Learning and Segmenting Dense Voxel Embeddings for 3D Neuron Reconstruction

Abstract

We show dense voxel embeddings learned via deep metric learning can be employed to produce a highly accurate segmentation of neurons from 3D electron microscopy images. A "metric graph" on a set of edges between voxels is constructed from the dense voxel embeddings generated by a convolutional network. Partitioning the metric graph with long-range edges as repulsive constraints yields an initial segmentation with high precision, with substantial accuracy gain for very thin objects. The convolutional embedding net is reused without any modification to agglomerate the systematic splits caused by complex "self-contact" motifs. Our proposed method achieves state-of-the-art accuracy on the challenging problem of 3D neuron reconstruction from the brain images acquired by serial section electron microscopy. Our alternative, object-centered representation could be more generally useful for other computational tasks in automated neural circuit reconstruction.

References in corpus (9)

• On the Convergence of Adam and Beyond
• Semantic Instance Segmentation with a Discriminative Loss Function
• Large Scale Image Segmentation with Structured Loss based Deep Learning for Connectome Reconstruction
• Superhuman Accuracy on the SNEMI3D Connectomics Challenge
• Semantic Instance Segmentation via Deep Metric Learning
• Image Segmentation by Size-Dependent Single Linkage Clustering of a Watershed Basin Graph
• A Multi-Pass Approach to Large-Scale Connectomics
• Flood-Filling Networks
• Instance Segmentation of Fibers from Low Resolution CT Scans via 3D Deep Embedding Learning

Cited by in corpus (1)

• Latent Feature Representation via Unsupervised Learning for Pattern Discovery in Massive Electron Microscopy Image Volumes