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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Tumor segmentation in oncological PET is challenging, a major reason beingthe partial-volume effects that arise due to low system resolution and finitevoxel size. The latter results in tissue-fraction effects, i.e. voxels containa mixture of tissue classes. Conventional segmentation methods are typicallydesigned to assign each voxel in the image as belonging to a certain tissueclass. Thus, these methods are inherently limited in modeling tissue-fractioneffects. To address the challenge of accounting for partial-volume effects, andin particular, tissue-fraction effects, we propose a Bayesian approach totissue-fraction estimation for oncological PET segmentation. Specifically, thisBayesian approach estimates the posterior mean of fractional volume that thetumor occupies within each voxel of the image. The proposed method, implementedusing a deep-learning-based technique, was first evaluated using clinicallyrealistic 2-D simulation studies with known ground truth, in the context ofsegmenting the primary tumor in PET images of patients with lung cancer. Theevaluation studies demonstrated that the method accurately estimated thetumor-fraction areas and significantly outperformed widely used conventionalPET segmentation methods, including a U-net-based method, on the task ofsegmenting the tumor. In addition, the proposed method was relativelyinsensitive to partial-volume effects and yielded reliable tumor segmentationfor different clinical-scanner configurations. The method was then evaluatedusing clinical images of patients with stage IIB/III non-small cell lung cancerfrom ACRIN 6668/RTOG 0235 multi-center clinical trial. Here, the results showedthat the proposed method significantly outperformed all other consideredmethods and yielded accurate tumor segmentation on patient images with Dicesimilarity coefficient (DSC) of 0.82 (95 % CI: [0.78, 0.86]).

A Bayesian approach to tissue-fraction estimation for oncological PET segmentation