Unlock instant, AI-driven research and patent intelligence for your innovation.

Multimodal Medical Image Registration Method Fused with Gradient Information and Generalized Entropy Similarity

A technology of medical image and gradient information, applied in the field of medical image processing, can solve the problems of not considering image gradient, low registration error and so on

Active Publication Date: 2020-09-25
ZHONGYUAN ENGINEERING COLLEGE
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The registration experiments of preoperative brain magnetic resonance images and intraoperative ultrasound images have confirmed that this method can obtain lower registration errors. However, this method only uses the direction information of the gradient and does not consider the image gradient model.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multimodal Medical Image Registration Method Fused with Gradient Information and Generalized Entropy Similarity
  • Multimodal Medical Image Registration Method Fused with Gradient Information and Generalized Entropy Similarity
  • Multimodal Medical Image Registration Method Fused with Gradient Information and Generalized Entropy Similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] Such as image 3 As shown, a multi-modal medical image registration method that fuses gradient information and generalized entropy similarity, the steps are as follows:

[0073] S1, construct a generalized entropy similarity measure.

[0074] S1.1, define Arimoto entropy A α ;

[0075]

[0076] Among them, X is a discrete random variable; α is a parameter that controls the non-scalability of Arimoto entropy; M is the number of elements of the discrete random variable X; i is the element number of the probability distribution P of the discrete random variable X; p i Is the i-th element of the probability distribution P.

[0077] According to Lopida's law, the limit of Arimoto entropy when α→1 is equal to Shannon entropy, so Shannon entropy can be regarded as a special case of Arimoto entropy.

[0078] S1.2, construct Jensen-Arimoto divergence (JAD).

[0079]

[0080] In the formula, A α (·) represents Arimoto entropy, ω i Represents the weighting factor, and ω i ≥0, ∑ω i = 1; Since...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a multimodal medical image registration method fusing gradient information with generalized entropy similarity. The method comprises steps of: S1, constructing a generalized entropy similarity measure; S2, constructing the gradient measure of an image to be registered; S3, constructing the similarity measure of the image to be registered; S4, constructing a registration model of a multimodal image; and S5, solving the registration model. The method comprehensively takes account of the gradient information and the grayscale distribution characteristics of different modalmedical images, and implements the accurate registration of the multimodal medical image, constructs the generalized entropy similarity measure based on a generalized information entropy, and has a wide range of properties. Rather than taking the grayscale difference between the images into consideration, the method calculates the information theory similarity between the images to be registeredby using the joint probability distribution of the grayscale values of the two images, is not only applicable to the same-modal medical images but also to the different-modal medical images with largegrayscale difference, and is expanded in the use range.

Description

Technical field [0001] The invention belongs to the technical field of medical image processing, and specifically relates to a multi-modal medical image registration method that integrates gradient information and generalized entropy similarity. Background technique [0002] Medical image registration is an important technology in the field of medical image processing. It plays an important role in medical information fusion, tumor growth monitoring, image-guided surgical treatment and radiotherapy plan formulation. The rapid development and wide application of microelectronics, computers, and information science have led to the rapid development of medical imaging technology. The continuous development of imaging equipment has sharply increased the amount of information that doctors can obtain from medical images. The image information acquired by a single imaging device can no longer meet the requirements of certain specific applications, and the previous image processing meth...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/30G06T7/00
Inventor 李碧草刘洲峰王贝张爱华黄杰舒华忠朱永胜刘闪亮
Owner ZHONGYUAN ENGINEERING COLLEGE