Digital X-ray image denoising method based on trainable joint bilateral filter

A bilateral filter and X-ray technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problem of reducing image quality, appearance, texture and other details that are difficult to substantially improve, and affect the follow-up processing of DR images, etc. problem, to achieve a robust effect

Pending Publication Date: 2022-05-13
SOUTHEAST UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is an obvious positive correlation between imaging quality and radiation dose, and the reduction of radiation dose usually introduces noise and artifacts, reducing the imaging quality; in addition, these noises will also affect the subsequent processing of DR images, such as image segmentation, recognition Wait
[0003] Commonly used DR image denoising methods, such as least squares filtering, mean filtering, and bilateral filtering, can maintain the overall quality of the image under low-dose conditions, but it is difficult to substantially improve the details of local appearance and texture.

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
  • Digital X-ray image denoising method based on trainable joint bilateral filter
  • Digital X-ray image denoising method based on trainable joint bilateral filter
  • Digital X-ray image denoising method based on trainable joint bilateral filter

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Example 1: see figure 1 , a digital X-ray image denoising method based on a trainable joint bilateral filter, the specific steps are as follows:

[0036] Step 1. Randomly read 128×128 low-dose digital X-ray images as the input of the EDCNN network, and the corresponding normal dose images as labels, and jointly train the EDCNN network.

[0037] Step 2, use the trained EDCNN network to initially remove the noise in the image, and generate a guide image for training the parameters of the joint bilateral filter.

[0038] Specifically, the EDCNN network consists of 1 edge enhancement module and 8 convolutional blocks, such as figure 2 shown. Among them, the convolution block is composed of the order of "1*1 convolution + LeakyReLU activation layer + 3*3 convolution + LeakyReLU activation layer", such as image 3 shown. The edge enhancement module consists of 4 Sobel operators in vertical, horizontal and 2 diagonal directions, namely:

[0039]

[0040] The EDCNN net...

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 plug-and-play and trainable combined bilateral filtering processing method which is used for low-dose digital X-ray imaging. Firstly, a guide image of the joint bilateral filter is generated through a deep neural network, then the obtained guide image and an original noise image are used for jointly training the joint bilateral filter, and finally a denoised image is obtained. According to the invention, under the condition that the X-ray dose is greatly reduced, a high-quality image can be quickly generated, and an effective denoising method is provided for a low-dose digital X-ray image.

Description

technical field [0001] The invention relates to a digital X-ray image denoising method based on a trainable joint bilateral filter, which belongs to the field of computer image processing. Background technique [0002] Digital X-ray imaging (DR) is an advanced X-ray photography technology formed by the combination of computer digital image processing technology and X-ray radiation technology. X-rays belong to ionizing radiation, and its excessive or inappropriate use may also damage normal organs. Rationalization of the use of X-ray imaging and optimization of the associated radiation doses are essential to protect the health of patients. However, there is an obvious positive correlation between imaging quality and radiation dose, and the reduction of radiation dose usually introduces noise and artifacts, reducing the imaging quality; in addition, these noises will also affect the subsequent processing of DR images, such as image segmentation, recognition Wait. [0003] C...

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): G06T5/00G06N3/04
CPCG06T5/002G06T2207/10116G06T2207/20028G06N3/045
Inventor 陈阳吴钱御
Owner SOUTHEAST 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