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

2026-02-19

AI Summary

This study addresses the challenge of differentiating Alzheimer’s disease (AD) from Lewy body dementia (LBD), whose clinical presentations substantially overlap, by overcoming limitations of existing atlas-based brain network approaches that struggle with topological heterogeneity and node misalignment arising from individualized cortical folding patterns. To this end, the authors propose a novel method for constructing cortical similarity networks based on three-hinge gyral landmarks, integrating local morphological features with anatomy-aware encoding. They further introduce a probabilistic permutation-invariant random walk framework that enables graph representation learning without explicit node correspondence. Evaluated on large-scale clinical cohorts of AD and LBD, the proposed approach significantly outperforms state-of-the-art sulcal- and atlas-based baselines, demonstrating its robustness and potential for precise dementia diagnosis.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Content-based information diffusion
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Alzheimer's disease
• Lewy body dementia
• gyral folding
• cortical heterogeneity
• graph learning

Innovation

• probability-invariant random walk
• gyral folding network
• cortical similarity network
• permutation invariance
• dementia diagnosis