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

CBCT image reconstruction method based on deep learning and electronics noise simulation

A noise simulation and deep learning technology, applied in the field of image processing, can solve the problem of inability to obtain high-precision spiral CT images at the same time, and achieve the effects of fast generation, improved quality, and low scanning dose.

Active Publication Date: 2022-03-25
SICHUAN UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] The purpose of the present invention is: in order to solve the above-mentioned technical problem that the high-precision spiral CT image and the registered CBCT image of the same scanning object in the same body position cannot be obtained at the same time, the present invention provides a method for deep learning and electronic noise simulation. CBCT Image Reconstruction Method

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
  • CBCT image reconstruction method based on deep learning and electronics noise simulation
  • CBCT image reconstruction method based on deep learning and electronics noise simulation
  • CBCT image reconstruction method based on deep learning and electronics noise simulation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] Such as figure 1 As shown, the present embodiment provides a CBCT image reconstruction method of deep learning and electronic noise simulation, including the following steps:

[0062] Step 1: Acquire and process data;

[0063] Acquire several high-resolution CT images, and generate simulated low-resolution CBCT images after noise processing on the high-resolution CT images;

[0064] Step 2: Build a deep neural network model;

[0065] Step 3: Train the deep neural network model;

[0066] Use the high-resolution CT images and low-resolution CBCT images in step 1 to train the deep neural network model built in step 2;

[0067] Step 4: Reconstruct the CBCT image;

[0068] Input the collected low-resolution CBCT images into the deep neural network model trained in step 3, and the deep neural network model outputs high-resolution CT images.

[0069] Use high-resolution CT images to generate simulated low-resolution CBCT images, thereby obtaining CT images and CBCT images...

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 CBCT image reconstruction method based on deep learning and electronic noise simulation, and relates to the technical field of image processing, which generates a simulated low-resolution CBCT image after performing noise processing on a high-resolution CT image, and trains a deep neural network by using the high-resolution CT image and the low-resolution CBCT image to obtain a CBCT image. And the trained deep neural network model is adopted, so that the high-resolution CT image can be obtained on the basis of subsequently inputting the low-resolution CBCT image, and the problem that the high-precision spiral CT image and the registration CBCT image of the same scanned object under the same body position cannot be obtained at the same time in the prior art is solved. Compared with an existing reconstruction method based on prior information, the scheme has the advantages that the scanning dose is low, the generation speed is high, and a high-precision image can be generated within one minute.

Description

technical field [0001] The present invention relates to the technical field of image processing, and more specifically to the technical field of CBCT image reconstruction methods for deep learning and electronic noise simulation. Background technique [0002] The International Agency for Research on Cancer under the World Health Organization released the latest global cancer statistics in 2018. In 2018, there were 18.1 million new cancer cases worldwide and 9.6 million deaths, further increasing the global cancer burden. Worldwide, 1 / 5 men and 1 / 6 women will suffer from cancer, and 1 / 8 men and 1 / 11 women will die from it. Radiation therapy is a treatment method that uses radiation to treat tumors. About 70% of cancer patients need radiation therapy during the treatment of cancer, and about 40% of cancers can be cured with radiation therapy. The role and status of radiotherapy in tumor treatment has become increasingly prominent, and it has become one of the main means of tr...

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): G06T11/00G06T3/40G06N3/04
CPCG06T11/005G06T11/008G06T3/4076G06N3/045
Inventor 宋莹张伟康苏嘉崇王强王雪桃柏森
Owner SICHUAN UNIV
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