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

Model generation method, image processing method and medical imaging equipment

A model generation and model technology, applied in the field of image processing, can solve problems such as high cost and poor security, and achieve the effect of good security and cost reduction

Active Publication Date: 2017-12-26
SHANGHAI UNITED IMAGING HEALTHCARE
View PDF3 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the embodiment of this solution provides a model generation method, an image processing method and a medical imaging device to solve the problems of poor security and high cost of DR devices with grids in the prior art

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
  • Model generation method, image processing method and medical imaging equipment
  • Model generation method, image processing method and medical imaging equipment
  • Model generation method, image processing method and medical imaging equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] figure 1 An example flow chart of the model generation method provided by the embodiment of the present invention. Such as figure 1 As shown, in this embodiment, the model generation method may include the following steps:

[0069] S101. Under specified imaging parameters, acquire first image data including scattering components, and acquire second image data corresponding to the first image data with suppressed scattering components.

[0070] S102, select the data at the specified position in the first image data or the related data of the first image data as input data, and select the position corresponding to the specified position in the second image data or the related data of the second image data The data at , as label data. It should be noted that the input data and label data in this application are both training data in the neural network, and the label data is used as the target reference, and the similarity with the label data is obtained by inputting the...

Embodiment 2

[0125] Through the model generation method in the foregoing embodiment 1, scatter correction models under various imaging parameters can be obtained. Using these scatter correction models, scatter correction can be performed on the DR image output by the DR device without a grid to remove the DR The scattering component in the image improves the DR image quality.

[0126] Wherein, the scattering correction models under various imaging parameters can be composed into a model library, and the model library is stored in the DR device or in an external device capable of data communication with the DR device. In this way, when the DR device needs to obtain the scatter correction model, it obtains the scatter correction model from the model library of the DR device itself or from the model library of the external device.

[0127] To this end, an embodiment of the present invention provides an image processing method.

[0128] image 3 It is an example flow chart of the image proce...

Embodiment 3

[0139] The embodiment of the present invention also provides an image processing method, which may include the following steps:

[0140] Obtain image data to be processed including scattering components;

[0141] Using the neural network-based scatter correction model to perform scatter correction on the image data to be processed to obtain the corrected image data;

[0142] The neural network-based scatter correction model is obtained through the following steps:

[0143] acquiring a plurality of training data pairs, each training data pair comprising first image data comprising a scatter component, second image data corresponding to the first image data with the scatter component suppressed;

[0144] machine learning to obtain a mapping relationship between the first image and the second image data;

[0145] According to the mapping relationship, the model parameters corresponding to the neural network model are determined, so as to obtain the neural network-based scatteri...

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

An embodiment of the invention provides a model generation method, an image processing method and medical imaging equipment. The model generation method includes: under specified imaging parameters, acquiring first image data with scattering component and second image data without scattering component, selecting input data from the first image data or related data thereof, and selecting label data from the second image data or related data thereof; according to the input data and the label data, performing machine learning by adopting a neutral network to generate a scattering-correction model. Machine learning is performed by the aid of the neutral network to generate the scattering-correction model, the scattering-correction model is used for performing scattering correction on DR (digital radiography) images, increasing of radiation dose of X-rays is not needed, better safety is achieved, adding of a grid in DR equipment is not needed, cost of the DR equipment can be reduced, and problems that the DR equipment with the grid is poor in safety and high in cost in the prior art are solved to some extent.

Description

【Technical field】 [0001] The proposal relates to the technical field of image processing, in particular to a model generation method, an image processing method and medical imaging equipment in digital radiography. 【Background technique】 [0002] High-energy rays have strong penetrating ability and can pass through many substances that are opaque to visible light. Medical imaging equipment uses this penetrating ability of high-energy rays to image the human body. For example, a DR (Digital Radiography, digital radiography) device is a device that uses X-rays to irradiate a target to be detected, and collects X-rays that pass through the target to be detected by an X-ray detector for imaging. [0003] When the target to be detected is irradiated with high-energy rays, after the rays pass through the target to be detected, not only primary radiation but also scattered radiation are generated. Scattered radiation will produce additional exposure, which is superimposed on the ...

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): G06T7/80G06T11/00G06N3/04G06N3/08H04N5/32
CPCH04N5/32G06N3/08G06T7/80G06T11/005G06T2207/10081G06N3/045
Inventor 宋燕丽周鑫邢潇丹陈刚李强
Owner SHANGHAI UNITED IMAGING HEALTHCARE
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com