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

The application of deep learning models to large-scale data sets requiresmeans for automatic quality assurance. We have previously developed a fullyautomatic algorithm for carotid artery wall segmentation in black-blood MRIthat we aim to apply to large-scale data sets. This method identifies nestedartery walls in 3D patches centered on the carotid artery. In this study, weinvestigate to what extent the uncertainty in the model predictions for thecontour location can serve as a surrogate for error detection and,consequently, automatic quality assurance. We express the quality of automaticsegmentations using the Dice similarity coefficient. The uncertainty in themodel's prediction is estimated using either Monte Carlo dropout or test-timedata augmentation. We found that (1) including uncertainty measurements did notdegrade the quality of the segmentations, (2) uncertainty metrics provide agood proxy of the quality of our contours if the center found during the firststep is enclosed in the lumen of the carotid artery and (3) they could be usedto detect low-quality segmentations at the participant level. This automaticquality assurance tool might enable the application of our model in large-scaledata sets.

Uncertainty-based quality assurance of carotid artery wall segmentation in black-blood MRI