Medical image registration method based on cross hill-climbing memetic quantum evolutionary computation

Abstract

The invention discloses a medical image registration method based on cross hill-climbing memetic quantum evolutionary computation, and mainly aims to solve the problem that in the prior art, the registration effect is poor. The method includes the steps that images are read in, and relevant parameters are initialized; an initial population is generated through a chaotic method; registration parameters corresponding to individuals in the population are computed; image conversion is conducted on the floating images according to the registration parameters to acquire the converted images; similarity between the converted images and a reference image is calculated, a local generation optimal registration parameter is looked for, and quantum revolution door update is conducted on all the individuals in the population according to the optimal registration parameter; cross hill-climbing memetic local learning is conducted on the optimal refrigeration parameter; whether an optimal individual meets a forgetting condition or not is judged, and forgetting operators are executed on the optimal individual; circulation conditions are controlled, if circulation is ended, the registration result is output. By the adoption of the method, the better registration result can be acquired, and the method can be used for registering the medical images.

Description

technical field [0001] The invention belongs to the technical field of image processing and relates to medical image registration, in particular to a new medical image registration method based on cross-climbing memetic quantum evolution calculation, which can be used for subsequent medical image understanding and processing. Background technique [0002] Medical image registration is a method of finding space transformation parameters through an optimization algorithm. Using this parameter to perform space transformation on two different medical images can make the two medical images achieve one-to-one correspondence in spatial position, or in A match is reached at points of surgical significance. The two images involved in registration may be of different imaging modes, of different patients, or medical images of the same patient taken at different times. [0003] Medical image registration methods generally include feature space, search space, similarity measure and sear...

AI Technical Summary

Problems solved by technology

The existing registration methods mainly use traditional optimization algorithms, which use the mathematical characteristics of the objective function to construct an optimization method. Although the speed is fast, the degree of registration is not high enough, and it is easy to fall into local extremum, especially for the optimization parameters. multiple non-rigid registration

In recent years, medical image registration based on genetic algorithm has also appeared, but the coding length of genetic algorithm is long, and it will still converge to local extremum, which will affect the registration effect

Images