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/

Zendy Plus

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

Zendy Tools

Zendy Open

Improving a semi-supervised image segmentation task has the option of addingmore unlabelled images, labelling the unlabelled images or combining both, asneither image acquisition nor expert labelling can be considered trivial inmost clinical applications. With a laparoscopic liver image segmentationapplication, we investigate the performance impact by altering the quantitiesof labelled and unlabelled training data, using a semi-supervised segmentationalgorithm based on the mean teacher learning paradigm. We first report asignificantly higher segmentation accuracy, compared with supervised learning.Interestingly, this comparison reveals that the training strategy adopted inthe semi-supervised algorithm is also responsible for this observedimprovement, in addition to the added unlabelled data. We then comparedifferent combinations of labelled and unlabelled data set sizes for trainingsemi-supervised segmentation networks, to provide a quantitative example of thepractically useful trade-off between the two data planning strategies in thissurgical guidance application.

More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation