Dynamic Structural Brain Network Construction by Hierarchical Prototype Embedding GCN using T1-MRI
This work addresses the problem of individual specificity and hierarchical connectivity in brain network construction for medical imaging researchers, though it appears incremental as it builds on existing methods like GCN and self-attention.
The paper tackles the challenge of constructing structural brain networks from T1-MRI data by dynamically localizing critical regions and embedding hierarchical brain semantics, achieving state-of-the-art performance in mild cognitive impairment conversion prediction on ADNI-1 and ADNI-2 databases.
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/*******.