Learning and Segmenting Dense Voxel Embeddings for 3D Neuron Reconstruction
This addresses the challenging problem of automated neural circuit reconstruction for neuroscience, offering an incremental improvement with a novel method for a known bottleneck.
The paper tackles 3D neuron reconstruction from electron microscopy images by using dense voxel embeddings learned via deep metric learning to produce highly accurate segmentation, achieving state-of-the-art accuracy with substantial gains for thin objects.
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.