Method and system for training heart motion field estimation model and method and system for heart motion field estimation

An estimation model and motion field technology, applied in the field of image processing, can solve the problem of low accuracy of cardiac motion estimation, and achieve the effect of overcoming the low accuracy of cardiac motion estimation

Pending Publication Date: 2020-10-16
SHENZHEN UNIV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Therefore, the training cardiac motion field estimation model provided by the present invention, the method and sy

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
  • Method and system for training heart motion field estimation model and method and system for heart motion field estimation
  • Method and system for training heart motion field estimation model and method and system for heart motion field estimation
  • Method and system for training heart motion field estimation model and method and system for heart motion field estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] A method for training a cardiac motion field estimation model provided by an embodiment of the present invention, such as figure 1 shown, including the following steps:

[0068] Step S1: Construct a semi-autoencoder network with preset network parameters.

[0069] The semi-autoencoder network includes an encoding layer, a deformation field calculation layer, and a spatial deformation layer, wherein the encoding layer includes three layers of convolutional networks with different resolutions, wherein;

[0070] The first layer is a convolution layer, the convolution kernel size of the convolution layer is 3×3, the number of convolution kernels is 16, and the two input images are concatenated as the input data of the convolution layer; the second layer It is composed of 4 convolutional layers cascaded. The size of the convolutional kernel of each convolutional layer is 3×3, and the number of convolutional kernels is 32. It is followed by a downsampling operation. The size...

Embodiment 2

[0116] An embodiment of the present invention provides a method for cardiac motion field estimation, such as Figure 4 shown, including the following steps:

[0117] Step S21: Obtain images of the end-diastole and end-systole to be estimated.

[0118] In the embodiment of the present invention, the cardiac image may be acquired by an image device, for example, a short-axis cardiac image may be obtained by a Cine Magnetic Resonance (Cine Magnetic Resonance, Cine-MR) device.

[0119] Step S22: Input the images of the end-diastole and end-systole to be estimated into the cardiac motion field estimation model obtained according to the method for training the cardiac motion field estimation model described in Example 1, and obtain the distribution parameters of invisible variable parameters.

[0120] Step S23: Sampling the distribution of the cloaking variable parameters to obtain the cloaking variable parameter values, constructing a dense deformation field using the radial basis...

Embodiment 3

[0127] An embodiment of the present invention provides a computer device, such as Figure 6 As shown, it includes: at least one processor 401 , such as a CPU (Central Processing Unit, central processing unit), at least one communication interface 403 , memory 404 , and at least one communication bus 402 . Wherein, the communication bus 402 is used to realize connection and communication between these components. Wherein, the communication interface 403 may include a display screen (Display) and a keyboard (Keyboard), and the optional communication interface 403 may also include a standard wired interface and a wireless interface. The memory 404 may be a high-speed RAM memory (Ramdom Access Memory, volatile random access memory), or a non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory 404 may also be at least one storage device located away from the aforementioned processor 401 . The processor 401 may execute the method for tra...

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 method and a system for training a heart motion field estimation model and a method and a system for heart motion field estimation. According to the method and the system fortraining a heart motion field estimation model, a semi-auto-encoder network is used to extract multi-scale features of the left ventricle in a Cine MR images at the end of diastole and the end of systole, different scale features are fused through an encoding network so as to decide distribution parameters of deformation parameters of control points, a deformation model of a radial basis functionis introduced into an auto-encoder, and a decoding process is not needed in an auto-encoder network structure, so that the network is lightened. The non-uniformly distributed control points are adopted, so that the deformation field of the area where the left ventricle is located is easier to control, and the deformation precision is higher; and meanwhile, invisible variable parameters have definite physical significance, the smoothness of a deformation field is easier to control, and a more stable and reasonable heart movement field is obtained to be used for quantitative analysis of cardiovascular diseases.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and system for training a cardiac motion field estimation model and cardiac motion field estimation. Background technique [0002] The purpose of cardiac motion estimation is to describe the spatiotemporal motion state of regions of interest, edges, and contours in image sequences, and its essence is to detect the displacement information between targets from cardiac image sequences. Image registration is an important technique for cardiac motion estimation, which estimates the displacement of the heart between consecutive time points based on a certain deformation model. The purpose of cardiac motion estimation based on image registration is to determine the deformation function of cardiac tissue during the cardiac cycle, which can describe the motion trajectory of the cardiac anatomical structure over time, so that the cardiac motion model of a motion cycle ca...

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
IPC IPC(8): G06T7/207G06N3/04G06N3/08
CPCG06T7/207G06N3/08G06T2207/20081G06T2207/20084G06T2207/30048G06T2207/20221G06N3/045Y02T90/00
Inventor 甘梓誉杨烜裴继红
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