Learning and Segmenting Dense Voxel Embeddings for 3D Neuron Reconstruction

TL;DR

This paper introduces a deep learning-based method for segmenting neurons in 3D electron microscopy images using dense voxel embeddings and metric graph partitioning, achieving state-of-the-art accuracy.

Contribution

The authors propose a novel approach that leverages dense voxel embeddings and metric graph partitioning for highly accurate neuron segmentation in 3D EM images, with no modification needed for the embedding network during agglomeration.

Findings

Achieves state-of-the-art accuracy on 3D neuron reconstruction

Improves segmentation of thin neuronal structures

Effectively handles complex self-contact motifs

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.