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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Background: Automated segmentation of spinal MR images plays a vital roleboth scientifically and clinically. However, accurately delineating posteriorspine structures presents challenges.  Methods: This retrospective study, approved by the ethical committee,involved translating T1w and T2w MR image series into CT images in a total ofn=263 pairs of CT/MR series. Landmark-based registration was performed to alignimage pairs. We compared 2D paired (Pix2Pix, denoising diffusion implicitmodels (DDIM) image mode, DDIM noise mode) and unpaired (contrastive unpairedtranslation, SynDiff) image-to-image translation using "peak signal to noiseratio" (PSNR) as quality measure. A publicly available segmentation networksegmented the synthesized CT datasets, and Dice scores were evaluated onin-house test sets and the "MRSpineSeg Challenge" volumes. The 2D findings wereextended to 3D Pix2Pix and DDIM.  Results: 2D paired methods and SynDiff exhibited similar translationperformance and Dice scores on paired data. DDIM image mode achieved thehighest image quality. SynDiff, Pix2Pix, and DDIM image mode demonstratedsimilar Dice scores (0.77). For craniocaudal axis rotations, at least twolandmarks per vertebra were required for registration. The 3D translationoutperformed the 2D approach, resulting in improved Dice scores (0.80) andanatomically accurate segmentations in a higher resolution than the original MRimage.  Conclusion: Two landmarks per vertebra registration enabled pairedimage-to-image translation from MR to CT and outperformed all unpairedapproaches. The 3D techniques provided anatomically correct segmentations,avoiding underprediction of small structures like the spinous process.

Denoising diffusion-based MRI to CT image translation enables automated spinal segmentation