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

Automated medical image segmentation, specifically using deep learning, hasshown outstanding performance in semantic segmentation tasks. However, thesemethods rarely quantify their uncertainty, which may lead to errors indownstream analysis. In this work we propose to use Bayesian neural networks toquantify uncertainty within the domain of semantic segmentation. We alsopropose a method to convert voxel-wise segmentation uncertainty into volumetricuncertainty, and calibrate the accuracy and reliability of confidence intervalsof derived measurements. When applied to a tumour volume estimationapplication, we demonstrate that by using such modelling of uncertainty, deeplearning systems can be made to report volume estimates with well-calibratederror-bars, making them safer for clinical use. We also show that theuncertainty estimates extrapolate to unseen data, and that the confidenceintervals are robust in the presence of artificial noise. This could be used toprovide a form of quality control and quality assurance, and may permit furtheradoption of deep learning tools in the clinic.

Towards safe deep learning: accurately quantifying biomarker uncertainty in neural network predictions