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

Detecting synaptic clefts is a crucial step to investigate the biologicalfunction of synapses. The volume electron microscopy (EM) allows theidentification of synaptic clefts by photoing EM images with high resolutionand fine details. Machine learning approaches have been employed toautomatically predict synaptic clefts from EM images. In this work, we proposea novel and augmented deep learning model, known as CleftNet, for improvingsynaptic cleft detection from brain EM images. We first propose two novelnetwork components, known as the feature augmentor and the label augmentor, foraugmenting features and labels to improve cleft representations. The featureaugmentor can fuse global information from inputs and learn commonmorphological patterns in clefts, leading to augmented cleft features. Inaddition, it can generate outputs with varying dimensions, making it flexibleto be integrated in any deep network. The proposed label augmentor augments thelabel of each voxel from a value to a vector, which contains both thesegmentation label and boundary label. This allows the network to learnimportant shape information and to produce more informative cleftrepresentations. Based on the proposed feature augmentor and label augmentor,We build the CleftNet as a U-Net like network. The effectiveness of our methodsis evaluated on both online and offline tasks. Our CleftNet currently ranks \#1on the online task of the CREMI open challenge. In addition, both quantitativeand qualitative results in the offline tasks show that our method outperformsthe baseline approaches significantly.

CleftNet: Augmented Deep Learning for Synaptic Cleft Detection from Brain Electron Microscopy