Augmented-reality surgical system using depth sensing

A head-mounted system for image-guided surgery, comprising:

• a head-mounted unit, comprising a see-through augmented-reality display and a depth sensor, which is configured to generate depth data with respect to a region of interest (ROI) of a body of a patient that is viewed through the display by a user wearing the head-mounted unit;
• and
• a processor, which is configured to:
• receive a three-dimensional (3D) tomographic image of the body of the patient;
• compute a depth map of the ROI based on the depth data generated by the depth sensor;
• compute a transformation over the ROI so as to register the tomographic image with the depth map;
• and
• apply the transformation in presenting a part of the tomographic image on the display in registration with the ROI viewed through the display,
• wherein the depth map includes a spine of the patient, which is exposed in a surgical procedure,
• wherein the processor is configured to compute the transformation by registering the spine in the depth map with the spine appearing in the tomographic image,
• wherein the tomographic image comprises a CT scan of the patient which was performed with an array of radiopaque fiducial markers fixed to the body of the patient, and
• wherein the processor is configured to identify respective 3D coordinates of the fiducial markers in the depth map and to register the CT scan with the ROI viewed through the display by matching the fiducial markers in the CT to the respective 3D coordinates.