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

Identifying image features that are robust with respect to segmentationvariability and domain shift is a tough challenge in radiomics. So far, thisproblem has mainly been tackled in test-retest analyses. In this work weanalyze radiomics feature stability based on probabilistic segmentations. Basedon a public lung cancer dataset, we generate an arbitrary number of plausiblesegmentations using a Probabilistic U-Net. From these segmentations, we extracta high number of plausible feature vectors for each lung tumor and analyzefeature variance with respect to the segmentations. Our results suggest thatthere are groups of radiomic features that are more (e.g. statistics features)and less (e.g. gray-level size zone matrix features) robust againstsegmentation variability. Finally, we demonstrate that segmentation varianceimpacts the performance of a prognostic lung cancer survival model and proposea new and potentially more robust radiomics feature selection workflow.

Radiomic Feature Stability Analysis based on Probabilistic Segmentations