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/

Zendy Plus

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

Zendy Tools

Zendy Open

Combining dual-energy computed tomography (DECT) with positron emissiontomography (PET) offers many potential clinical applications but typicallyrequires expensive hardware upgrades or increases radiation doses on PET/CTscanners due to an extra X-ray CT scan. The recent PET-enabled DECT methodallows DECT imaging on PET/CT without requiring a second X-ray CT scan. Itcombines the already existing X-ray CT image with a 511 keV \gamma-ray CT (gCT)image reconstructed from time-of-flight PET emission data. A kernelizedframework has been developed for reconstructing gCT image but this method hasnot fully exploited the potential of prior knowledge. Use of deep neuralnetworks may explore the power of deep learning in this application. However,common approaches require a large database for training, which is impracticalfor a new imaging method like PET-enabled DECT. Here, we propose asingle-subject method by using neural-network representation as a deepcoefficient prior to improving gCT image reconstruction withoutpopulation-based pre-training. The resulting optimization problem becomes thetomographic estimation of nonlinear neural-network parameters from gCTprojection data. This complicated problem can be efficiently solved byutilizing the optimization transfer strategy with quadratic surrogates. Eachiteration of the proposed neural optimization transfer algorithm includes: PETactivity image update; gCT image update; and least-square neural-networklearning in the gCT image domain. This algorithm is guaranteed to monotonicallyincrease the data likelihood. Results from computer simulation, real phantomdata and real patient data have demonstrated that the proposed method cansignificantly improve gCT image quality and consequent multi-materialdecomposition as compared to other methods.

Single-Subject Deep-Learning Image Reconstruction with a Neural Optimization Transfer Algorithm for PET-enabled Dual-Energy CT Imaging