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

The RefleXion X1 is the first biology-guided radiotherapy (BgRT) system. Itsdual 90-degree PET detector collects fewer pair production events compared to afull-ring diagnostic PET system. In the proposed BgRT workflow, a short scan isacquired before treatment delivery to ensure image quality and consistency. Theshorter scan time, a quarter of the simulation scan time, also leads to fewercoincidence events and hence reduced image quality. In this study, we proposeda patient-specific mean teacher UNet (MT-UNet) to enhance PET image quality andlow-dose PET reconstruction on RefleXion X1. PET/CT scans of nine cancerpatients were acquired using RefleXion X1. Every patient had one simulationscan. Five patients had additional scans acquired during the first and thefinal treatment fractions. Treatment scans were acquired using the same imagingprotocol as the simulation scan. For each scan, we reconstructed a full-doseimage and evenly split coincidence events into four sessions to reconstructfour quarter-dose PET images. For each patient, our proposed MT-UNet wastrained using quarter-dose and full-dose images of the simulation scan. For theimage quality enhancement task, we applied nine trained MT-UNets to full-dosesimulation PET images of the nine patients to generate enhanced images,respectively. The enhanced images were compared with the original full-doseimages using CNR and SNR. For the low-dose image reconstruction task, weapplied five trained MT-UNets to ten quarter-dose treatment images of fivepatients to predict full-dose images, respectively. The predicted and groundtruth full-dose images were compared using SSIM and PSNR. We also trained andevaluated patient-specific UNets for model comparison. Our proposedpatient-specific MT-UNet achieved better performance in improving the qualityof RefleXion low-dose and full-dose images compared to the patient-specificUNet.

Patient-specific mean teacher UNet for enhancing PET image and low-dose PET reconstruction on RefleXion X1 biology-guided radiotherapy system