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

Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool forstudying the native structure and organization of macromolecules inside singlecells. For systematic recognition and recovery of macromolecular structurescaptured by CECT, methods for several important tasks such as subtomogramclassification and semantic segmentation have been developed. However, therecognition and recovery of macromolecular structures are still very difficultdue to high molecular structural diversity, crowding molecular environment, andthe imaging limitations of CECT. In this paper, we propose a novel multi-task3D convolutional neural network model for simultaneous classification,segmentation, and coarse structural recovery of macromolecules of interest insubtomograms. In our model, the learned image features of one task are sharedand thereby mutually reinforce the learning of other tasks. Evaluated onrealistically simulated and experimental CECT data, our multi-task learningmodel outperformed all single-task learning methods for classification andsegmentation. In addition, we demonstrate that our model can generalize todiscover, segment and recover novel structures that do not exist in thetraining data.

Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography