.1132231/fullautism spectrum disorderfunctional near-infrared spectroscopymultivariable time seriesgraph convolution networkadaptive spatiotemporal graph convolution network |
| spellingShingle | Haoran Zhang Lingyu Xu Lingyu Xu Jie Yu Jun Li Jun Li Jinhong Wang Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network Frontiers in Neuroscience autism spectrum disorder functional near-infrared spectroscopy multivariable time series graph convolution network adaptive spatiotemporal graph convolution network |
| title | Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network |
| title_full | Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network |
| title_fullStr | Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network |
| title_full_unstemmed | Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network |
| title_short | Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network |
| title_sort | identification of autism spectrum disorder based on functional near infrared spectroscopy using adaptive spatiotemporal graph convolution network |
| topic | autism spectrum disorder functional near-infrared spectroscopy multivariable time series graph convolution network adaptive spatiotemporal graph convolution network |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2023.1132231/full |
| work_keys_str_mv | AT haoranzhang identificationofautismspectrumdisorderbasedonfunctionalnearinfraredspectroscopyusingadaptivespatiotemporalgraphconvolutionnetwork AT lingyuxu identificationofautismspectrumdisorderbasedonfunctionalnearinfraredspectroscopyusingadaptivespatiotemporalgraphconvolutionnetwork AT lingyuxu identificationofautismspectrumdisorderbasedonfunctionalnearinfraredspectroscopyusingadaptivespatiotemporalgraphconvolutionnetwork AT jieyu identificationofautismspectrumdisorderbasedonfunctionalnearinfraredspectroscopyusingadaptivespatiotemporalgraphconvolutionnetwork AT junli identificationofautismspectrumdisorderbasedonfunctionalnearinfraredspectroscopyusingadaptivespatiotemporalgraphconvolutionnetwork AT junli identificationofautismspectrumdisorderbasedonfunctionalnearinfraredspectroscopyusingadaptivespatiotemporalgraphconvolutionnetwork AT jinhongwang identificationofautismspectrumdisorderbasedonfunctionalnearinfraredspectroscopyusingadaptivespatiotemporalgraphconvolutionnetwork |