High-precision automated reconstruction of neurons with flood-filling networks

By Michał Januszewski, J. Kornfeld, Peter H. Li, Art Pope, T. Blakely, Larry F. Lindsey, Jeremy B. Maitin-Shepard, Mike Tyka, Winfried Denk, Viren Jain. Nature Methods, 2017

380 citations recorded by the source corpus.

Reconstruction of neural circuits from volume electron microscopy data requires the tracing of cells in their entirety, including all their neurites. Automated approaches have been developed for tracing, but their error rates are too high to generate reliable circuit diagrams without extensive human proofreading. We present flood-filling networks, a method for automated segmentation that, similar to most previous efforts, uses convolutional neural networks, but contains in addition a recurrent pathway that allows the iterative optimization and extension of individual neuronal processes. We used flood-filling networks to trace neurons in a dataset obtained by serial block-face electron microscopy of a zebra finch brain. Using our method, we achieved a mean error-free neurite path length of 1.1 mm, and we observed only four mergers in a test set with a path length of 97 mm. The performance of flood-filling networks was an order of magnitude better than that of previous approaches applied to this dataset, although with substantially increased computational costs. Flood-filling networks are a deep-learning-based pipeline for reconstruction of neurons from electron microscopy datasets. The approach results in exceptionally low error rates, thereby reducing the need for extensive human proofreading.

Subfields: Biophysics, Structural Biology, Surfaces, Coatings and Films

View Paper: https://www.semanticscholar.org/paper/7cfc1e85392d4007a90ecd05b7a0318252041c3c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

Citations in the corpus

Object Instance Annotation With Deep Extreme Level Set Evolution (2019, background): “[22] adds a recurrent pathway onto deep CNNs and reconstructs neural cells by iterative extension.”
A connectome of the Drosophila central complex reveals network motifs suitable for flexible navigation and context-dependent action selection (2020, methodology): “…et al., 2018) and improvements in machine learning have enabled high-throughput reconstruction of larger neural circuits (Dorkenwald et al., 2020; Januszewski et al., 2018), the step from acquiring a volume to obtaining a complete connectome still requires considerable human proofreading and…”
Deep learning for cellular image analysis (2019, methodology): “These approaches have been applied to the segmentation of neurons in images from cryo-electron microscopy 101 , with enough accuracy to place imaging-based connectomics within reach 102 .”