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

Vertebral bone segmentation from magnetic resonance (MR) images is achallenging task. Due to the inherent nature of the modality to emphasize softtissues of the body, common thresholding algorithms are ineffective indetecting bones in MR images. On the other hand, it is relatively easier tosegment bones from CT images because of the high contrast between bones and thesurrounding regions. For this reason, we perform a cross-modality synthesisbetween MR and CT domains for simple thresholding-based segmentation of thevertebral bones. However, this implicitly assumes the availability of pairedMR-CT data, which is rare, especially in the case of scoliotic patients. Inthis paper, we present a completely unsupervised, fully three-dimensional (3D)cross-modality synthesis method for segmenting scoliotic spines. A 3D CycleGANmodel is trained for an unpaired volume-to-volume translation across MR and CTdomains. Then, the Otsu thresholding algorithm is applied to the synthesized CTvolumes for easy segmentation of the vertebral bones. The resultingsegmentation is used to reconstruct a 3D model of the spine. We validate ourmethod on 28 scoliotic vertebrae in 3 patients by computing thepoint-to-surface mean distance between the landmark points for each vertebraobtained from pre-operative X-rays and the surface of the segmented vertebra.Our study results in a mean error of 3.41 $\pm$ 1.06 mm. Based on qualitativeand quantitative results, we conclude that our method is able to obtain a goodsegmentation and 3D reconstruction of scoliotic spines, all after training fromunpaired data in an unsupervised manner.

Three-dimensional Segmentation of the Scoliotic Spine from MRI using Unsupervised Volume-based MR-CT Synthesis