Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Registration Model Establishment Method and Application of Non-rigid Multimodal Medical Image

A medical image and registration model technology, applied in image analysis, image enhancement, image data processing, etc. The effect of efficient medical image registration, clear and complete image characterization results, and high registration accuracy

Active Publication Date: 2022-05-20
HUAZHONG UNIV OF SCI & TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above image registration method based on end-to-end deep learning is difficult to effectively deal with the nonlinear gray level difference of multimodal images, and it is difficult to achieve accurate image registration because of indiscriminately learning the deformation of smooth and edge regions. allow

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
  • A Registration Model Establishment Method and Application of Non-rigid Multimodal Medical Image
  • A Registration Model Establishment Method and Application of Non-rigid Multimodal Medical Image
  • A Registration Model Establishment Method and Application of Non-rigid Multimodal Medical Image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] A method for establishing a registration model of a non-rigid multimodal medical image, such as figure 1 shown, including the following steps:

[0062] (1) Obtain a medical dataset in which each sample includes a paired reference image and a floating image and an actual registered image between these two images;

[0063] For the convenience of expression, the reference image and the floating image in each sample in the medical image dataset are denoted as I r and I f , in the subsequent training process, the actual registration image is the label image, which is recorded as I l ;

[0064] (2) Establish the first generative confrontation network GAN_dr, in which the generator G_dr takes the structural representation map of the reference image and the floating image as input to generate the structural representation map of the deformation recovery, and the discriminator D_dr uses the deformation recovery generated by the generator G_dr The structural representation ma...

Embodiment 2

[0126] A registration method for non-rigid multimodal medical images such as Figure 4 shown, including:

[0127] For the floating image to be registered floating image I f and the reference image I r , after calculating the structural characterization graphs IMIND_f and IMIND_r respectively, input to the registration model established by the registration model establishment method of the non-rigid multimodal medical image provided by the above-mentioned embodiment 1, so as to output the registration image I by the registration model g .

[0128] The non-rigid multimodal medical image registration method provided in this embodiment first calculates the structural representation diagram of the reference image and the floating image to be registered, which can convert the multimodal image into a single-modal image, reducing the damage caused by multimodality. impact, the registration model established based on this embodiment can achieve fast and accurate image registration, ...

Embodiment 3

[0130] A computer-readable storage medium, including a stored computer program; when the computer program is executed by a processor, the device where the computer-readable storage medium is located is controlled to execute the method for establishing a registration model of a non-rigid multimodal medical image provided in Embodiment 1 above, And / or the method for registering non-rigid multimodal medical images provided in Embodiment 2 above.

[0131] The registration effect of the present invention will be further explained in conjunction with the comparative experimental results below. During the experiment, five existing registration methods were selected as comparative examples of the above-mentioned embodiment 2, and the comparative examples are as follows:

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 non-rigid multi-mode medical image registration model establishment method and its application. In the field of medical image registration, it includes: establishing a generative confrontation network GAN_dr, wherein the generator G_dr is used to generate a structural representation graph for deformation recovery , the discriminator D_dr is used to judge whether the structural representation map generated by G_dr has effectively recovered the deformation; calculate the structural representation map of the reference image, floating image and actual registration image in each sample in the medical data set, and use the calculation results to train GAN_dr ; Establish a generative confrontation network GAN_ie, in which the generator G_ie uses the structural representation map as input to estimate the registration image, and the discriminator D_ie is used to judge whether the estimated registration image is consistent with the actual registration image; use the trained G_dr Generate the structural representation diagram of the deformation recovery corresponding to each sample in the medical data set, and train GAN_ie; connect the trained G_ie to G_dr to obtain the registration model. The invention can realize fast and accurate matching of medical images.

Description

technical field [0001] The invention belongs to the field of medical image registration, and more particularly relates to a method for establishing a registration model of a non-rigid multi-mode medical image and an application thereof. Background technique [0002] Due to the different principles of various imaging technologies, each imaging method has its own advantages in reflecting human body information. Functional imaging, such as functional magnetic resonance imaging (fMRI), focuses on reflecting human metabolic information, while anatomical imaging, such as T1-weighted MRI, can more clearly reflect the anatomical structure of the human body. Furthermore, even for anatomical imaging such as T1-weighted MRI and T2-weighted MRI, there are differences in the information they provide. Therefore, the fusion of different information from multimodal images can better assist the diagnosis and treatment of human diseases. Multimodal medical image registration is the basis of...

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): G06T7/33G06T7/13G06T5/50G06K9/62G06V10/774
CPCG06T7/13G06T7/344G06T5/50G06F18/214G06T7/33G06T2207/10088G06T2207/20081G06T2207/20084G06T2207/30016G06T7/337G16H30/20G06V10/454G06V10/761G06T5/20
Inventor 张旭明朱星星
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com