Bone visualization of the cervical spine with deep learning-based synthetic CT compared to conventional CT: A single-center noninferiority study on image quality. Issue 154 (September 2022)

• Record Type: Journal Article
• Authors: van der Kolk, Brigitta (Britt) Y.M.; Slotman, Derk J. (Jorik); Nijholt, Ingrid M.; van Osch, Jochen A.C.; Snoeijink, Tess J.; Podlogar, Martin; van Hasselt, Boudewijn A.A.M.; Boelhouwers, Henk J.; van Stralen, Marijn; Seevinck, Peter R.; Schep, Niels W.L.; Maas, Mario; Boomsma, Martijn F.
• Is Part Of: European journal of radiology. Issue 154(2022)
• Publication Date: 2022-09
• Subjects: Cervical spine -- Deep learning -- Synthetic CT -- Magnetic Resonance Imaging -- Image quality -- Artificial intelligence; CI confidence interval -- DL deep learning -- DSC dice similarity coefficient -- ICC intraclass correlation coefficient -- MAE mean absolute error -- SSIM structural similarity index -- sCT synthetic CT -- T1w-MGE T1-weighted multiple gradient-echo; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2022.110414
• Languages: English
• ISSNs: 0720-048X

Abstract

Highlights: sCT was noninferior to CT for general visualization of cervical spine structures. Noninferiority was also demonstrated in most detailed structure assessments. Acceptable image quality of the sCT was found in 93.3% of the scans. Geometrical analysis of the sCT showed good to excellent agreement with CT. sCT provides optimal visualization of soft and bony structures in a single MRI exam. Abstract: Purpose: To investigate whether the image quality of a specific deep learning-based synthetic CT (sCT) of the cervical spine is noninferior to conventional CT. Method: 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 point on this scale. Additionally, acceptable image quality was defined as a score of 3–4 in ≥ 80% of the scans. Quantitative assessment included geometrical analysis and voxelwise comparisons. Results: Qualitative image assessment showed that sCT was noninferior 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 level 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). Conclusions: 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.