Synthetic CT

A synthetic or pseudo CT image is basically a CT image generated through an MR image instead of using a CT scanner to scan one from scratch. Generating synthetic CT from MR is a simple idea but it requires solving a complex problem that air and bone look almost the same in an MR image.

van der Kolk et al. investigated whether the image quality of a specific deep learning-based synthetic CT (sCT) of the cervical spine is non-inferior to conventional CT.

Paired MRI and CT data were collected from 25 consecutive participants (≥ 50 years) with cervical radiculopathy. The MRI exam included a T1-weighted multiple gradient echo sequence for sCT reconstruction. For qualitative image assessment, four structures at two vertebral levels were evaluated on sCT and compared with CT by three assessors using a four-point scale (range 1-4). The noninferiority margin was set at 0.5 points on this scale. Additionally, acceptable image quality was defined as a score of 3-4 in ≥ 80% of the scans. The quantitative assessment included geometrical analysis and voxelwise comparisons.

Qualitative image assessment showed that sCT was non-inferior to CT for overall bone image quality, artifacts, imaging of intervertebral joints and neural foramina at levels C3-C4 and C6-C7, and cortical delineation at C6-C7. Noninferiority was weak to absent for cortical delineation at levels C3-C4 and trabecular bone at both levels. Acceptable image quality was achieved for all structures in sCT and CT, except for trabecular bone in sCT and level C6-C7 in CT. Geometrical analysis of the sCT showed good to excellent agreement with CT. Voxelwise comparisons showed a mean absolute error of 80.05 (±6.12) HU, dice similarity coefficient (cortical bone) of 0.84 (±0.04) and structural similarity index of 0.86 (±0.02).

This deep learning-based sCT was noninferior to conventional CT for the general visualization of bony structures of the cervical spine, artifacts, and most detailed structure assessments ¹⁾.