Improving 3d Em Data Segmentation By Joint Optimization Over Boundary Evidence And Biological Priors

We present a new automated neuron segmentation algorithm for isotropic 3D electron microscopy data. We cast the problem into the asymmetric multiway cut framework. The latter combines boundary-based segmentation (clustering) with region-based segmentation (semantic labeling) in a single problem and objective function. This joint formulation allows us to augment local boundary evidence with higher-level biological priors, such as membership to an axonic or dendritic neurite. Joint optimization enforces consistency between evidence and priors, leading to correct resolution of many difficult boundary configurations. We show experimentally on a FIB/SEM dataset of mouse cortex that the new approach outperforms existing hierarchical segmentation and multicut algorithms which only use boundary evidence.