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

While supervised learning has achieved remarkable success, obtaininglarge-scale labeled datasets in biomedical imaging is often impractical due tohigh costs and the time-consuming annotations required from radiologists.Semi-supervised learning emerges as an effective strategy to overcome thislimitation by leveraging useful information from unlabeled datasets. In thispaper, we present a novel semi-supervised learning method, Dual-DecoderConsistency via Pseudo-Labels Guided Data Augmentation (DCPA), for medicalimage segmentation. We devise a consistency regularization to promoteconsistent representations during the training process. Specifically, we usedistinct decoders for student and teacher networks while maintain the sameencoder. Moreover, to learn from unlabeled data, we create pseudo-labelsgenerated by the teacher networks and augment the training data with thepseudo-labels. Both techniques contribute to enhancing the performance of theproposed method. The method is evaluated on three representative medical imagesegmentation datasets. Comprehensive comparisons with state-of-the-artsemi-supervised medical image segmentation methods were conducted under typicalscenarios, utilizing 10% and 20% labeled data, as well as in the extremescenario of only 5% labeled data. The experimental results consistentlydemonstrate the superior performance of our method compared to other methodsacross the three semi-supervised settings. The source code is publiclyavailable at https://github.com/BinYCn/DCPA.git.

Dual-Decoder Consistency via Pseudo-Labels Guided Data Augmentation for Semi-Supervised Medical Image Segmentation