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

Multi-modal medical image fusion method based on multi-scale anisotropic decomposition and low-rank analysis

An anisotropic and medical image technology, which is applied in image enhancement, image data processing, and graphic image conversion, can solve the problems of lack of details in fused images and the inability to effectively extract detailed information, so as to improve structural awareness and increase details Information content, effect of improving visual contrast

Active Publication Date: 2017-09-01
BEIJING UNIDRAW VR TECH RES INST CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The main disadvantage of this type of method is that the wavelet kernel function used has nothing to do with the processed data, and cannot effectively extract detailed information in different directions, so there is a shortcoming of lack of details in the fused image

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
  • Multi-modal medical image fusion method based on multi-scale anisotropic decomposition and low-rank analysis
  • Multi-modal medical image fusion method based on multi-scale anisotropic decomposition and low-rank analysis
  • Multi-modal medical image fusion method based on multi-scale anisotropic decomposition and low-rank analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0037] figure 1 The general processing flow of multi-modal medical image fusion method based on multi-scale anisotropy decomposition and low-rank analysis is given. figure 2 with image 3 The detailed steps of multi-scale image representation method based on thermonuclear pyramid and saliency information scale space construction method based on low-rank analysis are given respectively.

[0038] The present invention provides a multi-modal medical image fusion method based on multi-scale anisotropic decomposition and low-rank analysis, the main steps of which are introduced as follows:

[0039] 1. Multi-scale image representation based on thermonuclear pyramid

[0040] In order to effectively extract the inherent structural information of the input image and encode it into the used thermal kernel, the present invention proposes to down-sampl...

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 provides a multi-modal medical image fusion method based on multi-scale anisotropic decomposition and low-rank analysis. The method includes the following steps: 1) constructing an image pyramid for the input image, gridding each layer of images, constructing data-dependent anisotropic heat kernels, and realizing multi-scale representation of images; 2) grouping images at different scales , and construct a low-rank analysis for each group, extract its low-rank part, filter out noise effectively, and construct a multi-scale space from the extracted salient information; 3) In each layer of the image pyramid, the low-frequency information adopts S The high-frequency information is fused using the maximum selection strategy, and the sampling weights between the pyramid layers are fused. The multimodal medical image fusion method proposed in the present invention has better robustness to the fusion of noisy images.

Description

technical field [0001] The invention relates to a multi-modal medical image fusion method based on multi-scale anisotropy decomposition and low-rank analysis. Background technique [0002] In clinical medicine, the medical influence of a single modality usually cannot meet the needs of medical staff. Medical diagnosis provides medical images of various modalities, which can be divided into two categories: anatomical structure images (such as: B-ultrasound, CT, MRI) and functional images (such as: PET, SPECT). Due to differences in imaging principles , different kinds of images also have their own advantages and disadvantages. For example, CT images have high spatial resolution and geometric characteristics, and can present human bones very clearly, which is convenient for providing good lesion localization, but the detection effect on human soft tissues is poor, while the imaging effect of human tissues in MRI images is better , is conducive to the determination of the les...

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): G06T5/50G06T3/40
Inventor 郝爱民王青正李帅秦洪
Owner BEIJING UNIDRAW VR TECH RES INST CO LTD
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