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

Low-dose CBCT image reconstruction method based on three-dimensional adversarial generation network

An image reconstruction and adversarial technology, which is applied in the field of medical image processing, can solve the problems of inability to meet the needs of clinical diagnosis and poor quality of reconstructed CT images, so as to improve the efficiency of clinical diagnosis, reduce the amount of X-ray radiation, and shorten the acquisition time.

Inactive Publication Date: 2019-09-27
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the deficiencies of the prior art, the purpose of the present invention is to provide a low-dose CBCT image reconstruction method based on a three-dimensional confrontational generation network, which solves the technical problems in the prior art that the quality of the reconstructed CT image is poor and cannot meet the needs of clinical diagnosis

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
  • Low-dose CBCT image reconstruction method based on three-dimensional adversarial generation network
  • Low-dose CBCT image reconstruction method based on three-dimensional adversarial generation network
  • Low-dose CBCT image reconstruction method based on three-dimensional adversarial generation network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The method of the present invention is divided into a training stage and a testing stage. The steps include: first, using the sinusoidal image of the complete projection data and the sinusoidal image of the incomplete projection data to train the adversarial generation network model, and obtain a three-dimensional adversarial network model that can generate high-quality sinusoidal images. Generate a network model model; secondly, use the trained model to predict the missing part of the sinusoidal image of the incomplete projection data, and obtain the generated sinusoidal image of the complete projection; finally, use the FDK method to reconstruct the CT from the sinusoidal image of the generated complete projection data image. The invention can predict missing projection data and further reconstruct high-quality CT images conforming to clinical diagnosis.

[0036] The present invention will be further described below in conjunction with the accompanying drawings. The ...

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 low-dose CBCT image reconstruction method based on a three-dimensional adversarial generation network, and belongs to the technical field of medical image processing. The method comprises the following steps: constructing a three-dimensional adversarial resistance generation network model; training a three-dimensional adversarial resistance generation network model through the sine image and the corresponding projection data; inputting the test image into the trained adversarial resistance generation network model, and predicting the missing part of the sine image of the incomplete projection data to obtain a sine image of complete projection; and reconstructing a CT image according to the sine image of the complete projection data. The method effectively shortens the acquisition time of the cone beam projection data, and improves the clinical diagnosis efficiency.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a low-dose CBCT image reconstruction method based on a three-dimensional confrontational generation network. Background technique [0002] Cone beam computed tomography (CBCT) is a medical imaging technique that can quickly and directly obtain three-dimensional CT images. However, relevant studies have shown that a complete CBCT scan is usually accompanied by a high level of ionizing radiation, and high doses of ionizing radiation can induce abnormal metabolism in the human body and even cancer, leukemia and other diseases. Therefore, how to reduce the dose of X-rays while ensuring the quality of reconstructed images to meet the requirements of clinical diagnosis has become the focus of research in the field of medical image processing. [0003] One of the important methods to reduce the radiation dose of patients in clinical practice is to reduce the scanning r...

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): G06T11/00
CPCG06T11/006
Inventor 戴修斌叶佳豪刘天亮晏善成
Owner NANJING UNIV OF POSTS & TELECOMM
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