Utility of Equivariant Message Passing in Cortical Mesh Segmentation
This addresses a domain-specific challenge in medical image analysis for cortical segmentation, but the findings are incremental as they compare existing methods without introducing a new approach.
The paper tackles the problem of cortical mesh segmentation under misalignment across subjects, finding that while plain GNNs outperform EGNNs on aligned meshes, EGNNs maintain consistent performance on misaligned meshes, and plain GNNs achieve best results with realigned data.
The automated segmentation of cortical areas has been a long-standing challenge in medical image analysis. The complex geometry of the cortex is commonly represented as a polygon mesh, whose segmentation can be addressed by graph-based learning methods. When cortical meshes are misaligned across subjects, current methods produce significantly worse segmentation results, limiting their ability to handle multi-domain data. In this paper, we investigate the utility of E(n)-equivariant graph neural networks (EGNNs), comparing their performance against plain graph neural networks (GNNs). Our evaluation shows that GNNs outperform EGNNs on aligned meshes, due to their ability to leverage the presence of a global coordinate system. On misaligned meshes, the performance of plain GNNs drop considerably, while E(n)-equivariant message passing maintains the same segmentation results. The best results can also be obtained by using plain GNNs on realigned data (co-registered meshes in a global coordinate system).