Training method of low-dose image denoising network, denoising method of low-dose image

A training method and low-dose technology, applied in computer equipment and storage media, low-dose image de-noising method, and low-dose image de-noising network training field, can solve problems such as poor robustness and poor imaging quality, and achieve improved The effect of robustness

Active Publication Date: 2022-05-20
SHENZHEN INST OF ADVANCED TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The principle of rational use of low dose (As Low As Reasonably Achievable, ALARA) requires that the radiation dose to patients should be reduced as much as possible under the premise of satisfying clinical diagnosis, and as the dose decreases, more noise will appear in the imaging process, thus Therefore, research and development of new low-dose CT imaging methods, which can not only ensure the quality of CT imaging but also reduce harmful radiation doses, have important scientific significance and application prospects in the field of medical diagnosis
Because the radiation dose used in different anatomical parts will be different, and the existing low-dose CT imaging method is usually based on the same anatomical part, which is less robust

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
  • Training method of low-dose image denoising network, denoising method of low-dose image
  • Training method of low-dose image denoising network, denoising method of low-dose image
  • Training method of low-dose image denoising network, denoising method of low-dose image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] refer to figure 1 , the training method of the low-dose image denoising network in the present embodiment includes steps:

[0047] S1. Obtain a training data set, wherein the training data set includes a plurality of input parameter groups, and each input parameter group includes a standard dose image and a low dose image;

[0048] S2. Establish a training network, which includes a low-dose image denoising network and a low-dose image generation network;

[0049] S3. Input the training data set into the training network, and the low-dose image denoising network generates the estimated dose level of the low-dose image and the estimated standard dose image based on the low-dose image; the low-dose image generation network generates the estimated image and the estimated dose level based on the standard dose generating a low dose estimation image;

[0050] S4. Construct a loss function according to the low dose image, the low dose estimated image, the standard dose image,...

Embodiment 2

[0090] refer to Figure 6 ~ Figure 7 , the training network in this embodiment also includes a low-dose image discrimination network D1, and each input parameter set in this embodiment also includes a dose level value corresponding to a low-dose image. A low-dose image discriminative network is used to generate dose class predictions from low-dose images and low-dose estimation images.

[0091] Specifically, the low-dose image discrimination network D1 includes a plurality of first numerically constrained layers 31 , a first tiling layer 32 , and a first fully connected layer 33 connected in sequence.

[0092] The first numerically constrained layer 31 includes a convolutional layer 310, a regularization layer 311, and an activation function 312 connected in sequence, wherein the activation function 312 is a Leaky ReLU function. This embodiment exemplifies that the low-dose image discrimination network D1 includes seven first numerically constrained layers 31, wherein the net...

Embodiment 3

[0102] refer to Figure 8-11 , the training network in this embodiment further includes a standard dose image discrimination network D2, and the standard dose image discrimination network D2 is used to generate a second authenticity prediction value according to the standard dose image and the standard dose estimation image. The low-dose image discrimination network D1 in this embodiment further includes a second fully connected layer 34 connected to the first tiling layer 32 .

[0103] Specifically, the standard dose image discrimination network D2 includes a plurality of second numerically constrained layers 41 , a second tiling layer 42 , and a third fully connected layer 43 connected in sequence.

[0104] The second numerically constrained layer 41 includes a convolutional layer 410, a regularization layer 411, and an activation function 412 connected in sequence, wherein the activation function 412 is a Leaky ReLU function. This embodiment exemplifies that the standard dos...

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 provides a low-dose image denoising network training method, a low-dose image denoising method, computer equipment and storage media, and the low-dose image denoising network training method in the low-dose image denoising network provided by the invention According to the low-dose image, the estimated dose level of the low-dose image and the standard dose estimated image will be generated, and then the low-dose estimated image will be generated according to the standard dose estimated image and the estimated dose level. The image and the standard dose estimation image construct a loss function, optimize the loss function, and obtain the parameters of the low-dose image denoising network, thereby fusing the dose level information into the image reconstruction process, improving the robustness of the denoising method and The quality of the reconstructed image.

Description

technical field [0001] The invention relates to the technical field of image reconstruction, in particular to a training method for a low-dose image denoising network, a low-dose image denoising method, computer equipment and a storage medium. Background technique [0002] Computed tomography (CT) is an important imaging method to obtain the internal structure information of objects in a non-destructive way. It has many advantages such as high resolution, high sensitivity and multi-level, and is one of the medical imaging diagnostic equipment with the largest installed capacity in my country. It is widely used in various medical clinical examination fields. However, due to the need to use X-rays in the process of CT scanning, as people gradually understand the potential hazards of radiation, the issue of CT radiation dose has attracted more and more attention. The principle of rational use of low dose (As Low As Reasonably Achievable, ALARA) requires that the radiation dose ...

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): G06T5/00
CPCG06T5/002G06T2207/10081G06T2207/20081G06T2207/10104G06T2207/10108G06T2207/20084G06T2207/30061
Inventor 郑海荣胡战利黄振兴梁栋刘新
Owner SHENZHEN INST OF ADVANCED TECH
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