Image processing method and device, training method and device, electronic terminal and storage medium

An image processing, image technology, applied in the field of image processing

Pending Publication Date: 2021-05-07
深圳市联影高端医疗装备创新研究院
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with low-dose CT scans, significant noise and 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
  • Image processing method and device, training method and device, electronic terminal and storage medium
  • Image processing method and device, training method and device, electronic terminal and storage medium
  • Image processing method and device, training method and device, electronic terminal and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] figure 1 It is a schematic flowchart of an image processing method provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of using low-dose CT images to generate high-dose predicted CT images. The method can be executed by the image processing device provided by the embodiment of the present invention, the device is realized by software and / or hardware, and is preferably configured in an electronic terminal installed with image processing function software, such as a computer.

[0038] see figure 1 , the image processing method provided by the present embodiment includes the following steps:

[0039] S110. Receive a CT image of a first dose.

[0040] The radiation dose of a CT image is related to the tube current in the tube of the scanning device. Generally, the radiation dose of CT scanning can be reduced by reducing the magnitude of the tube current during scanning. As the tube current decreases, the number of photons reachi...

Embodiment 2

[0052] The image processing method provided in this embodiment can be combined with various optional solutions in the image processing method provided in the above embodiments. The raw image processing method provided in this embodiment optimizes the construction of the adversarial loss function and the cyclic loss function, and can train the generator and the discriminator in the preset generative adversarial network according to the adversarial loss function and the cyclic loss function.

[0053] figure 2 It is a schematic flowchart of an image processing method provided in Embodiment 2 of the present invention. see figure 2 , the image processing method provided by the present embodiment includes the following steps:

[0054] S210. Construct a preset generative adversarial network including a first generator, a second generator, a first discriminator, and a second discriminator.

[0055] In this embodiment, the preset generation confrontation network adopts the Cycle G...

Embodiment 3

[0073] The image processing method provided in this embodiment can be combined with various optional solutions in the image processing method provided in the above embodiments. The image processing method provided in this embodiment optimizes the training steps of the preset generative adversarial network, for example, while the first generator is trained with the preset generative adversarial network based on the adversarial loss function and the cyclic loss function, it also includes: the first A generator is trained with the preset generation confrontation network based on the identity loss function; and / or, for example, when the first generator is trained with the preset generation confrontation network based on the confrontation loss function and the loop loss function, it also includes: the first The generator is trained with a preset generative adversarial network based on a fully variational loss function.

[0074] By introducing an identity loss function in the traini...

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 embodiment of the invention discloses an image processing method and device, an electronic terminal and a storage medium, and the method comprises the steps: inputting a received CT image of a first dose into a first generator to generate a predicted CT image of a second dose, wherein the second dose is greater than the first dose, the first generator is included in a preset generative adversarial network in a training process, and is trained along with the preset generative adversarial network based on an adversarial loss function and a cyclic loss function, and the loop loss function comprises an image-based style loss function and/or a perception loss function. And the first generator in the trained network is utilized to generate a high-dose prediction CT image according to the low-dose CT image, so that noise and artifacts in the low-dose CT image are inhibited, and the image quality is improved.

Description

technical field [0001] Embodiments of the present invention relate to image processing technologies, and in particular, to an image processing method, training method, device, electronic terminal, and storage medium. Background technique [0002] Computed Tomography (CT) is a technology that scans a layer of a certain thickness of the human body with a ray beam, and constructs an image based on the radiation received by the detector that passes through the layer. CT scan is one of the imaging methods widely used in medicine and can be used for the examination of many diseases. [0003] Since the radiation used in the CT scanning process has certain risks, it is often used to avoid this risk in clinical practice by reducing the radiation dose. However, through low-dose CT scanning, there are obvious noise and artifacts in the reconstructed low-dose CT images. Therefore, there is an urgent need for an image processing method that can suppress noise and artifacts in low-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
IPC IPC(8): G06T11/00G06T5/00G06N3/04
CPCG06T11/008G06T5/002G06T2207/20081G06N3/045
Inventor 韦子权
Owner 深圳市联影高端医疗装备创新研究院
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