Multi-mode medical image registration method based on edge features and CS (Cauchy-Schwarz) information

Abstract

The invention discloses a multi-mode medical image registration method based on edge features and CS (Cauchy-Schwarz) information. Based on the principle of a generalized morphological filter, the method disclosed by invention improves the morphological gradient operator and performs image edge detection by use of a new gradient filtering operator so as to improve the computing speed and anti-noise performance of the image edge detection and quickly realize rough detection of the image edge, and determines the coordinates and direction of the image edge point to lay a foundation for the subsequent image registration; the method constructs a new CS geometrical information measure according to a CS inequality, wherein the measuring method does not involve division and logarithm arithmetic in the mathematical computation process, and can effectively reduce the computing complexity in image registration and improve the computing efficiency; and moreover, the method adopts a Powell method to optimize registration parameters, does not need to derivate a target function, has quadratic convergence and high convergence speed, and is conveniently realized by programming. Compared with the prior art, the method disclosed by the invention has better performance in computing standard deviation, information amount, average computing time and the like, and has better robustness.

Description

technical field [0001] The invention relates to a medical image registration method, in particular to a multimodal medical image registration method based on edge features and CS (Cauchy-Schwarz) information. Background technique [0002] Medical image registration refers to medical images from different forms of imaging equipment (such as MRI, CT, PET, SPECT, etc.) Corresponding points on another medical image achieve spatial consistency. [0003] With the development of computer technology and electronic technology, various modal imaging equipment such as MRI, PET, and CT have gradually become routine diagnostic equipment in hospitals, and medical images have become an indispensable and important means for clinical diagnosis and treatment. How to maximize the use of useful information provided by imaging data and improve the accuracy of doctor's diagnosis of diseases is of great significance to clinical diagnosis. The main purpose of medical image registration is to orga...

AI Technical Summary

Problems solved by technology

These two types of images have their own advantages and disadvantages: the resolution of functional images is poor, but it provides organ function and metabolism information that cannot be replaced by anatomical images; anatomical images provide anatomical shape information of organs with higher resolution (Functional images cannot provide anatomical details of organs or lesions), but cannot reflect the function of organs

The main problems existing in the current multimodal medical image registration methods are: image data segmentation has not been an effective method for image registration mechanism, lack of invariance of image local features, image segmentation effect deviates from physiological visual attention characteristics, and constructed The medical image registration measure of the medical image registration is often too large in calculation, slow in speed, and poor in robustness, and it is difficult to meet the requirements of image registration.

Images