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

Precise segmentation of organs and tumors plays a crucial role in clinicalapplications. It is a challenging task due to the irregular shapes and varioussizes of organs and tumors as well as the significant class imbalance betweenthe anatomy of interest (AOI) and the background region. In addition, in mostsituation tumors and normal organs often overlap in medical images, but currentapproaches fail to delineate both tumors and organs accurately. To tackle suchchallenges, we propose a position-guided deformable UNet, namely PGD-UNet,which exploits the spatial deformation capabilities of deformable convolutionto deal with the geometric transformation of both organs and tumors. Positioninformation is explicitly encoded into the network to enhance the capabilitiesof deformation. Meanwhile, we introduce a new pooling module to preserveposition information lost in conventional max-pooling operation. Besides, dueto unclear boundaries between different structures as well as the subjectivityof annotations, labels are not necessarily accurate for medical imagesegmentation tasks. It may cause the overfitting of the trained network due tolabel noise. To address this issue, we formulate a novel loss function tosuppress the influence of potential label noise on the training process. Ourmethod was evaluated on two challenging segmentation tasks and achieved verypromising segmentation accuracy in both tasks.

PGD-UNet: A Position-Guided Deformable Network for Simultaneous Segmentation of Organs and Tumors