Cell membrane feature detection using graph neural networks

Many cellular processes involve complex deformations of the cell surface, which are difficult to automatically detect and analyse in 3D microscopy images. One issue faced by modern machine learning methods is that 3D microscopy images are large and require a high computational load to analyse. To simplify this problem, we propose a graph convolutional neural network applied to a triangulated mesh of the cell surface, where nodes are associated with geometric and intensity features of biomarkers on or near the surface. Here, we focus on identification of macropinocytic cups on the surface of Dictyostelium cells, structures involved in the uptake of extracellular fluid. The network classifies each node into belonging to a cup or not, enabling subsequent studies of the detailed distribution of molecules regulating fluid uptake in cells. We show that a simple network architecture can identify key features of the surface, suggesting that these methods have strong potential for advancing the analysis of cell surface dynamics