Segmentation-based Brain MR Image Registration Method

An image registration and brain technology, applied in the field of image processing, can solve problems such as difficult registration tasks

Active Publication Date: 2017-07-11
HOPE CLEAN ENERGY (GRP) CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the diversity of images and the varying degrees of degradation of the images themselves, it is difficult for us to find a general method to complete all registration tasks

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
  • Segmentation-based Brain MR Image Registration Method
  • Segmentation-based Brain MR Image Registration Method
  • Segmentation-based Brain MR Image Registration Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] In order to describe the content of the embodiment conveniently, the existing terms are introduced:

[0014] bias field. The mean and variance of different local regions of the same tissue have large deviations, especially when high-field-strength nuclear magnetic resonance equipment appears, this problem becomes more prominent. The commonly used bias field model is the multiplicative bias field.

[0015] Gradient descent method. The direction of the negative gradient is used to determine the new search direction of each iteration, so that each iteration can gradually reduce the optimized objective function.

[0016] B-splines. B-spline is a special representation of spline curve. It is a linear combination of B-spline basis curves. B-splines are a generalization of Bézier curves, which can be further extended to non-uniform rational B-splines, allowing us to build accurate models for more general geometries.

[0017] Affine transformation. In geometry, a vector ...

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 brain MR image registration method. The brain MR image registration method comprises the steps that a template brain MR image and an objective brain MR image are divided to obtain three obvious tissue areas, similarity between corresponding tissue of the tissue areas obtained through division is firstly calculated, and different layering levels are used for the tissue areas with the different similarities in the registration process. If the corresponding tissue areas are high in similarity, a good registration result can be obtained by using few layers and the high mesh resolution in the registration process. After registration on the corresponding tissue areas is finished, an objective image can be registered to a template image completely.

Description

technical field [0001] The invention belongs to the technical field of image processing, and mainly relates to an MR brain image registration method based on image segmentation. Background technique [0002] Image registration is the process of matching and superimposing two or more images acquired at different times, different imaging devices or under different conditions. Image registration technology has high applications in the fields of remote sensing, medical imaging, cartography, and computer vision. In general, we classify its main applications into four categories: multi-view analysis, multi-temporal analysis, multi-modal analysis, and scene-to-model registration. Due to the variety of images and the varying degrees of degradation of the images themselves, it is difficult for us to find a general method to complete all registration tasks. Each method not only needs to consider the geometric deformation of the image, but also factors such as radial deformation and ...

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): G06T7/00A61B5/055
Inventor 解梅宋浩
Owner HOPE CLEAN ENERGY (GRP) 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

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