Learning and Segmenting Dense Voxel Embeddings for 3D Neuron Reconstruction

Kisuk Lee, Ran Lu, Kyle Luther, H. Sebastian Seung

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

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.

Original languageEnglish (US)
Pages (from-to)3801-3811
Number of pages11
JournalIEEE Transactions on Medical Imaging
Volume40
Issue number12
DOIs
StatePublished - Dec 1 2021
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Keywords

  • Connectomics
  • deep metric learning
  • dense embeddings
  • electron microscopy
  • image segmentation
  • neuron reconstruction

Fingerprint

Dive into the research topics of 'Learning and Segmenting Dense Voxel Embeddings for 3D Neuron Reconstruction'. Together they form a unique fingerprint.

Cite this