Paper ID: 2411.05825 • Published Nov 5, 2024
SurfGNN: A robust surface-based prediction model with interpretability for coactivation maps of spatial and cortical features
Zhuoshuo Li (1), Jiong Zhang (2), Youbing Zeng (1), Jiaying Lin (1), Dan Zhang (3), Jianjia Zhang (1), Duan Xu (4), Hosung Kim...
TL;DR
Get AI-generated summaries with premium
Get AI-generated summaries with premium
Current brain surface-based prediction models often overlook the variability
of regional attributes at the cortical feature level. While graph neural
networks (GNNs) excel at capturing regional differences, they encounter
challenges when dealing with complex, high-density graph structures. In this
work, we consider the cortical surface mesh as a sparse graph and propose an
interpretable prediction model-Surface Graph Neural Network (SurfGNN). SurfGNN
employs topology-sampling learning (TSL) and region-specific learning (RSL)
structures to manage individual cortical features at both lower and higher
scales of the surface mesh, effectively tackling the challenges posed by the
overly abundant mesh nodes and addressing the issue of heterogeneity in
cortical regions. Building on this, a novel score-weighted fusion (SWF) method
is implemented to merge nodal representations associated with each cortical
feature for prediction. We apply our model to a neonatal brain age prediction
task using a dataset of harmonized MR images from 481 subjects (503 scans).
SurfGNN outperforms all existing state-of-the-art methods, demonstrating an
improvement of at least 9.0% and achieving a mean absolute error (MAE) of
0.827+0.056 in postmenstrual weeks. Furthermore, it generates feature-level
activation maps, indicating its capability to identify robust regional
variations in different morphometric contributions for prediction.