Transformer-based structural connectivity networks for ADHD-related connectivity alterations
Abstract Background Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder that affects behavior, attention, and learning. Current diagnoses rely heavily on subjective assessments, underscoring the need for objective imaging-based methods. This study aims to explore...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Communications Medicine |
| Online Access: | https://doi.org/10.1038/s43856-025-01015-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849342784176128000 |
|---|---|
| author | Liting Shi Lei Shi Zhijun Cui Chengting Lin Rui Zhang Jiayi Zhang Yechen Zhu Wei Shi Jianlin Wang Yanlong Wang Dongxing Wang Haihong Liu Xin Gao |
| author_facet | Liting Shi Lei Shi Zhijun Cui Chengting Lin Rui Zhang Jiayi Zhang Yechen Zhu Wei Shi Jianlin Wang Yanlong Wang Dongxing Wang Haihong Liu Xin Gao |
| author_sort | Liting Shi |
| collection | DOAJ |
| description | Abstract Background Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder that affects behavior, attention, and learning. Current diagnoses rely heavily on subjective assessments, underscoring the need for objective imaging-based methods. This study aims to explore whether structural connectivity networks derived from MRI can reveal alterations associated with ADHD and support data-driven understanding. Methods We collected brain MRI data from 947 individuals (aged 7–26 years; 590 males, 356 females, 1 unspecified) across eight centers, sourced from the Neuro Bureau ADHD-200 preprocessed dataset. Transformer-based deep learning models were used to learn relationships between different brain regions and construct structural connectivity networks. To prepare input for the model, each region was transformed into a standardized data sequence using four different strategies. The strength of connectivity between brain regions was then measured to identify structural differences related to ADHD. Five-fold cross-validation and statistical analyses were used to evaluate model robustness and group differences, respectively. Results Here we show that the proposed method performs well in distinguishing ADHD individuals from healthy controls, with accuracy reaching 71.9 percent and an area under curve of 0.74. The structural networks also reveal significant differences in connectivity patterns (paired t-test: P = 0.81 × 10−6), particularly involving regions responsible for motor and executive function. Notably, the importance rankings of several brain regions, including the thalamus and caudate, differ markedly between groups. Conclusions This study shows that ADHD may be associated with connectivity alterations in multiple brain regions. Our findings suggest that brain structural connectivity networks built using Transformer-based methods offer a promising tool for both diagnosis and further research into brain structure. |
| format | Article |
| id | doaj-art-cf7a8abfa5e4454ab5172641667aa591 |
| institution | Kabale University |
| issn | 2730-664X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Medicine |
| spelling | doaj-art-cf7a8abfa5e4454ab5172641667aa5912025-08-20T03:43:15ZengNature PortfolioCommunications Medicine2730-664X2025-07-015111110.1038/s43856-025-01015-1Transformer-based structural connectivity networks for ADHD-related connectivity alterationsLiting Shi0Lei Shi1Zhijun Cui2Chengting Lin3Rui Zhang4Jiayi Zhang5Yechen Zhu6Wei Shi7Jianlin Wang8Yanlong Wang9Dongxing Wang10Haihong Liu11Xin Gao12Department of Radiology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesDepartment of Radiology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesBeijing Children’s Hospital, Capital Medical University, National Center for Children’s HealthThe Second School of Clinical Medicine, Zhejiang Chinese Medical UniversitySuzhou Institute of Biomedical Engineering and Technology, Chinese Academy of ScienceSuzhou Institute of Biomedical Engineering and Technology, Chinese Academy of ScienceSuzhou Institute of Biomedical Engineering and Technology, Chinese Academy of ScienceSuzhou Institute of Biomedical Engineering and Technology, Chinese Academy of ScienceDepartment of Radiology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesDepartment of Radiology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of SciencesDepartment of Neurology, The Second Affiliated Hospital of Soochow UniversityBeijing Children’s Hospital, Capital Medical University, National Center for Children’s HealthSuzhou Institute of Biomedical Engineering and Technology, Chinese Academy of ScienceAbstract Background Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder that affects behavior, attention, and learning. Current diagnoses rely heavily on subjective assessments, underscoring the need for objective imaging-based methods. This study aims to explore whether structural connectivity networks derived from MRI can reveal alterations associated with ADHD and support data-driven understanding. Methods We collected brain MRI data from 947 individuals (aged 7–26 years; 590 males, 356 females, 1 unspecified) across eight centers, sourced from the Neuro Bureau ADHD-200 preprocessed dataset. Transformer-based deep learning models were used to learn relationships between different brain regions and construct structural connectivity networks. To prepare input for the model, each region was transformed into a standardized data sequence using four different strategies. The strength of connectivity between brain regions was then measured to identify structural differences related to ADHD. Five-fold cross-validation and statistical analyses were used to evaluate model robustness and group differences, respectively. Results Here we show that the proposed method performs well in distinguishing ADHD individuals from healthy controls, with accuracy reaching 71.9 percent and an area under curve of 0.74. The structural networks also reveal significant differences in connectivity patterns (paired t-test: P = 0.81 × 10−6), particularly involving regions responsible for motor and executive function. Notably, the importance rankings of several brain regions, including the thalamus and caudate, differ markedly between groups. Conclusions This study shows that ADHD may be associated with connectivity alterations in multiple brain regions. Our findings suggest that brain structural connectivity networks built using Transformer-based methods offer a promising tool for both diagnosis and further research into brain structure.https://doi.org/10.1038/s43856-025-01015-1 |
| spellingShingle | Liting Shi Lei Shi Zhijun Cui Chengting Lin Rui Zhang Jiayi Zhang Yechen Zhu Wei Shi Jianlin Wang Yanlong Wang Dongxing Wang Haihong Liu Xin Gao Transformer-based structural connectivity networks for ADHD-related connectivity alterations Communications Medicine |
| title | Transformer-based structural connectivity networks for ADHD-related connectivity alterations |
| title_full | Transformer-based structural connectivity networks for ADHD-related connectivity alterations |
| title_fullStr | Transformer-based structural connectivity networks for ADHD-related connectivity alterations |
| title_full_unstemmed | Transformer-based structural connectivity networks for ADHD-related connectivity alterations |
| title_short | Transformer-based structural connectivity networks for ADHD-related connectivity alterations |
| title_sort | transformer based structural connectivity networks for adhd related connectivity alterations |
| url | https://doi.org/10.1038/s43856-025-01015-1 |
| work_keys_str_mv | AT litingshi transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT leishi transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT zhijuncui transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT chengtinglin transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT ruizhang transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT jiayizhang transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT yechenzhu transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT weishi transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT jianlinwang transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT yanlongwang transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT dongxingwang transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT haihongliu transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations AT xingao transformerbasedstructuralconnectivitynetworksforadhdrelatedconnectivityalterations |