Spinal fusion is a common procedure to stabilize the spinal column by fixating parts of the spine. In such procedures,
metal screws are inserted through the patients back into a vertebra, and the screws of adjacent vertebrae are connected by
metal rods to generate a fixed bridge. In these procedures, 3D image guidance for intervention planning and outcome
control is required. Here, for anatomical guidance, an automated approach for vertebra segmentation from C-arm CT
images of the spine is introduced and evaluated.
As a prerequisite, 3D C-arm CT images are acquired covering the vertebrae of interest. An automatic model-based
segmentation approach is applied to delineate the outline of the vertebrae of interest. The segmentation approach is based
on 24 partial models of the cervical, thoracic and lumbar vertebrae which aggregate information about (i) the basic shape
itself, (ii) trained features for image based adaptation, and (iii) potential shape variations. Since the volume data sets
generated by the C-arm system are limited to a certain region of the spine the target vertebra and hence initial model
position is assigned interactively.
The approach was trained and tested on 21 human cadaver scans. A 3-fold cross validation to ground truth annotations
yields overall mean segmentation errors of 0.5 mm for T1 to 1.1 mm for C6. The results are promising and show
potential to support the clinician in pedicle screw path and rod planning to allow accurate and reproducible insertions.