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 ability of deep learning to predict with uncertainty is recognized as keyfor its adoption in clinical routines. Moreover, performance gain has beenenabled by modelling uncertainty according to empirical evidence. Whileprevious work has widely discussed the uncertainty estimation in segmentationand classification tasks, its application on bounding-box-based detection hasbeen limited, mainly due to the challenge of bounding box aligning. In thiswork, we explore to augment a 2.5D detection CNN with two differentbounding-box-level (or instance-level) uncertainty estimates, i.e., predictivevariance and Monte Carlo (MC) sample variance. Experiments are conducted forlung nodule detection on LUNA16 dataset, a task where significant semanticambiguities can exist between nodules and non-nodules. Results show that ourmethod improves the evaluating score from 84.57% to 88.86% by utilizing acombination of both types of variances. Moreover, we show the generateduncertainty enables superior operating points compared to using the probabilitythreshold only, and can further boost the performance to 89.52%. Example noduledetections are visualized to further illustrate the advantages of our method.

Exploring Instance-Level Uncertainty for Medical Detection