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

Prostate cancer (PCa) is one of the leading causes of death for menworldwide. Multi-parametric magnetic resonance (mpMR) imaging has emerged as anon-invasive diagnostic tool for detecting and localising prostate tumours byspecialised radiologists. These radiological examinations, for example, fordifferentiating malignant lesions from benign prostatic hyperplasia intransition zones and for defining the boundaries of clinically significantcancer, remain challenging and highly skill-and-experience-dependent. We firstinvestigate experimental results in developing object detection neural networksthat are trained to predict the radiological assessment, using thesehigh-variance labels. We further argue that such a computer-assisted diagnosis(CAD) system needs to have the ability to control the false-positive rate (FPR)or false-negative rate (FNR), in order to be usefully deployed in a clinicalworkflow, informing clinical decisions without further human intervention. Thiswork proposes a novel PCa detection network that incorporates a lesion-levelcost-sensitive loss and an additional slice-level loss based on alesion-to-slice mapping function, to manage the lesion- and slice-level costs,respectively. Our experiments based on 290 clinical patients concludes that 1)The lesion-level FNR was effectively reduced from 0.19 to 0.10 and thelesion-level FPR was reduced from 1.03 to 0.66 by changing the lesion-levelcost; 2) The slice-level FNR was reduced from 0.19 to 0.00 by taking intoaccount the slice-level cost; (3) Both lesion-level and slice-level FNRs werereduced with lower FP/FPR by changing the lesion-level or slice-level costs,compared with post-training threshold adjustment using networks without theproposed cost-aware training.

Controlling False Positive/Negative Rates for Deep-Learning-Based Prostate Cancer Detection on Multiparametric MR images