Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for enhancing CT image quality and resolution based on deep learning

A CT image and deep learning technology, applied in the field of image processing, can solve the problems of image detail loss, image denoising, etc., and achieve the effect of improving the quality of CT images

Pending Publication Date: 2021-03-02
SUBTLE MEDICAL TECH
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem of image denoising and image detail loss after super-resolution processing in the prior art, and propose a method for enhancing CT image quality and resolution based on deep learning

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
  • Method for enhancing CT image quality and resolution based on deep learning
  • Method for enhancing CT image quality and resolution based on deep learning
  • Method for enhancing CT image quality and resolution based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] Such as figure 1 As shown, the present embodiment proposes a method for enhancing CT image quality and resolution based on deep learning, which mainly includes the following steps:

[0025] S1. Preprocessing the collected clinical data to obtain a data set.

[0026] S2. Construct a deep learning model including a generator network, a decision network and a perception network.

[0027] S3. Constructing a loss function.

[0028] S4. Utilize the data set and the loss function to update the parameters of the iterative generation network to obtain a trained deep learning model.

[0029] S5. Input the low-quality and low-resolution images into the trained deep learning model to obtain high-quality and high-resolution images.

[0030] Specifically, the process of preprocessing clinical data in step S1 includes the following:

[0031] S11. Acquire low-quality CT images with low radiation dose and low resolution and high-quality CT images with normal radiation dose and high ...

Embodiment 2

[0055] The difference from Example 1 is that in this example, the collected clinical data are preprocessed to obtain the data set. The low-quality CT image is obtained by three-dimensional interpolation method to obtain the same size as the high-quality CT image, and then obtained after cropping. Pairs of small chunks of data.

[0056] The generation network can be but not limited to U-Net structure, and the decision device can be but not limited to Patch GAN. The use of Patch GAN can take into account the influence of different parts of the image, and solve the problem of inconsistent output images caused by only one corresponding output for one input. precise question.

[0057] Unlike the simulation training set used in the prior art, the present invention obtains a real training data set by preprocessing real clinical data, so that the deep learning model can be applied to clinical practice. The deep learning model of the present invention can optimize low-radiation and lo...

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 enhancing CT image quality and resolution based on deep learning. The method comprises the following steps: S1, preprocessing acquired clinical data to obtain a data set; S2, constructing a deep learning model comprising a generation network, a decision device network and a sensing network; S3, constructing a loss function; S4, updating parameters of the iterative generation network by using the data set and the loss function to obtain a trained deep learning model; and S5, inputting the low-quality low-resolution image into the trained deep learning modelto obtain a high-quality high-resolution image. According to the invention, a deep learning model is constructed based on deep learning, and clinical data is preprocessed to obtain a data set, so thatthe influence of dislocation of data acquired at different times in space due to patient displacement or other reasons can be reduced; by combining a deep learning model of a loss function, the end-to-end processing of two tasks of CT image quality improvement and super-resolution can be realized to directly obtain a final result.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method for enhancing CT image quality and resolution based on deep learning. Background technique [0002] Computed tomography (CT) is one of the most important imaging and diagnostic modalities in modern hospitals and clinics. In order to directly obtain high-quality, high-resolution CT images during the scanning process, it is necessary to increase the cost of the scanning equipment and increase the radiation dose during the scanning process. However, according to related studies, X-rays during CT scanning may cause genetic damage and induce cancer at a probability related to radiation dose. Therefore, in order to improve the quality and resolution of CT images while avoiding or reducing the risk of damage to the health of patients during scanning, it is necessary to reconstruct clinical CT data containing a lot of noise and low resolution to obtain low-nois...

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): G06T11/00G06T3/40G16H30/20G06N3/04G06N3/08
CPCG06T11/003G06T3/4053G16H30/20G06N3/08G06T2211/424G06N3/045G06T3/4046G06T7/0012G16H30/40G16H50/20G16H50/70G06T3/60G06T2207/10081G06T2207/20132
Inventor 龚南杰王嘉宸项磊
Owner SUBTLE MEDICAL 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
Eureka Blog
Learn More
PatSnap group products