A Deep Learning-Based Method for Incomplete Data Reconstruction of X-ray Absorption Contrast Computed Tomography

A deep learning and tomography technology, applied in image data processing, calculation, 2D image generation, etc., can solve the problems of image loss of details, insufficient use of CT imaging system information, deformation of original image structure, etc., and achieve high image quality. , the effect of fast calculation speed and simple calculation process

Active Publication Date: 2021-03-30
BEIHANG UNIV +1
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing reconstruction technology based on deep learning only post-processes the reconstruction results, and does not make full use of all the information obtained by the CT imaging system, resulting in the loss of some details in the processed image, which makes the original image structure deformed

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
  • A Deep Learning-Based Method for Incomplete Data Reconstruction of X-ray Absorption Contrast Computed Tomography
  • A Deep Learning-Based Method for Incomplete Data Reconstruction of X-ray Absorption Contrast Computed Tomography
  • A Deep Learning-Based Method for Incomplete Data Reconstruction of X-ray Absorption Contrast Computed Tomography

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0034] figure 1 The flow chart of the method for reconstructing incomplete data of X-ray absorption contrast computed tomography based on deep learning provided by the embodiment of the present invention, that is, the reconstruction of incomplete data of X-ray absorption contrast computed tomography based on deep learning of the present invention method. The embodiment of the present invention provides a reconstruction method based on deep learning for common incomplete data situations (such as sparse angle and limited angle) of X-ray absorption contrast computed tomography imaging. The specific steps of the method are as follows:

[0035] Step S101. Reconstruct the incomplete projection sequence obtained by the CT imaging system with the FBP reconstruction algorithm to obtain an initial reconstructed image. Due to the incomplete projection se...

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 for reconstructing incomplete data of X-ray absorption contrast computed tomography based on deep learning. The method comprises the following steps: using a filtering back-projection reconstruction algorithm to obtain an initial reconstruction image; performing forward projection on the above-mentioned initial reconstruction image Obtain the projection sequence polluted by artifacts; use deep learning technology to process the above-mentioned projection sequence contaminated by artifacts to obtain a projection sequence without artifacts; use the filtered back-projection reconstruction algorithm to reconstruct the above-mentioned projection sequence without artifacts, Obtain the final reconstruction result image. Compared with the traditional incomplete data reconstruction method, the embodiment of the present invention has a simple calculation process, fewer parameters that need to be manually set, faster calculation speed, and higher image quality.

Description

technical field [0001] The invention relates to the technical field of X-ray absorption contrast computed tomography reconstruction, in particular to a method for reconstructing incomplete X-ray data based on deep learning. Background technique [0002] In the X-ray absorption contrast computed tomography (Computed Tomography, referred to as CT) system, the X-ray source emits X-rays and passes through a certain area of ​​the object to be detected from different angles. Receive rays. Then, according to the different degrees of attenuation of the rays at each angle, a certain reconstruction algorithm is used to perform calculations to reconstruct the ray linear attenuation coefficient distribution mapping image of the scanned area of ​​the object, so as to realize the reconstruction of the image by projection and reproduce the image of the object in the area without loss. Characteristics such as medium density, composition and structural morphology. [0003] Reconstruction a...

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 Patents(China)
IPC IPC(8): G06T11/00G06N3/04
CPCG06T11/003G06N3/045G06T11/006G06T2211/436G01N2223/419G01N2223/401G06T2211/441G01N23/046G01N23/083G06T11/008G06T2211/421
Inventor 傅健董建兵张昌盛
Owner BEIHANG 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