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

Background: In MR-guided proton therapy planning, aligning MR and CT imagesis key for MR-based CT synthesis, especially in mobile regions like thehead-and-neck. Misalignments here can lead to less accurate synthetic CT (sCT)images, impacting treatment precision. Purpose: This study introduces a novelnetwork that cohesively unifies image generation and registration processes toenhance the quality and anatomical fidelity of sCTs derived from better-alignedMR images. Methods: The approach synergizes a generation network (G) with adeformable registration network (R), optimizing them jointly in MR-to-CTsynthesis. This goal is achieved by alternately minimizing the discrepanciesbetween the generated/registered CT images and their corresponding reference CTcounterparts. The generation network employs a UNet architecture, while theregistration network leverages an implicit neural representation of theDeformable Vector Fields (DVFs). We validated this method on a datasetcomprising 60 Head-and-Neck patients, reserving 12 cases for holdout testing.Results: Compared to the baseline Pix2Pix method with MAE 124.95\pm 30.74 HU,the proposed technique demonstrated 80.98\pm 7.55 HU. The unifiedtranslation-registration network produced sharper and more anatomicallycongruent outputs, showing superior efficacy in converting MR images to sCTs.Additionally, from a dosimetric perspective, the plan recalculated on theresulting sCTs resulted in a remarkably reduced discrepancy to the referenceproton plans. Conclusions: This study conclusively demonstrates that a holisticMR-based CT synthesis approach, integrating both image-to-image translation anddeformable registration, significantly improves the precision and quality ofsCT generation, particularly for the challenging body area with varied anatomicchanges between corresponding MR and CT.

A Unified Generation-Registration Framework for Improved MR-based CT Synthesis in Proton Therapy