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...

Full description

Saved in:
Bibliographic Details
Main Authors: Jia Tan, Xiaomei Ren, Yong Chen, Xianju Yuan, Feiba Chang, Rui Yang, Chengqun Ma, Xiaoyu Chen, Miao Tian, Wei Chen, Zihong Wang
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