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

Image segmentation is a fundamental problem in medical image analysis. Inrecent years, deep neural networks achieve impressive performances on manymedical image segmentation tasks by supervised learning on large manuallyannotated data. However, expert annotations on big medical datasets aretedious, expensive or sometimes unavailable. Weakly supervised learning couldreduce the effort for annotation but still required certain amounts ofexpertise. Recently, deep learning shows a potential to produce more accuratepredictions than the original erroneous labels. Inspired by this, we introducea very weakly supervised learning method, for cystic lesion detection andsegmentation in lung CT images, without any manual annotation. Our method worksin a self-learning manner, where segmentation generated in previous steps(first by unsupervised segmentation then by neural networks) is used as groundtruth for the next level of network learning. Experiments on a cystic lunglesion dataset show that the deep learning could perform better than theinitial unsupervised annotation, and progressively improve itself afterself-learning.

Self-Learning to Detect and Segment Cysts in Lung CT Images without Manual Annotation