English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The current neuron reconstruction pipeline for electron microscopy (EM) datausually includes automatic image segmentation followed by extensive humanexpert proofreading. In this work, we aim to reduce human workload bypredicting connectivity between over-segmented neuron pieces, taking bothmicroscopy image and 3D morphology features into account, similar to humanproofreading workflow. To this end, we first construct a dataset, namedFlyTracing, that contains millions of pairwise connections of segmentsexpanding the whole fly brain, which is three orders of magnitude larger thanexisting datasets for neuron segment connection. To learn sophisticatedbiological imaging features from the connectivity annotations, we propose anovel connectivity-aware contrastive learning method to generate densevolumetric EM image embedding. The learned embeddings can be easilyincorporated with any point or voxel-based morphological representations forautomatic neuron tracing. Extensive comparisons of different combinationschemes of image and morphological representation in identifying split errorsacross the whole fly brain demonstrate the superiority of the proposedapproach, especially for the locations that contain severe imaging artifacts,such as section missing and misalignment. The dataset and code are available athttps://github.com/Levishery/Flywire-Neuron-Tracing.

Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing