Solving Large Multicut Problems for Connectomics via Domain Decomposition

Constantin Pape

Abstract: In this contribution we demonstrate how a Multicut- based segmentation pipeline can be scaled up to datasets of hundreds of Gigabytes in size. Such datasets are preva- lent in connectomics, where neuron segmentation needs to be performed across very large electron microscopy image volumes. We show the advantages of a hierarchical block- wise scheme over local stitching strategies and evaluate the performance of different Multicut solvers for the segmenta- tion of the blocks in the hierarchy. We validate the accuracy of our algorithm on a small fully annotated dataset (5x5x5 mm) and demonstrate no significant loss in segmentation quality compared to solving the Multicut problem globally. We evaluate the scalability of the algorithm on a 95x60x60 mm image volume and show that solving the Multicut prob- lem is no longer the bottleneck of the segmentation pipeline.