2D histology meets 3D topology: Cytoarchitectonic brain mapping with Graph Neural Networks

TL;DR

This paper introduces a novel method combining 2D histology and 3D topology using graph neural networks to improve brain region mapping accuracy, addressing limitations of previous 2D-only approaches.

Contribution

It reformulates cytoarchitectonic brain mapping as a node classification problem on a 3D mesh using deep features from 2D histology and GNNs, enhancing accuracy.

Findings

Significantly improved classification results over previous methods.

Effective integration of 2D histology with 3D brain topology.

Framework allows incorporation of additional neuroanatomical priors.

Abstract

Cytoarchitecture describes the spatial organization of neuronal cells in the brain, including their arrangement into layers and columns with respect to cell density, orientation, or presence of certain cell types. It allows to segregate the brain into cortical areas and subcortical nuclei, links structure with connectivity and function, and provides a microstructural reference for human brain atlases. Mapping boundaries between areas requires to scan histological sections at microscopic resolution. While recent high-throughput scanners allow to scan a complete human brain in the order of a year, it is practically impossible to delineate regions at the same pace using the established gold standard method. Researchers have recently addressed cytoarchitectonic mapping of cortical regions with deep neural networks, relying on image patches from individual 2D sections for classification. However, the 3D context, which is needed to disambiguate complex or obliquely cut brain regions, is not taken into account. In this work, we combine 2D histology with 3D topology by reformulating the mapping task as a node classification problem on an approximate 3D midsurface mesh through the isocortex. We extract deep features from cortical patches in 2D histological sections which are descriptive of cytoarchitecture, and assign them to the corresponding nodes on the 3D mesh to construct a large attributed graph. By solving the brain mapping problem on this graph using graph neural networks, we obtain significantly improved classification results. The proposed framework lends itself nicely to integration of additional neuroanatomical priors for mapping.