GAN-based method for converting multimodal low-dose CT to high-dose CT

A low-dose, high-dose technology, applied in the field of medical image processing, can solve the problems that the data of commercial scanners is not easy to provide to researchers, and the noise distribution in the image domain cannot be accurately determined.

Active Publication Date: 2020-12-25
SUN YAT SEN UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to solve this inherent physical problem, many methods have been designed in the past to improve the image quality of low-dose CT (Low-Dose CT, LDCT). The traditional methods include model-based iterative reconstruction, filtering before reconstruction, and reconstructed images. Post-processing, the processing technology before reconstruction is specific to the scanner, and the data of commercial scanners is not easy to provide to researchers, and the processing technology after reconstruction cannot accurately determine the noise distribution in the image domain, so that the algorithm cannot be used in Optimal trade-off between structure preservation and noise reduction

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
  • GAN-based method for converting multimodal low-dose CT to high-dose CT
  • GAN-based method for converting multimodal low-dose CT to high-dose CT
  • GAN-based method for converting multimodal low-dose CT to high-dose CT

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Such as figure 1 As shown, the implementation steps of the method for converting GAN-based multimodal low-dose CT to high-dose CT in this embodiment include:

[0068] 1) Input low-dose CT of any modality (indicated as l in the figure i );

[0069] 2) Perform two-dimensional discrete wavelet transform (represented as Wavelet in the figure) on low-dose CT to obtain multiple decomposition results;

[0070] 3) Input the low-dose CT and its multiple decomposition results into the encoder (indicated as EC in the figure) in the trained GAN network for encoding (the result in the figure is expressed as code i ), and then (the encoding result code i ) through the decoder in the GAN network (represented as DC in the figure) to decode the encoding result to obtain the corresponding high-dose modal image (represented as h in the figure i,t ).

[0071] Such as figure 1 As shown, in step 2), two-dimensional discrete wavelet transform is performed on low-dose CT to obtain multip...

Embodiment 2

[0140] This embodiment is basically the same as Embodiment 1, and the main difference is that the training methods for the GAN network are different. Its main reason is: because the high-dose CT training data set with task label that embodiment one requires is difficult to obtain, existing public data set mostly is: unlabeled low-dose high-dose CT registration data set (data set A ); low-dose CT dataset with task labels (Dataset B). On the basis of following the modular method of Example 1, this example designs a supplementary scheme, adopts a hybrid supervised learning method, conducts supervised task processor training on dataset B, and performs supervised low-dose CT on dataset A Switch to high-dose CT training, and then combine the trained modules to perform unsupervised training on the labeled data set B, and then convert to generate high-quality high-dose CT images.

[0141] Such as Figure 9 As shown, step 3) of this embodiment also includes the step of training the G...

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 and system for converting multi-mode low-dose CT into high-dose CT based on a GAN, and a medium. The method comprises the steps: inputting low-dose CT in any mode; performing two-dimensional discrete wavelet transform on the low-dose CT to obtain a plurality of decomposition results; and inputting the low-dose CT and a plurality of decomposition results into a trained encoder in the GAN network, encoding, and decoding the encoding result through a decoder in the GAN network to obtain a corresponding high-dose modal image. The method is based on the wide development of GAN in multi-domain conversion and the decomposition capability of traditional wavelet transform, the low-dose CT and the wavelet transform result are inputted into the trained encoder in theGAN network together for encoding, the encoding result is decoded through the decoder in the GAN network to obtain the corresponding high-dose modal image, and low-dose CT image conversion in any modeis conveniently converted to the high-dose CT image.

Description

technical field [0001] The present invention relates to the field of medical image processing, in particular to a method, system and medium for converting multi-modal low-dose CT into high-dose CT based on GAN (Generative Adversarial Network), which is used for low-dose CT of any modality by generating countermeasures. Network conversion generates high-dose CT. Background technique [0002] As one of the modern mainstream medical images, the detection method of computer tomography (Computed tomography, CT) has been widely used in clinical diagnosis in various clinical fields. With the popularization and development of CT scanning, more and more people have begun to pay attention to the possible radiation hazards of CT scanning to the human body. CT scans are generally accompanied by high levels of x-ray radiation, and medical research has shown that excessive x-ray exposure may induce metabolic abnormalities or cancer, leukemia or other genetic diseases. The researchers ho...

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): A61B6/03
CPCA61B6/03A61B6/52
Inventor 苏琬棋瞿毅力邓楚富王莹陈志广卢宇彤
Owner SUN YAT SEN 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