2D-3D image registration algorithm

Abstract

The invention discloses a 2D-3D image registration algorithm. The algorithm comprises the following steps: (1) scanning an affected part of a patient before an operation to obtain a preoperative 3D image; carrying out positive and lateral perspective scanning on the corresponding affected parts of the patient in an operation to obtain positive and lateral 2D perspective images; (2) constructing aspace model of intraoperative shooting positive and lateral perspective imaging equipment, and calculating and obtaining an initial pose of the preoperative 3D image in the space model according to the step (1); (3) generating a positive side position DRR image of the preoperative 3D image by adopting the space model constructed in the step (2), and carrying out template matching on the positive side position DRR image and the corresponding intraoperative 2D perspective image to obtain a rough matching transformation pose of the preoperative 3D image; and (4) performing accurate optimization matching by using a gradient descent optimization algorithm to obtain a final transformation pose of the preoperative 3D image. According to the method, rough matching is carried out by adopting template matching, and then the optimal result is obtained by using the gradient descent optimization algorithm, so that a very accurate registration result can be obtained while the registration speed is ensured.

Description

technical field [0001] The invention relates to the technical field of surgical navigation, in particular to a registration algorithm for 3D CT images and 2D perspective images. Background technique [0002] The 3D CT image and 2D perspective image registration algorithm calculates the pose transformation value between the 3D CT image and the 2D perspective image, which is used to integrate preoperative information (CT-based surgical planning data) into the image-guided placement surgery. In intraoperative X-ray projection images to improve the accuracy of reaching the target position. The current algorithm implementation usually uses 3D CT images to generate 2D DRR (Digital Reconstruction Radiology) images, calculates the similarity between DRR images and fluoroscopic images, and finds a certain pose of CT so that the generated DRR images and fluoroscopic images have the best similarity. Since the target variable has 6 degrees of freedom (3 of which represent rotation and...

AI Technical Summary

Problems solved by technology

Since the target variable has 6 degrees of freedom (3 of which represent rotation and the other 3 represent translation), the traditional similarity evaluation algorithm based on template matching or the algorithm based on random sampling search cannot obtain accurate results, and it is very consuming , which affects the application of the algorithm in the actual scene

Images