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

Automatic segmentation of ground glass opacities and consolidations in chestcomputer tomography (CT) scans can potentially ease the burden of radiologistsduring times of high resource utilisation. However, deep learning models arenot trusted in the clinical routine due to failing silently onout-of-distribution (OOD) data. We propose a lightweight OOD detection methodthat leverages the Mahalanobis distance in the feature space and seamlesslyintegrates into state-of-the-art segmentation pipelines. The simple approachcan even augment pre-trained models with clinically relevant uncertaintyquantification. We validate our method across four chest CT distribution shiftsand two magnetic resonance imaging applications, namely segmentation of thehippocampus and the prostate. Our results show that the proposed methodeffectively detects far- and near-OOD samples across all explored scenarios.

Distance-based detection of out-of-distribution silent failures for Covid-19 lung lesion segmentation