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

TL;DR

This paper introduces a probability-invariant random walk framework for classifying individualized gyral folding brain networks, improving robustness and accuracy in differentiating Alzheimer's and Lewy body dementia.

Contribution

It presents a novel random walk-based method that handles anatomical variability without explicit node alignment, advancing brain network analysis for dementia diagnosis.

Findings

Outperforms existing models in clinical datasets

Demonstrates robustness to anatomical heterogeneity

Improves diagnostic accuracy for AD and LBD

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.