Quick image registration method based on B spline and Levenberg Marquardt optimization

An image registration and fast technology, applied in the field of medical image analysis and processing, can solve the problems of low precision and slow speed, and achieve the effect of improving the running speed

Inactive Publication Date: 2018-07-13
北京中科嘉宁科技有限公司
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a fast image registration method based on B-splines and Levenberg-Marquardt optimization, in order to solve the problems of slow speed and low precision of existing registration methods, and adopt the free deformation model based on B-splines as

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
  • Quick image registration method based on B spline and Levenberg Marquardt optimization
  • Quick image registration method based on B spline and Levenberg Marquardt optimization
  • Quick image registration method based on B spline and Levenberg Marquardt optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] see Figure 1-10 , the present invention is based on the fast image registration method of B-spline and fast Levenberg-Marquardt optimization, adopts the free deformation model based on B-spline as the deformation model of image, and utilizes fast Levenberg-Marquardt optimization method to the control in the free deformation model The optimal position of the point is used to solve the problem. This method can adapt to 2D medical images and even 3D medical images with large data volume.

[0058] The variables involved in the registration method are named as follows:

[0059] R←reference image, T←floating image, K←maximum number of iterations, ε←the threshold for the change of the similarity measure between two adjacent iterations, if the change in the similarity measure between two adjacent iterations is less than the threshold, it is determined that the iteration is terminated, and the algorithm Finish.

[0060] The registration method includes the following steps:

...

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 relates to a quick image registration method based on B spline and Levenberg Marquardt optimization. An image registration problem is converted into a target function minimum solving problem herein; a triple B spline is sued to simulate nonrigid deformation of an image; Levenberg Marquardt optimization is used to perform iterative solving on the problem; based on the Levenberg Marquardt optimization, a Jacobian matrix with highest computing quantity is reused, an approximate iterative step is introduced, and optimal weight of the approximate iterative step is found by means of linear search. In order to eliminate the influence of a regularization item coefficient in the iteration process upon converging speed, the invention also introduces an adaptive method to determine thecoefficient; by establishing a correlation between variations of the coefficient and those of a target function value, it is possible to effectively accelerate algorithm convergence.

Description

technical field [0001] The invention relates to the technical field of medical image analysis and processing, in particular to a fast image registration method based on B-spline and Levenberg-Marquardt optimization. Background technique [0002] Image registration is one of the most critical techniques in medical image processing. With the help of medical image registration technology, two or more images from different imaging devices can be combined to take advantage of their respective information and express more abundant information on one image. At the same time, sometimes it is necessary to compare the patient's image with the image of the same part of the normal person in clinical practice, which is of great significance for assisting doctors in diagnosis and treatment, and image registration is also a key technology for this type of application. In recent decades, with the rapid development of computers and medical equipment, image registration technology has also b...

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
IPC IPC(8): G06T7/33
CPCG06T7/33G06T2207/30004
Inventor 吕科董继阳
Owner 北京中科嘉宁科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap