Application of improved graph convolutional network for cortical surface parcellation
Abstract Accurate cortical surface parcellation is essential for elucidating brain organizational principles, functional mechanisms, and the neural substrates underlying higher cognitive and emotional processes. However, the cortical surface is a highly folded complex geometry, and large regional va...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-00116-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850273581736394752 |
|---|---|
| author | Jia Tan Xiaomei Ren Yong Chen Xianju Yuan Feiba Chang Rui Yang Chengqun Ma Xiaoyu Chen Miao Tian Wei Chen Zihong Wang |
| author_facet | Jia Tan Xiaomei Ren Yong Chen Xianju Yuan Feiba Chang Rui Yang Chengqun Ma Xiaoyu Chen Miao Tian Wei Chen Zihong Wang |
| author_sort | Jia Tan |
| collection | DOAJ |
| description | Abstract Accurate cortical surface parcellation is essential for elucidating brain organizational principles, functional mechanisms, and the neural substrates underlying higher cognitive and emotional processes. However, the cortical surface is a highly folded complex geometry, and large regional variations make the analysis of surface data challenging. Current methods rely on geometric simplification, such as spherical expansion, which takes hours for spherical mapping and registration, a popular but costly process that does not take full advantage of inherent structural information. In this study, we propose an Attention-guided Deep Graph Convolutional network (ADGCN) for end-to-end parcellation on primitive cortical surface manifolds. ADGCN consists of a deep graph convolutional layer with a symmetrical U-shaped structure, which enables it to effectively transmit detailed information of the original brain map and learn the complex graph structure, help the network enhance feature extraction capability. What’s more, we introduce the Squeeze and Excitation (SE) module, which enables the network to better capture key features, suppress unimportant features, and significantly improve parcellation performance with a small amount of computation. We evaluated the model on a public dataset of 100 artificially labeled brain surfaces. Compared with other methods, the proposed network achieves Dice coefficient of 88.53% and an accuracy of 90.27%. The network can segment the cortex directly in the original domain, and has the advantages of high efficiency, simple operation and strong interpretability. This approach facilitates the investigation of cortical changes during development, aging, and disease progression, with the potential to enhance the accuracy of neurological disease diagnosis and the objectivity of treatment efficacy evaluation. |
| format | Article |
| id | doaj-art-ef5ab21ac62a4f3085e3ef14044e571d |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-ef5ab21ac62a4f3085e3ef14044e571d2025-08-20T01:51:27ZengNature PortfolioScientific Reports2045-23222025-05-0115111610.1038/s41598-025-00116-0Application of improved graph convolutional network for cortical surface parcellationJia Tan0Xiaomei Ren1Yong Chen2Xianju Yuan3Feiba Chang4Rui Yang5Chengqun Ma6Xiaoyu Chen7Miao Tian8Wei Chen9Zihong Wang10Department of Medical Engineering, First Affiliated Hospital of Army Medical UniversityDepartment of Medical Engineering, First Affiliated Hospital of Army Medical UniversityDepartment of Medical Engineering, First Affiliated Hospital of Army Medical UniversityDepartment of Medical Engineering, First Affiliated Hospital of Army Medical UniversityDepartment of Medical Engineering, First Affiliated Hospital of Army Medical UniversityDepartment of Medical Engineering, First Affiliated Hospital of Army Medical UniversityDepartment of Medical Engineering, First Affiliated Hospital of Army Medical UniversityDepartment of Medical Engineering, First Affiliated Hospital of Army Medical UniversityDepartment of Medical Engineering, First Affiliated Hospital of Army Medical UniversityDepartment of Radiology , First Affiliated Hospital of Army Medical University Department of Medical Engineering, First Affiliated Hospital of Army Medical UniversityAbstract Accurate cortical surface parcellation is essential for elucidating brain organizational principles, functional mechanisms, and the neural substrates underlying higher cognitive and emotional processes. However, the cortical surface is a highly folded complex geometry, and large regional variations make the analysis of surface data challenging. Current methods rely on geometric simplification, such as spherical expansion, which takes hours for spherical mapping and registration, a popular but costly process that does not take full advantage of inherent structural information. In this study, we propose an Attention-guided Deep Graph Convolutional network (ADGCN) for end-to-end parcellation on primitive cortical surface manifolds. ADGCN consists of a deep graph convolutional layer with a symmetrical U-shaped structure, which enables it to effectively transmit detailed information of the original brain map and learn the complex graph structure, help the network enhance feature extraction capability. What’s more, we introduce the Squeeze and Excitation (SE) module, which enables the network to better capture key features, suppress unimportant features, and significantly improve parcellation performance with a small amount of computation. We evaluated the model on a public dataset of 100 artificially labeled brain surfaces. Compared with other methods, the proposed network achieves Dice coefficient of 88.53% and an accuracy of 90.27%. The network can segment the cortex directly in the original domain, and has the advantages of high efficiency, simple operation and strong interpretability. This approach facilitates the investigation of cortical changes during development, aging, and disease progression, with the potential to enhance the accuracy of neurological disease diagnosis and the objectivity of treatment efficacy evaluation.https://doi.org/10.1038/s41598-025-00116-0Attention mechanismCortical surface parcellationDeep learningGraph Convolution networkMRI |
| spellingShingle | Jia Tan Xiaomei Ren Yong Chen Xianju Yuan Feiba Chang Rui Yang Chengqun Ma Xiaoyu Chen Miao Tian Wei Chen Zihong Wang Application of improved graph convolutional network for cortical surface parcellation Scientific Reports Attention mechanism Cortical surface parcellation Deep learning Graph Convolution network MRI |
| title | Application of improved graph convolutional network for cortical surface parcellation |
| title_full | Application of improved graph convolutional network for cortical surface parcellation |
| title_fullStr | Application of improved graph convolutional network for cortical surface parcellation |
| title_full_unstemmed | Application of improved graph convolutional network for cortical surface parcellation |
| title_short | Application of improved graph convolutional network for cortical surface parcellation |
| title_sort | application of improved graph convolutional network for cortical surface parcellation |
| topic | Attention mechanism Cortical surface parcellation Deep learning Graph Convolution network MRI |
| url | https://doi.org/10.1038/s41598-025-00116-0 |
| work_keys_str_mv | AT jiatan applicationofimprovedgraphconvolutionalnetworkforcorticalsurfaceparcellation AT xiaomeiren applicationofimprovedgraphconvolutionalnetworkforcorticalsurfaceparcellation AT yongchen applicationofimprovedgraphconvolutionalnetworkforcorticalsurfaceparcellation AT xianjuyuan applicationofimprovedgraphconvolutionalnetworkforcorticalsurfaceparcellation AT feibachang applicationofimprovedgraphconvolutionalnetworkforcorticalsurfaceparcellation AT ruiyang applicationofimprovedgraphconvolutionalnetworkforcorticalsurfaceparcellation AT chengqunma applicationofimprovedgraphconvolutionalnetworkforcorticalsurfaceparcellation AT xiaoyuchen applicationofimprovedgraphconvolutionalnetworkforcorticalsurfaceparcellation AT miaotian applicationofimprovedgraphconvolutionalnetworkforcorticalsurfaceparcellation AT weichen applicationofimprovedgraphconvolutionalnetworkforcorticalsurfaceparcellation AT zihongwang applicationofimprovedgraphconvolutionalnetworkforcorticalsurfaceparcellation |