Medical Image Fusion Method Based on Quaternion Wavelet Transform Context Structure

Abstract

The present invention discloses a medical image fusion method based on the context structure of quaternion wavelet transform (QWT). The method mainly solves the problems in the prior art that the brightness, the contrast and other factors change and the original image information is lost during the medical image fusion process. The method comprises the steps of 1) respectively subjecting to-be-fused images to QWT treatment to obtain the corresponding QWT coefficients of the to-be-fused images; 2) fusing the low-frequency portions of the QWT coefficients of the to-be-fused images according to the fusion rule of the maximum operation of absolute values so as to obtain a low-frequency fusion coefficient; 3) figuring out a sharpness coefficient corresponding to a high-frequency sub-band coefficient for the high-frequency portions of the QWT coefficients of the to-be-fused images; 4) obtaining a fused high-frequency coefficient based on a context statistical model and a sharpness coefficient design fusion rule; 5) according to the low-frequency fusion coefficient and the high-frequency fusion coefficient, obtaining a fused image through the QWT inverse transformation. According to the technical scheme of the invention, the structure information and the function information of a medical image are fully integrated, so that the details of the image are effectively protected. The visual effect of the image is improved. Compared with the traditional fusion method, the image fusion quality is greatly improved.

Description

technical field [0001] The invention relates to a medical image fusion method based on a quaternion wavelet transform context structure, which is a fusion method in the technical field of medical image processing and is widely used in clinical medical diagnosis and treatment. Background technique [0002] As a research hotspot at home and abroad, medical image fusion technology has strong practicability. There are many medical imaging, mainly including ultrasound, X-ray, magnetic resonance MRI, computed tomography CT, positron emission tomography PET, single photon emission tomography SPECT, infrared and so on. According to the content of each medical image, these medical images can be roughly divided into two categories: functional images SPECT, PET, etc. and anatomical structure images CT, MRI, B-ultrasound, etc. These two types of images have their own advantages and disadvantages: the anatomical image mainly provides the anatomical information of the organs, although it...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to address the above-mentioned deficiencies in the prior art, and propose a medical image fusion method based on the quaternion wavelet transform context structure, to solve the problem of brightness, contrast, etc. in the fusion image obtained by the existing multi-scale medical image fusion method Changes and the loss of original image information, and fully integrate the structural information and functional information of medical images of different scales, effectively protect image details, enhance image contrast and edge contours, improve its visual effects, and improve the quality of fusion images

Images