Fast 3D-2D image registration method with application to continuously guided endoscopy
View Patent ↗Fast and continuous registration between two imaging modalities makes it possible to completely determine the rigid transformation between multiple sources at real-time or near real-time frame-rates in order to localize video cameras and register the two sources. A set of reference images are computed or captured within a known environment, with corresponding depth maps and image gradients defining a reference source. Given one frame from a real-time or near-real time video feed, and starting from an initial guess of viewpoint, a real-time video frame is warped to the nearest viewing site of the reference source. An image difference is computed between the warped video frame and the reference image. Steps are repeated for each frame until the viewpoint converges or the next video frame becomes available. The final viewpoint gives an estimate of the relative rotation and translation between the camera at that particular video frame and the reference source.
1. A real time method of registering video frames of a body lumen received from an endoscope inserted into the body lumen during a medical procedure to previously acquired images of the body lumen, the method comprising the steps of:
computing, in advance, a plurality of virtual reference images of a body lumen, each reference image being computed from three-dimensional image data and including a viewpoint with a depth map and image gradients;
receiving video frames associated with a body lumen from an endoscope; and
registering, in real time, each video frame received from the endoscope to at least one of the reference images using its depth map and image gradients.
2. The method of claim 1 , wherein real-time registration step further includes the steps of:
a) warping the video frame to the viewpoint of one reference image of the plurality of reference images or warping one reference image of the plurality of reference images at a viewpoint to the video frame;
b) automatically computing an image difference between (i) the warped video frame and the reference image, or (ii) the warped reference image and the video frame;
c) updating a viewpoint of the video frame using an optimization technique; and
d) repeating steps a) through c) for each video frame until the viewpoint of the video frame converges on a final viewpoint or a next video frame becomes available.
3. The method of claim 1 , including the step of guessing an initial viewpoint of the video frame.
4. The method of claim 1 , including a final viewpoint, and wherein the final viewpoint gives an estimate of the relative rotation and translation between the video frame of the video feed and the reference image.
5. The method of claim 1 , further including the step of using a resolution pyramid wherein all images, depth maps, and gradients are down-sampled.
6. The method of claim 1 , further including the step of using a weighted normalized cross-correlation objective function.
7. The method of claim 1 , further including an optimization technique based on a Gauss-Newton parameter update.
8. The method of claim 1 , wherein the computed set of reference images of a body lumen comprises a 3-D model of a bronchial tree.
9. The method of claim 1 , wherein the computing step is performed prior to the procedure.
10. The method of claim 1 , further including an updating step performed during the registering.
11. The method of claim 1 , further including an updating step performed during the registering.