Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-resolution network missing CT projection data estimation method based on multiple discriminators

A technology of projection data and discriminator, which is applied in the field of estimation of missing CT projection data based on multi-discriminator multi-analysis network, can solve problems such as insufficient clarity of CT projection data, and achieve the effect of improving clarity and quality

Pending Publication Date: 2020-06-09
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the purpose of the present invention is to provide a method for estimating missing CT projection data based on a multi-discriminator multi-analysis network to solve the problem of insufficient definition of CT projection data existing 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
  • Multi-resolution network missing CT projection data estimation method based on multiple discriminators
  • Multi-resolution network missing CT projection data estimation method based on multiple discriminators
  • Multi-resolution network missing CT projection data estimation method based on multiple discriminators

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0059] This embodiment is a method for estimating missing CT projection data based on a multi-discriminant multi-analysis network. In practical applications, the following steps are included:

[0060] (1) The training data is 124 complete CT projection data, and the image size is 720×1024 pixels;

[0061] Simulate the CT projection data image in the case of sparse and missing CT scan angles in medicine, that is, occlude the image in the vertical direction, and set the pixel value of the area to 0. In this embodiment, 4 occlusion areas are set in the scanning angle, which is reflected in the projection data image as follows: the initial pixel points of occlusion are [0, 0], [0, 256], [0, 512], [0 , 768], the width of the block is 128 pixels, and the height is 720 pixels. The processed missing CT projection data image is a sparse missing projection data image with 4 missing regions.

[0062] (2) The multi-analysis network model of multi-discriminator trains 124 images each tim...

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 multi-resolution network missing CT projection data estimation method based on multiple discriminators. The method comprises the steps of acquiring an incomplete CT projection data image; inputting the incomplete CT projection data image into a multi-analytic network model to obtain a complete CT projection data image; and carrying out reconstruction processing on the complete CT projection data image through a convolution filtering back projection method to obtain a CT image. The image definition of the predicted CT projection data and the consistency of the boundary of the missing area can be remarkably improved, the quality of the CT image is further improved, and the peak signal-to-noise ratio and the structural similarity value reflect the superiority of themethod.

Description

technical field [0001] The invention relates to the technical field of image reconstruction, in particular to a method for estimating missing CT projection data based on a multi-discriminator-based multi-analysis network. Background technique [0002] As a routine and effective clinical medical diagnostic tool at present, X-ray computed tomography provides a wealth of human organ tissue information for clinicians to diagnose. However, relevant studies have shown that a complete CT 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. [0003] One of the important ways to reduce the radiation dose of patients clinically is to reduce the CT scanning range, that is, to limit the rotation angle range of the detector to a range less than the standard, thereby greatly reducing the X-ray radiation dose received by patients as a whole . 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 Applications(China)
IPC IPC(8): G06T5/00G06N3/04G06N3/08
CPCG06N3/08G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30004G06N3/045G06T5/77
Inventor 戴修斌林语萱刘天亮晏善成
Owner NANJING UNIV OF POSTS & TELECOMM