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

Positron emission tomography (PET) is the most sensitive molecular imagingmodality routinely applied in our modern healthcare. High radioactivity causedby the injected tracer dose is a major concern in PET imaging and limits itsclinical applications. However, reducing the dose leads to inadequate imagequality for diagnostic practice. Motivated by the need to produce high qualityimages with minimum low-dose, Convolutional Neural Networks (CNNs) basedmethods have been developed for high quality PET synthesis from its low-dosecounterparts. Previous CNNs-based studies usually directly map low-dose PETinto features space without consideration of different dose reduction level. Inthis study, a novel approach named CG-3DSRGAN (Classification-Guided GenerativeAdversarial Network with Super Resolution Refinement) is presented.Specifically, a multi-tasking coarse generator, guided by a classificationhead, allows for a more comprehensive understanding of the noise-level featurespresent in the low-dose data, resulting in improved image synthesis. Moreover,to recover spatial details of standard PET, an auxiliary super resolutionnetwork - Contextual-Net - is proposed as a second-stage training to narrow thegap between coarse prediction and standard PET. We compared our method to thestate-of-the-art methods on whole-body PET with different dose reductionfactors (DRFs). Experiments demonstrate our method can outperform others on allDRF.

CG-3DSRGAN: A classification guided 3D generative adversarial network for image quality recovery from low-dose PET images