Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Gyral-Sulcal-Net: An Integrated Network Representation of Brain Folding Patterns

Chao Cao, Tong Chen, Nan Zhao, Minheng Chen, Michael Qu, Zeyu Zhang, Xiao Shi, Xiang Li, Tianming Liu, Lu Zhang

TL;DR

The paper tackles the limitation of region-based brain networks that overlook fine-grained cortical folding landmarks. It introduces GS-Net, a four-step pipeline that segments gyri and sulci, erodes to skeletons, marches and trims to form GyralNet and SulcalNet, and integrates them to identify Gyri Conjunction, Sulci Conjunction, and Sulci-Gyri Conjunction nodes. Across 1,623 brains from diverse cohorts, GS-Net provides a fast, accurate, and unified representation of folding patterns, outperforming baselines in detecting consistent landmarks while drastically reducing computation time. This approach offers a scalable framework to integrate folding patterns with structural and functional networks, enabling finer-grained analyses of cortical morphology and its genetic and developmental determinants.

Abstract

Our brain functions as a complex communication network, and studying it from a network perspective offers valuable insights into its organizational principles and links to cognitive functions and brain disorders. However, most current network studies typically use brain regions as nodes, often overlooking the intricate folding patterns of finer-scale anatomical landmarks within these regions. In this study, we introduce a novel approach to integrate the brain's two primary folding patterns - gyri and sulci - into a unified network termed the Gyral-Sulcal-Net (GS-Net), in which three different types of finer-scale landmarks have been successfully identified. We evaluated the proposed GS-Net across multiple datasets, comprising over 1,600 brains, spanning different age groups (from 34 gestational weeks to elderly adults) and cohorts (healthy brains and those with pathological conditions). The experimental results demonstrate that the GS-Net can effectively integrate and represent diverse cortical folding patterns from a network perspective. More importantly, this approach offers a promising way for integrating different folding patterns into a unified anatomical brain network, alongside structural and functional networks, providing a comprehensive framework for studying brain networks. (The GS-Net toolbox will be released soon.)

Gyral-Sulcal-Net: An Integrated Network Representation of Brain Folding Patterns

TL;DR

The paper tackles the limitation of region-based brain networks that overlook fine-grained cortical folding landmarks. It introduces GS-Net, a four-step pipeline that segments gyri and sulci, erodes to skeletons, marches and trims to form GyralNet and SulcalNet, and integrates them to identify Gyri Conjunction, Sulci Conjunction, and Sulci-Gyri Conjunction nodes. Across 1,623 brains from diverse cohorts, GS-Net provides a fast, accurate, and unified representation of folding patterns, outperforming baselines in detecting consistent landmarks while drastically reducing computation time. This approach offers a scalable framework to integrate folding patterns with structural and functional networks, enabling finer-grained analyses of cortical morphology and its genetic and developmental determinants.

Abstract

Our brain functions as a complex communication network, and studying it from a network perspective offers valuable insights into its organizational principles and links to cognitive functions and brain disorders. However, most current network studies typically use brain regions as nodes, often overlooking the intricate folding patterns of finer-scale anatomical landmarks within these regions. In this study, we introduce a novel approach to integrate the brain's two primary folding patterns - gyri and sulci - into a unified network termed the Gyral-Sulcal-Net (GS-Net), in which three different types of finer-scale landmarks have been successfully identified. We evaluated the proposed GS-Net across multiple datasets, comprising over 1,600 brains, spanning different age groups (from 34 gestational weeks to elderly adults) and cohorts (healthy brains and those with pathological conditions). The experimental results demonstrate that the GS-Net can effectively integrate and represent diverse cortical folding patterns from a network perspective. More importantly, this approach offers a promising way for integrating different folding patterns into a unified anatomical brain network, alongside structural and functional networks, providing a comprehensive framework for studying brain networks. (The GS-Net toolbox will be released soon.)
Paper Structure (14 sections, 4 figures)

This paper contains 14 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Method
  3. Method Overview
  4. Gyri-Sulci Segmentation
  5. Gyri-Sulci Bidirectional Erosion
  6. Tree Marching and Trimming
  7. Integration and Landmark Identification
  8. Results
  9. Datasets Description and Data Pre-processing
  10. Constructed GS-Net
  11. Comparison with Baseline Methods
  12. Runtime Comparison
  13. Discussion and Conclusion
  14. Compliance with ethical standards

Figures (4)

  • Figure 1: The pipeline of proposed GS-Net framework.
  • Figure 2: Constructed GS-Net of 25 randomly selected subjects from 5 different cohorts, including AD patients, elderly adults, young adults, individuals at 6 months, and individuals at 34 weeks’ gestation.
  • Figure 3: Qualitative comparison across five subjects shows that both the Single-Measure sulc-based baseline and the traditional method frequently produce redundant or spurious 3HGs (yellow circles). In contrast, our Multi-Measures approach yields more accurate and consistent 3HGs.
  • Figure 4: Runtime comparison between the traditional method and our Multi-Measures approach (Ours).