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

Patient motion during PET is inevitable. Its long acquisition time not onlyincreases the motion and the associated artifacts but also the patient'sdiscomfort, thus PET acceleration is desirable. However, accelerating PETacquisition will result in reconstructed images with low SNR, and the imagequality will still be degraded by motion-induced artifacts. Most of theprevious PET motion correction methods are motion type specific that requiremotion modeling, thus may fail when multiple types of motion present together.Also, those methods are customized for standard long acquisition and could notbe directly applied to accelerated PET. To this end, modeling-free universalmotion correction reconstruction for accelerated PET is still highlyunder-explored. In this work, we propose a novel deep learning-aided motioncorrection and reconstruction framework for accelerated PET, calledFast-MC-PET. Our framework consists of a universal motion correction (UMC) anda short-to-long acquisition reconstruction (SL-Reon) module. The UMC enablesmodeling-free motion correction by estimating quasi-continuous motion fromultra-short frame reconstructions and using this information formotion-compensated reconstruction. Then, the SL-Recon converts the acceleratedUMC image with low counts to a high-quality image with high counts for ourfinal reconstruction output. Our experimental results on human studies showthat our Fast-MC-PET can enable 7-fold acceleration and use only 2 minutesacquisition to generate high-quality reconstruction images thatoutperform/match previous motion correction reconstruction methods usingstandard 15 minutes long acquisition data.

Fast-MC-PET: A Novel Deep Learning-aided Motion Correction and Reconstruction Framework for Accelerated PET