Image registration method and device

An image registration and registration technology, applied in the field of image processing, can solve problems such as misalignment, difficulty in ensuring real-time performance, and high computational complexity

Active Publication Date: 2018-10-19
NEUSOFT MEDICAL SYST CO LTD
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, regarding the imaged object in the image, for example, the above-mentioned liver with position differences due to respiratory movement, because its relative position changes with time, when using rigid registration to register liver images corresponding to different time points , will produce obvious misalignment results. At this time, elastic registration methods are generally used. The common methods are elastic body-based, fluid-based and optofluid-based methods. However, elastic registration models generally have high computational complexity and require Assist acceleration to improve registration speed
Even if the above two basic registration methods are optimized and accelerated, real-time performance is still difficult to guarantee

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
  • Image registration method and device
  • Image registration method and device
  • Image registration method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] An image registration method shown in an exemplary embodiment of the present application will be introduced below with reference to the accompanying drawings. The image registration method provided in this embodiment can perform image registration for different medical images. For the convenience of description, in this embodiment of the application, registration of a liver image may be used as an example for introduction.

[0045] see figure 1 , is a flow chart of an image registration method provided in an embodiment of the present application, and the method may include the following steps:

[0046] S101. Acquire a reference image and an image to be registered, where the reference image and the image to be registered are three-dimensional images generated by the same object to be imaged under different imaging conditions.

[0047] In this embodiment, when the imaged object in the image, such as the liver, is under different imaging conditions, its position may chang...

Embodiment 2

[0078] In this embodiment, since the current reference image and the current image to be registered are divided into blocks in the same manner according to the actual motion direction of the imaged object, multiple pairs of reference blocks and blocks to be registered will be obtained. For each pair of the reference block and the block to be registered, the corresponding similarity is calculated, and then the target displacement corresponding to each block to be registered is determined. In this case, if each block to be registered is moved according to the target displacement corresponding to the block to be registered, since multiple target displacements may be different, or even have a relatively large gap, resulting in The variation range of the images to be registered is relatively large, that is, some blocks to be registered are too convex, and some blocks to be registered are too concave.

[0079] For this reason, based on the image registration method provided in the f...

Embodiment 3

[0107] It should be noted that, in order to realize image registration, it is usually necessary to perform image registration based on image features. Therefore, in this embodiment, a certain type of image feature or at least two types of image features can be selected in advance from many image features as the selected image feature, and then, in the first embodiment above, S103 "determine the image block result "Before, the feature image of the reference image is generated according to the selected image features, and the feature image of the reference image is used as the current reference image, and the feature image of the image to be registered is generated according to the selected image feature, and the feature image of the image to be registered is generated. The feature image of the registration image is used as the current image to be registered.

[0108] Among them, image features may include color features, texture features, shape features, and spatial relationshi...

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 an image registration method and device. The method comprises a step of acquiring a reference image and a to-be-registered image as a current reference image and a current to-be-registered image, a step of determining an image segmentation result, a step of taking two mutually corresponding image blocks in the current reference image and the current to-be-registered image as a reference image block and a to-be-registered image block, a step of determining a similarity degree of the corresponding image blocks, a step of determining a target displacement amount of the to-be-registered image block according to the similarity, a step of allowing the to-be-registered image block to move according to the target displacement amount to complete registration of this time, judging whether a registration end condition is satisfied or not, ending the registration if so, taking a to-be-registered image after the registration of this time if not, and determining an image segmentation result again to start a next registration operation. According to the image registration method and device, the image registration speed can be improved, and the accuracy of an image registration result can be improved.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to an image registration method and device. Background technique [0002] With the continuous development of medical imaging, medical image analysis has become a very important content of clinical diagnosis, and the problem of medical image registration has been gradually raised, and has become one of the hot topics in the field of medical image research. Medical image registration refers to seeking one or a series of spatial transformations for a medical image to achieve spatial consistency with corresponding points on another medical image. This consistency refers to the same anatomical point on the human body. The two matched images have the same spatial position, and the result of registration should make all the anatomical points on the two images, or at least all anatomical points with diagnostic significance and surgical points of interest, be matched. [...

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 Applications(China)
IPC IPC(8): G06T7/30G06T5/00
CPCG06T5/002G06T7/30G06T2207/30061G06T2207/20021
Inventor 周楹君李丙生马锐兵
Owner NEUSOFT MEDICAL SYST CO LTD
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