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

Uncertainty quantification in medical images has become an essential additionto segmentation models for practical application in the real world. Althoughthere are valuable developments in accurate uncertainty quantification methodsusing 2D images and slices of 3D volumes, in clinical practice, the complete 3Dvolumes (such as CT and MRI scans) are used to evaluate and plan the medicalprocedure. As a result, the existing 2D methods miss the rich 3D spatialinformation when resolving the uncertainty. A popular approach for quantifyingthe ambiguity in the data is to learn a distribution over the possiblehypotheses. In recent work, this ambiguity has been modeled to be strictlyGaussian. Normalizing Flows (NFs) are capable of modelling more complexdistributions and thus, better fit the embedding space of the data. To thisend, we have developed a 3D probabilistic segmentation framework augmented withNFs, to enable capturing the distributions of various complexity. To test theproposed approach, we evaluate the model on the LIDC-IDRI dataset for lungnodule segmentation and quantify the aleatoric uncertainty introduced by themulti-annotator setting and inherent ambiguity in the CT data. Following thisapproach, we are the first to present a 3D Squared Generalized Energy Distance(GED) of 0.401 and a high 0.468 Hungarian-matched 3D IoU. The obtained resultsreveal the value in capturing the 3D uncertainty, using a flexible posteriordistribution augmented with a Normalizing Flow. Finally, we present thealeatoric uncertainty in a visual manner with the aim to provide clinicianswith additional insight into data ambiguity and facilitating more informeddecision-making.

Probabilistic 3D segmentation for aleatoric uncertainty quantification in full 3D medical data