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

A registration method for dynamic contrast-enhanced magnetic resonance image sequences of the breast

A magnetic resonance image and dynamic enhancement technology, applied in the field of medical medical image registration, can solve problems such as inability to guarantee time continuity, achieve the effects of reducing complexity and calculation, fast implementation, and improving estimation accuracy

Active Publication Date: 2016-04-06
SOUTHERN MEDICAL UNIVERSITY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although Zheng's method allows for enhanced spatial smoothness, it cannot guarantee temporal continuity

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 method for dynamic contrast-enhanced magnetic resonance image sequences of the breast
  • A registration method for dynamic contrast-enhanced magnetic resonance image sequences of the breast
  • A registration method for dynamic contrast-enhanced magnetic resonance image sequences of the breast

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] A registration method for breast dynamic enhanced magnetic resonance image sequences, such as figure 1 shown, including the following steps:

[0054] (1) Read the image data of all time frames in the same layer of the DCE-MRI image sequence;

[0055] (2) Use affine transformation to roughly register the images before and after enhancement, and obtain the initial estimate of the deformation field;

[0056] (3) Perform motion compensation on the DCE-MRI image sequence from the currently estimated deformation field, and calculate the enhancement field at each time point;

[0057] (4) Use K-means clustering to discretely divide the enhanced fields of time series into finite types for the enhanced fields at all time points obtained in step (3), and then use Markov random field to model the enhanced fields of time series , use the Fast-PD algorithm to optimize the discrete Markov random field energy to solve the time series enhanced field;

[0058] (5) Use the time series ...

Embodiment 2

[0088] The method of the present invention is described with a specific embodiment.

[0089] In this embodiment, the image size is 384×384×56, the pixel size is 1×1×1 mm, and a total of nine images of the patient at different times are collected. The image at the first moment is the image before enhancement, and the images at other moments are the image after enhancement.

[0090] (1) Read in the images of the ninth floor at nine times respectively, with figure 2 Five breast DCE-MRI images with obvious gray scale changes in the selected images are shown.

[0091] (2) Taking the pre-enhanced image as a reference image and the post-enhancement image as a floating image, affine transformation is used to perform rough registration on the pre-enhancement and post-enhancement images, and the initial estimation of the deformation field is obtained.

[0092] (3) Perform motion compensation on the DCE-MRI image sequence by the currently estimated deformation field, according to the ...

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 registering method of a breast dynamic contrast-enhanced magnetic resonance image (DCE-MRI) sequence. The registering method comprises the following steps of: (1) reading image data of all time frames on the same layer of the DCE-MRI sequence; (2) coarsely registering an image to be enhanced and an enhanced image to obtain an initial estimation value of a deformation field; (3) performing motion compensation on the DCE-MRI sequence, and calculating an enhancement field of each time point; (4) modeling, and solving a time sequence enhancement field; (5) de-enhancing the DCE-MRI sequence; (6) solving the deformation field; and (7) judging whether the solutions of the time sequence enhancement field and the deformation field converge or not; if the solutions do not converge, regarding the currently solved deformation field as the currently estimated deformation field, and performing the step (3); and if the solutions converge, registering the image sequence. The registering method is accurate in registering and small in calculation amount; the time sequence enhancement field can be estimated.

Description

technical field [0001] The invention relates to a registration method of medical images, in particular to a registration method of a breast dynamic enhanced magnetic resonance image sequence. Background technique [0002] The registration method of Dynamic Contrast-Enhanced Magnetic Resonance Image (DCE-MRI) of the breast generally regards the MRI images before and after enhancement as images of different modalities, and then uses mutual information as a similarity measure to match the images before and after enhancement. allow. [0003] Rueckert uses normalized mutual information as a similarity measure (RueckertD, SonodaLI, HayesC, HillDLG, LeachMO, HawkesDJ. Nonrigidregistrationusing free-form deformations: ApplicationtobreastMRImages.IEEETransactionsonMedicalImaging, 1999.18(8):p.712-721), with 3D rigid registration as Coarse registration results, and then use the free deformation model based on B-splines to describe the deformation field of the breast, and add the smoo...

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): G06T7/00
Inventor 阳维余丽玲卢振泰高杨冯前进陈武凡
Owner SOUTHERN MEDICAL UNIVERSITY
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