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

Medical image segmentation based on deep learning is often faced with theproblems of insufficient datasets and long time-consuming labeling. In thispaper, we introduce the self-supervised method MAE(Masked Autoencoders) intoknee joint images to provide a good initial weight for the segmentation modeland improve the adaptability of the model to small datasets. Secondly, wepropose a weakly supervised paradigm for meniscus segmentation based on thecombination of point and line to reduce the time of labeling. Based on the weaklabel ,we design a region growing algorithm to generate pseudo-label. Finallywe train the segmentation network based on pseudo-labels with weight transferfrom self-supervision. Sufficient experimental results show that our proposedmethod combining self-supervision and weak supervision can almost approach theperformance of purely fully supervised models while greatly reducing therequired labeling time and dataset size.

Automatic segmentation of meniscus based on MAE self-supervision and point-line weak supervision paradigm