Dynamic Structural Brain Network Construction by Hierarchical Prototype Embedding GCN using T1-MRI

TL;DR

This paper introduces a novel method for constructing dynamic structural brain networks from T1-MRI data, utilizing hierarchical prototypes and graph convolutional networks to improve individual specificity and hierarchical correlation modeling, achieving state-of-the-art results in MCI prediction.

Contribution

The paper presents a new dynamic brain network construction approach that localizes critical regions and models hierarchical correlations using prototypes and GCNs, addressing limitations of previous methods.

Findings

Achieved state-of-the-art performance on ADNI datasets for MCI prediction.

Effectively localizes critical brain regions with hierarchical distribution.

Demonstrates improved correlation modeling over traditional static methods.

Abstract

Constructing structural brain networks using T1-weighted magnetic resonance imaging (T1-MRI) presents a significant challenge due to the lack of direct regional connectivity information. Current methods with T1-MRI rely on predefined regions or isolated pretrained location modules to obtain atrophic regions, which neglects individual specificity. Besides, existing methods capture global structural context only on the whole-image-level, which weaken correlation between regions and the hierarchical distribution nature of brain connectivity.We hereby propose a novel dynamic structural brain network construction method based on T1-MRI, which can dynamically localize critical regions and constrain the hierarchical distribution among them for constructing dynamic structural brain network. Specifically, we first cluster spatially-correlated channel and generate several critical brain regions as prototypes. Further, we introduce a contrastive loss function to constrain the prototypes distribution, which embed the hierarchical brain semantic structure into the latent space. Self-attention and GCN are then used to dynamically construct hierarchical correlations of critical regions for brain network and explore the correlation, respectively. Our method is evaluated on ADNI-1 and ADNI-2 databases for mild cognitive impairment (MCI) conversion prediction, and acheive the state-of-the-art (SOTA) performance. Our source code is available at http://github.com/*******.