CT-CBCT image deformation registration method

Abstract

The invention provides a CT-CBCT image deformation registration method. The method belongs to the technical field of medical image processing, and specifically comprises the following steps: preprocessing a CBCT image and a CT image; establishing local control points of the image A and the image B and determining fields and sizes of the control points; comparing the neighborhood gray average EA of the ith control point QAi of the image A with the neighborhood gray average EB of the ith control point QBi of the image B; and finishing deformation registration of a group of CT images and a group of CBCT images. According to the method, two-stage evaluation is adopted for control point neighborhood gray scale correction registration to judge a dark area and an artifact area, so that local gray scale correction registration is performed on two groups of images in a targeted manner according to whether the dark area exists or not and whether the artifact area exists; in addition, local control points are established on the basis of two groups of images participating in registration by utilizing gradient change characteristics and adopting a grid division mechanism, and local gray correction registration is performed on the basis of neighborhoods of the control points, so that global blind matching is avoided.

Description

Technical field[0001]The present invention relates to the field of medical image processing, and more particularly to a CT-CBCT imaging modification method, and more particularly to a CT-CBCT image variable registration method based on the control point neighborhood gradation correction.Background technique[0002]Medical image registration is one of the key technologies of precision radiation therapy, and provides a basis for the diagnosis of the disease, the target area, precise pendulum and precision treatment. Multimode image variation registration provides a more abundant medical image information for doctors and physiologists.[0003]Traditional deformation registration method often causes the CT-CBCT image misconduct or mismatch during the problem of image contrast, and the occurrence of CT-CBCT image is misconducting or mismatched, in order to solve these problems, in order to solve these problems Outer research scholars proposed global strength correction methods to prepare the...

AI Technical Summary

Problems solved by technology

[0003] Traditional deformation registration methods often cause CT-CBCT image mismatch or mismatch phenomenon due to insufficient image contrast and gray level discontinuity when dealing with CT-CBCT deformation registration problems. To solve these problems, domestic Foreign researchers proposed a global intensity correction method to preprocess CBCT images, with the purpose of converting CBCT-CT multi-modal deformation registration into the same-modal deformation registration problem, but in the actual CT-CBCT deformation registration In the research, it is found that artifacts always exist locally, which will destroy the original intensity or grayscale distribution correspondence. Therefore, it is necessary to perform local grayscale correction on CBCT images with artifacts. While correcting CBCT images, CT-CBCT The images are matched to complete the final registration of CT-CBCT

Images