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

Although deep encoder-decoder networks have achieved astonishing performancefor mitochondria segmentation from electron microscopy (EM) images, they stillproduce coarse segmentations with lots of discontinuities and false positives.Besides, the need for labor intensive annotations of large 3D dataset and hugememory overhead by 3D models are also major limitations. To address theseproblems, we introduce a multi-task network named EM-Net, which includes anauxiliary centerline detection task to account for shape information ofmitochondria represented by centerline. Therefore, the centerline detectionsub-network is able to enhance the accuracy and robustness of segmentationtask, especially when only a small set of annotated data are available. Toachieve a light-weight 3D network, we introduce a novel hierarchicalview-ensemble convolution module to reduce number of parameters, and facilitatemulti-view information aggregation.Validations on public benchmark showedstate-of-the-art performance by EM-Net. Even with significantly reducedtraining data, our method still showed quite promising results.

EM-NET: Centerline-Aware Mitochondria Segmentation in EM Images via Hierarchical View-Ensemble Convolutional Network