Brain magnetic resonance image registration method based on K-means clustering method

Abstract

The invention discloses a brain magnetic resonance image registration method based on a K-means clustering method. The method comprises the steps that firstly, an accumulated angle point set is acquired through mixed angle point detection of a Harris operator and a SUSAN operator, a new angle point set is screened out through angle point strength, rough matching screening is carried out through a cross correlation coefficient method, then angle points are clustered by introducing the K-means clustering method, precise angle point pairs are screened out by combining a normalized correlation method and a voting matching method, finally, the angle point set is optimized through a Powell algorithm, a rebuilt parameter value is obtained, and final registration is carried out on images. The brain magnetic resonance image registration method has the advantages that good stability is achieved, feature point information can be described completely and accurately, the running time of a program in subsequent operation is reduced, registration accuracy is improved, an image registration algorithm is improved more precisely and efficiently, and a transformation image fluctuant within a large range can be compatible better.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a brain magnetic resonance image registration method based on a K-means clustering method. Background technique [0002] Brain MRI image analysis is an important means of pathological analysis, and image registration is an important part of image processing. After analysis, it is found that there are problems in the existing research, such as mutual information method, normalized mutual information method and particle swarm optimization algorithm. Due to the lack of consideration of factors such as distribution, the accuracy of the registration results is not high, and the registration takes a long time. [0003] In addition, the corner feature point (referred to as corner) detection algorithm has the advantages of small amount of calculation, high real-time and high effectiveness, and has been widely used in multi-type image registration. The corner detection ...

AI Technical Summary

Problems solved by technology

Moravec operator is sensitive to edge response and noise, which affects the accuracy of corner point extraction; Harris operator is sensitive to noise, but it is still a relatively stable corner point extraction operator; SUSAN operator has strong noise resistance , scaling and rotation invariance

[0004] However, most of the current research on corner detection algorithms is based on the improvement of the above operators, and there are few studies on corner detection algorithms used in brain MR image registration, and they are mainly limited to the improvement of the same corner detection algorithm.

However, the corner points extracted by different operators cannot completely and correctly describe the feature point information. It is necessary to study the combination of different operators to extract corner points to comprehensively realize brain MR image registration

Images