Dual-energy CT image decomposition method based on CNN (convolutional neural network)

A convolutional neural network, CT image technology, applied in neural learning methods, biological neural network models, image analysis, etc., can solve problems such as large noise and low signal-to-noise ratio, and achieve the effect of improving training efficiency

Active Publication Date: 2018-06-29
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF1 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem that the base material image obtained by the existing dual-energy CT image decomposition method contains a large amount of noise and the signal-to-noise ratio is low, the present invention provides a dual-energy CT image decomposition method based on convolutional neural network, through

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
  • Dual-energy CT image decomposition method based on CNN (convolutional neural network)
  • Dual-energy CT image decomposition method based on CNN (convolutional neural network)
  • Dual-energy CT image decomposition method based on CNN (convolutional neural network)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Such as figure 1 As shown, a kind of convolutional neural network-based dual-energy CT image decomposition method of the present invention comprises the following steps:

[0039] Step S101: Design a double-input, double-output convolutional neural network model as the mapping function D(μ H，L ; Θ), where μ H,L For a dual-energy CT image, the convolutional neural network model is designed as a network structure model with double input and double output, such as figure 2 As shown, A and B in the figure are the input high-energy CT images and low-energy CT images, M1 and M2 are the output base material 1 and base material 2, "→" represents two different network structures; and in the dual-input and dual-output Cross convolution is established in the network structure model, such as image 3 Shown; Short links are established in the convolutional neural network model. The specific convolutional neural network model is as follows Figure 4 Shown: Among them, the convol...

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 relates to the technical fields of medical dual-energy image decomposition and image processing, in particular to a dual-energy CT image decomposition method and particularly provides adual-energy CT image decomposition method based on a CNN (convolutional neural network). The dual-energy CT image decomposition method based on the CNN comprises the following steps: designing a CNN model to serve as a mapping function D (mu H, L; theta) of a dual-energy decomposition model; training the CNN with the CNN model and a training data set, and effectively estimating the CNN parameter theta; efficiently decomposing substrate materials of dual-energy CT images with the trained CNN and the CNN parameter theta obtained in step 2. Through establishment of the dual-input dual-output CNNmodel and cross convolution, reasonable shunt of different substrate materials of high-energy CT images and low-energy CT images is realized, so that quality of decomposition of the substrate materials of the dual-energy CT images is improved effectively.

Description

technical field [0001] The present invention relates to the technical field of medical dual-energy image decomposition and image processing, in particular to a dual-energy CT image decomposition method, in particular to a convolutional neural network-based dual-energy CT image decomposition method. Background technique [0002] Dual-energy CT image reconstruction has been increasingly used in medical imaging, safety inspection, nondestructive testing and other fields. Compared with traditional single-energy spectral CT imaging technology, dual-energy CT can use image attenuation information under different energy spectra to realize Identification of different substance materials. Dual-energy CT technology has broken the physical limitations of traditional single-energy spectrum CT, and has become a hot and difficult issue in the field of CT imaging. [0003] The core theory of dual-energy CT imaging technology is the dual-energy CT image reconstruction algorithm, in which t...

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): G06T5/00G06N3/04G06N3/08
CPCG06N3/08G06T5/006G06T2207/10081G06T2207/20084G06T2207/20081G06N3/045
Inventor 闫镔李磊张文昆梁宁宁席晓琦王林元韩玉
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
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