Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Probability-Invariant Random Walk Learning on Gyral Folding-Based Cortical Similarity Networks for Alzheimer's and Lewy Body Dementia Diagnosis

Minheng Chen, Jing Zhang, Tong Chen, Chao Cao, Tianming Liu, Li Su, Dajiang Zhu

TL;DR

A probability-invariant random-walk-based framework that classifies individualized gyral folding networks without explicit node alignment is proposed, demonstrating robustness and potential for dementia diagnosis.

Abstract

Alzheimer's disease (AD) and Lewy body dementia (LBD) present overlapping clinical features yet require distinct diagnostic strategies. While neuroimaging-based brain network analysis is promising, atlas-based representations may obscure individualized anatomy. Gyral folding-based networks using three-hinge gyri provide a biologically grounded alternative, but inter-individual variability in cortical folding results in inconsistent landmark correspondence and highly irregular network sizes, violating the fixed-topology and node-alignment assumptions of most existing graph learning methods, particularly in clinical datasets where pathological changes further amplify anatomical heterogeneity. We therefore propose a probability-invariant random-walk-based framework that classifies individualized gyral folding networks without explicit node alignment. Cortical similarity networks are built from local morphometric features and represented by distributions of anonymized random walks, with an anatomy-aware encoding that preserves permutation invariance. Experiments on a large clinical cohort of AD and LBD subjects show consistent improvements over existing gyral folding and atlas-based models, demonstrating robustness and potential for dementia diagnosis.

Probability-Invariant Random Walk Learning on Gyral Folding-Based Cortical Similarity Networks for Alzheimer's and Lewy Body Dementia Diagnosis

TL;DR

A probability-invariant random-walk-based framework that classifies individualized gyral folding networks without explicit node alignment is proposed, demonstrating robustness and potential for dementia diagnosis.

Abstract

Alzheimer's disease (AD) and Lewy body dementia (LBD) present overlapping clinical features yet require distinct diagnostic strategies. While neuroimaging-based brain network analysis is promising, atlas-based representations may obscure individualized anatomy. Gyral folding-based networks using three-hinge gyri provide a biologically grounded alternative, but inter-individual variability in cortical folding results in inconsistent landmark correspondence and highly irregular network sizes, violating the fixed-topology and node-alignment assumptions of most existing graph learning methods, particularly in clinical datasets where pathological changes further amplify anatomical heterogeneity. We therefore propose a probability-invariant random-walk-based framework that classifies individualized gyral folding networks without explicit node alignment. Cortical similarity networks are built from local morphometric features and represented by distributions of anonymized random walks, with an anatomy-aware encoding that preserves permutation invariance. Experiments on a large clinical cohort of AD and LBD subjects show consistent improvements over existing gyral folding and atlas-based models, demonstrating robustness and potential for dementia diagnosis.
Paper Structure (11 sections, 4 equations, 3 figures, 1 table)

This paper contains 11 sections, 4 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Dataset description and data pre-processing
  4. Preliminaries and method overview
  5. Conductance-based random walk sampling
  6. Anatomy-aware anonymized walk recording
  7. Reader neural network and aggregation
  8. Experiments and Results
  9. Experimental setup
  10. Results
  11. Conclusion

Figures (3)

  • Figure 1: Overview of PaIRWaL. Random walks on gyral folding-based similarity networks are encoded into invariant sequences and aggregated for graph-level classification.
  • Figure 2: Classification performance for AD/CN, LBD/CN, and AD/LBD tasks. Bars show mean ± standard deviation across cross-validation folds. ** denotes the statistical significance (p < 0.05) assessed using a two-sample t-test.
  • Figure 3: Sensitivity analysis and visualization of the proposed PaIRWaL. (a) Classification accuracy under different random walk lengths. (b) Performance with varying numbers of sampled walks per graph. (c) Cortical surface projection of aggregated 3HG heatmaps, obtained by region-wise weighted averaging and normalization on the Destrieux atlas, highlighting discriminative folding regions.