Solving Large Multicut Problems for Connectomics via Domain Decomposition

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 prevalent 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 segmentation of the blocks in the hierarchy. We validate the accuracy of our algorithm on a small fully annotated dataset (5×5×5 μm) and demonstrate no significant loss in segmentation quality compared to solving the Multicut problem globally. We evaluate the scalability of the algorithm on a 95 x 60 x 60 μm image volume and show that solving the Multicut problem is no longer the bottleneck of the segmentation pipeline.

[1]  Stephen M. Plaza.  Focused Proofreading: Efficiently Extracting Connectomes from Segmented EM Images , 2014, ArXiv.

[2]  Philipp Otto,et al.  webKnossos: efficient online 3D data annotation for connectomics , 2017, Nature Methods.

[3]  Daniel R. Berger,et al.  The Fuzzy Logic of Network Connectivity in Mouse Visual Thalamus , 2016, Cell.

[4]  Hayk Saribekyan,et al.  A Multi-Pass Approach to Large-Scale Connectomics , 2016, ArXiv.

[5]  Jacob Goldberger,et al.  Ensemble Segmentation Using Efficient Integer Linear Programming , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Ullrich Köthe,et al.  Globally Optimal Closed-Surface Segmentation for Connectomics , 2012, ECCV.

[7]  Gerhard Reinelt,et al.  Globally Optimal Image Partitioning by Multicuts , 2011, EMMCVPR.

[8]  Fred A Hamprecht,et al.  Multicut brings automated neurite segmentation closer to human performance , 2017, Nature Methods.

[9]  Jörg H. Kappes,et al.  Fusion moves for correlation clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Stephen M. Plaza,et al.  Large-Scale Electron Microscopy Image Segmentation in Spark , 2016, ArXiv.

[11]  M. Meilă.  Comparing clusterings---an information based distance , 2007 .

[12]  Bjoern Andres,et al.  A Message Passing Algorithm for the Minimum Cost Multicut Problem , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Davi D Bock,et al.  Volume electron microscopy for neuronal circuit reconstruction , 2012, Current Opinion in Neurobiology.

[14]  S.,et al.  An Efficient Heuristic Procedure for Partitioning Graphs , 2022 .

[15]  Ullrich Köthe,et al.  Probabilistic image segmentation with closedness constraints , 2011, 2011 International Conference on Computer Vision.

[16]  Joachim M. Buhmann,et al.  Crowdsourcing the creation of image segmentation algorithms for connectomics , 2015, Front. Neuroanat..

[17]  Ullrich Köthe,et al.  Cut, Glue, & Cut: A Fast, Approximate Solver for Multicut Partitioning , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Ullrich Köthe,et al.  An Efficient Fusion Move Algorithm for the Minimum Cost Lifted Multicut Problem , 2016, ECCV.

[19]  M. R. Rao,et al.  The partition problem , 1993, Math. Program..

[20]  Srinivas C. Turaga,et al.  Connectomic reconstruction of the inner plexiform layer in the mouse retina , 2013, Nature.

[21]  Jianbo Shi,et al.  Machine Learning of Hierarchical Clustering to Segment 2D and 3D Images , 2013, PloS one.

[22]  William R. Gray Roncal,et al.  Saturated Reconstruction of a Volume of Neocortex , 2015, Cell.

[23]  H. Sebastian Seung,et al.  Superhuman Accuracy on the SNEMI3D Connectomics Challenge , 2017, ArXiv.

[24]  Brett J. Graham,et al.  Anatomy and function of an excitatory network in the visual cortex , 2016, Nature.

[25]  Won-Ki Jeong,et al.  Whole-brain serial-section electron microscopy in larval zebrafish , 2017, Nature.

[26]  Chao Chen,et al.  An efficient conditional random field approach for automatic and interactive neuron segmentation , 2016, Medical Image Anal..

[27]  Ullrich Köthe,et al.  Learning to Segment Neurons with Non-local Quality Measures , 2013, MICCAI.

[28]  Anirban Chakraborty,et al.  Graph-based active learning of agglomeration (GALA): a Python library to segment 2D and 3D neuroimages , 2014, Front. Neuroinform..

[29]  Kyomin Jung,et al.  Local Rules for Global MAP: When Do They Work ? , 2009, NIPS.

[30]  Srinivas C. Turaga,et al.  Space-time wiring specificity supports direction selectivity in the retina , 2014, Nature.

[31]  Matthew Cook,et al.  Efficient automatic 3D-reconstruction of branching neurons from EM data , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Stephan Saalfeld,et al.  CATMAID: collaborative annotation toolkit for massive amounts of image data , 2009, Bioinform..

[33]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[34]  Gregory D. Hager,et al.  An automated images-to-graphs framework for high resolution connectomics , 2014, Front. Neuroinform..

[35]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Eric T. Trautman,et al.  A complete electron microscopy volume of the brain of adult Drosophila melanogaster , 2017 .