Heart motion estimation method and system and terminal equipment

A motion estimation and heart technology, applied in the field of image processing, can solve problems such as difficult to determine the corresponding relationship of sampling points on the myocardial contour, difficult heart motion model estimation, etc., and achieve the effect of reducing the gradient disappearance phenomenon

Active Publication Date: 2019-08-16
SHENZHEN UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to propose a cardiac motion estimation method, system and terminal equipment to solve the problem in the prior art that it is difficult to determine the corresponding relationship between sampling points on the myocardial contour based on cardiac Cine MRI, and it is difficult to estimate the cardiac motion model

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
  • Heart motion estimation method and system and terminal equipment
  • Heart motion estimation method and system and terminal equipment
  • Heart motion estimation method and system and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Such as figure 1 As shown, the embodiment of the present invention provides a heart motion estimation method, by constructing a left ventricle correspondence learning network, judging the left ventricle image feature pairs with corresponding relations, and using the deformation function to estimate the cardiac motion field according to these correspondence relations, effectively By overcoming the mismatch problem in the corresponding relationship, the corresponding relationship of the myocardium can be accurately extracted without segmenting the myocardium, thereby obtaining a stable and reasonable cardiac motion field. The heart motion estimation method includes but not limited to the following steps:

[0067] S101. Build a basic network model.

[0068] In the above step S101, the basic network model is a deep learning network with dense connections and atrous convolutions.

[0069] In specific applications, the deep learning network of densely connected mixed hole c...

Embodiment 2

[0108] Such as Figure 4 As shown, the embodiment of the present invention shows a schematic structural diagram of the basic network model of the left ventricle correspondence learning network in the first embodiment. Among them, the left ventricle correspondence learning network is based on the deep learning network of densely connected mixed hole convolution.

[0109] see Figure 4 , in the embodiment of the present invention, the basic network model 40 of the left ventricle correspondence learning network includes two densely connected networks with the same structure;

[0110] The densely connected network includes a two-layer cascaded traditional convolution network 41 (not shown in the figure) and a five-layer cascaded hole convolution network 42 (not shown in the figure);

[0111] Among them, the traditional convolutional network 41 and the hole convolutional network 42 are densely connected to each other;

[0112] Among them, the network parameters of the two-layer ...

Embodiment 3

[0124] The embodiment of the present invention is based on the heart motion estimation method provided in the first and second embodiments, and describes the construction and training of the left ventricle correspondence learning network, that is, step S101 to step S103 and their detailed implementation process, the implementation and implementation in practical applications. Realize the principle.

[0125] In the embodiment of the present invention, the assumed application scenario is cardiac motion estimation in which the image of the left ventricle is Cine MRI.

[0126] In the embodiment of the present invention, it starts from step S101, and step S101: build a basic network model. The implementation and implementation principle of step S101 in practical applications are as follows:

[0127] 1) Construct a deep learning network with densely connected mixed hole convolution.

[0128] Among them, the deep learning network of densely connected mixed hole convolution is compo...

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 is applicable to the technical field of image processing, and provides a heart motion estimation method and system and terminal equipment, and the method comprises the steps: building abasic network model which is a deep learning network of dense connection mixed hole convolution; obtaining an image feature pair set according to the left ventricle sample image; inputting the image feature pair set into a basic network model for training to obtain a left ventricle corresponding relation learning network; obtaining a first target image and a second target image; respectively sampling the first target image and the second target image to obtain a sub-image slice data set; inputting the sub-image slice data set into a left ventricle corresponding relation learning network to obtain a corresponding relation between sub-image slices; and estimating the heart motion field by using a deformation function according to the corresponding relationship between the sub-image patches.By means of the method, a stable and reasonable heart motion field can be obtained on the premise that the cardiac muscle layer is not segmented.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a heart motion estimation method, system and terminal equipment. Background technique [0002] Cardiac MRI (Magnetic resonance Imaging, nuclear magnetic resonance image) has been widely used to analyze the motion estimation of the heart. Cardiac motion estimation is to estimate the deformation function between the hearts of heart images at different time points. This continuous motion field can describe the heart at any time. The state of the heart, including cardiac output, ejection fraction, myocardial strain and other indicators, detects the location of the lesion on the heart and the changes in the surrounding tissue of the lesion, and provides important help for the discovery and treatment of coronary heart disease. [0003] In traditional cardiac motion estimation methods, non-invasive grid markers are used based on MRI during the cardiac cycle, and then the motion o...

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): G06T7/00G06T7/223G06T7/246G06N3/04G06N3/08
CPCG06T7/0012G06T7/223G06T7/246G06N3/08G06T2207/10088G06T2207/30048G06N3/045
Inventor 汤江月杨烜裴继红杨博乾
Owner SHENZHEN UNIV
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