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

We hypothesize that anatomical priors can be viable mediums to infusedomain-specific clinical knowledge into state-of-the-art convolutional neuralnetworks (CNN) based on the U-Net architecture. We introduce a probabilisticpopulation prior which captures the spatial prevalence and zonal distinction ofclinically significant prostate cancer (csPCa), in order to improve itscomputer-aided detection (CAD) in bi-parametric MR imaging (bpMRI). To evaluateperformance, we train 3D adaptations of the U-Net, U-SEResNet, UNet++ andAttention U-Net using 800 institutional training-validation scans, paired withradiologically-estimated annotations and our computed prior. For 200independent testing bpMRI scans with histologically-confirmed delineations ofcsPCa, our proposed method of encoding clinical priori demonstrates a strongability to improve patient-based diagnosis (upto 8.70% increase in AUROC) andlesion-level detection (average increase of 1.08 pAUC between 0.1-10 falsepositives per patient) across all four architectures.

Encoding Clinical Priori in 3D Convolutional Neural Networks for Prostate Cancer Detection in bpMRI