Feature-based multimodal registration framework for vertebral pose estimation.

Purpose: The reliable estimation of the vertebral body posture helps to aid a safe and effective spine surgery. The proposed work aims to present an MR to X-ray image registration to assess the 3D pose of the vertebral body during spine surgery. The 3D assessment of vertebral pose assists in analyzing the position and orientation of the vertebral body to provide information during various clinical diagnosis conditions such as curvature estimation and pedicle screw insertion surgery.

Methods: The proposed feature-based registration framework extracted vertebral end plates to avoid the mismatch between the intensities of MR and X-ray images. Using the projection matrix, the segmented MRI is forward projected and then registered to the X-ray image using binary image matching similarity and the CMA-ES optimizer.

Results: The proposed method estimated the vertebral pose by registering the simulated X-ray onto pre-operative MRI. To evaluate the efficacy of the proposed approach, a certain number of experiments are carried out on the simulated dataset.

Conclusion: The proposed method is a fast and accurate registration method that can provide 3D information about the vertebral body. This 3D information is useful to improve accuracy during various clinical diagnoses.