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

Cardiovascular disease (CVD) is the leading cause of death worldwide, andmyocardial perfusion imaging using SPECT has been widely used in the diagnosisof CVDs. The GE 530/570c dedicated cardiac SPECT scanners adopt a stationarygeometry to simultaneously acquire 19 projections to increase sensitivity andachieve dynamic imaging. However, the limited amount of angular samplingnegatively affects image quality. Deep learning methods can be implemented toproduce higher-quality images from stationary data. This is essentially afew-view imaging problem. In this work, we propose a novel 3D transformer-baseddual-domain network, called TIP-Net, for high-quality 3D cardiac SPECT imagereconstructions. Our method aims to first reconstruct 3D cardiac SPECT imagesdirectly from projection data without the iterative reconstruction process byproposing a customized projection-to-image domain transformer. Then, given itsreconstruction output and the original few-view reconstruction, we furtherrefine the reconstruction using an image-domain reconstruction network.Validated by cardiac catheterization images, diagnostic interpretations fromnuclear cardiologists, and defect size quantified by an FDA 510(k)-clearedclinical software, our method produced images with higher cardiac defectcontrast on human studies compared with previous baseline methods, potentiallyenabling high-quality defect visualization using stationary few-view dedicatedcardiac SPECT scanners.

Transformer-based Dual-domain Network for Few-view Dedicated Cardiac SPECT Image Reconstructions