Improved multi-sequence magnetic resonance image registration method based on self-similarity

Abstract

An improved multi-sequence magnetic resonance image registration method based on self-similarity comprises the following steps: 1) de-noising all three-dimensional magnetic resonance images layer by layer using a non-local mean fast de-noising algorithm; 2) extracting the foreground part by using the cascading Otsu algorithm, that is, using the Otsu algorithm for many times to superimpose the foreground part on the previous image; 3) using local three-dimensional median filter to optimize the result; 4) encoding that preprocessed image by use self-similarity; 5) using a discrete-based optimization method to calculate similarity measure between feature images, and judge whet that similarity measure reaches the optimal state; 6) using the final transformation matrix to transform the originalfloating image to obtain the final result map. The invention has strong anti-noise interference ability and high registration accuracy.

Description

technical field [0001] The invention relates to a multi-sequence magnetic resonance image registration method. Background technique [0002] Usually, the registration between different sequences of magnetic resonance images is to optimize the similarity measure through the similarity measure and optimization algorithm, and always find the best similarity measure value. The image registration method determines the degree of similarity between images of different sequences through the similarity measure, but the similarity measure ignores the structural information existing between the images. When the similarity measure between different sequences of magnetic resonance images falls into a local optimum , tends to output a different result than what a human visually should get. At present, there are many kinds of image registration, such as the research based on similarity measure, such as the image registration method based on mutual information, the mutual information image...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of the existing multi-sequence magnetic resonance image registration method in the case of noise, the conversion map effect of the multi-sequence magnetic resonance medical image is poor and the stability is poor, the invention provides a better stability. Noise strategy combined with a self-similarity-based transformation method to obtain multi-sequence MR transformation maps

Images