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

Machine learning applications in medical imaging are frequently limited bythe lack of quality labeled data. In this paper, we explore the self trainingmethod, a form of semi-supervised learning, to address the labeling burden. Byintegrating reinforcement learning, we were able to expand the application ofself training to complex segmentation networks without any further humanannotation. The proposed approach, reinforced self training (ReST), fine tunesa semantic segmentation networks by introducing a policy network that learns togenerate pseudolabels. We incorporate an expert demonstration network, based oninverse reinforcement learning, to enhance clinical validity and convergence ofthe policy network. The model was tested on a pulmonary nodule segmentationtask in chest X-rays and achieved the performance of a standard U-Net whileusing only 50% of the labeled data, by exploiting unlabeled data. When the samenumber of labeled data was used, a moderate to significant cross validationaccuracy improvement was achieved depending on the absolute number of labelsused.

Integrating Reinforcement Learning to Self Training for Pulmonary Nodule Segmentation in Chest X-rays