Decoding Functional Networks for Visual Categories via GNNs
For neuroscientists, this provides a connectivity-based framework to understand how large-scale brain networks represent visual categories, extending beyond voxel-level selectivity.
The study uses a signed Graph Neural Network on 7T fMRI data to decode visual categories (sports, food, vehicles) from functional connectivity, achieving accurate decoding and revealing reproducible subnetworks along visual pathways.
Understanding how large-scale brain networks represent visual categories is fundamental to linking perception and cortical organization. Using high-resolution 7T fMRI from the Natural Scenes Dataset, we construct parcel-level functional graphs and train a signed Graph Neural Network that models both positive and negative interactions, with a sparse edge mask and class-specific saliency. The model accurately decodes category-specific functional connectivity states (sports, food, vehicles) and reveals reproducible, biologically meaningful subnetworks along the ventral and dorsal visual pathways. This framework bridges machine learning and neuroscience by extending voxel-level category selectivity to a connectivity-based representation of visual processing.