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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Purpose: The localisation and segmentation of individual bones is animportant preprocessing step in many planning and navigation applications. Itis, however, a time-consuming and repetitive task if done manually. This istrue not only for clinical practice but also for the acquisition of trainingdata. We therefore not only present an end-to-end learnt algorithm that iscapable of segmenting 125 distinct bones in an upper-body CT, but also providean ensemble-based uncertainty measure that helps to single out scans to enlargethe training dataset with. Methods We create fully automated end-to-end learntsegmentations using a neural network architecture inspired by the 3D-Unet andfully supervised training. The results are improved using ensembles andinference-time augmentation. We examine the relationship ofensemble-uncertainty to an unlabelled scan's prospective usefulness as part ofthe training dataset. Results: Our methods are evaluated on an in-house datasetof 16 upper-body CT scans with a resolution of \SI{2}{\milli\meter} perdimension. Taking into account all 125 bones in our label set, our mostsuccessful ensemble achieves a median dice score coefficient of 0.83. We find alack of correlation between a scan's ensemble uncertainty and its prospectiveinfluence on the accuracies achieved within an enlarged training set. At thesame time, we show that the ensemble uncertainty correlates to the number ofvoxels that need manual correction after an initial automated segmentation,thus minimising the time required to finalise a new ground truth segmentation.Conclusion: In combination, scans with low ensemble uncertainty need lessannotator time while yielding similar future DSC improvements. They are thusideal candidates to enlarge a training set for upper-body distinct bonesegmentation from CT scans. }

Ensemble uncertainty as a criterion for dataset expansion in distinct bone segmentation from upper-body CT images