A geometric approach to robust medical image segmentation

Ainkaran Santhirasekaram, Mathias Winkler, Andrea G. Rockall, Ben Glocker

Abstract: Highlights•Geometric constraints in the latent space of a deep learning for Robust Segmentation.•We hypothesis and prove group equivariant constraints in the latent space improves robustness.•A discrete equivariant shape latent space is sampled to construct the segmentation map.•Method demonstrated in the task of single domain generalisation.