Computed tomography (CT) image generation method used for attenuation correction of positron emission tomography (PET) images

A CT image, attenuation correction technology, applied in the field of medical image reconstruction, can solve problems such as the increase of correction errors, and achieve the effect of reducing pressure, reducing costs, and enhancing costs

Active Publication Date: 2020-07-24
ZHEJIANG LAB +1
View PDF7 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method relies on accurate segmentation, but when there are soft tissue areas with continuous bone transformation and similar tissue areas with large density gradients in the measurement area, it is not accurate to use only three discrete values ​​instead, and it will cause a large error
If the registration of the segmented CT image and PET image is inaccurate, the correction error will also increase

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
  • Computed tomography (CT) image generation method used for attenuation correction of positron emission tomography (PET) images
  • Computed tomography (CT) image generation method used for attenuation correction of positron emission tomography (PET) images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] Such as figure 1 It is a flowchart of a CT image generation method for PET image attenuation correction of the present invention, the method includes the following steps:

[0022] Step 1: Use PET / CT equipment to collect several patients at T 1 The CT image and PET image at any time, the pixels with the same coordinates in the two images correspond to the same position in the body; then collect the patient at T 2 The CT image and the PET image at each moment, the pixels with the same coordinates in the two images correspond to the same position in the body. This is because the same anatomical information corresponds to the same person's CT image and PET image acquired at the same time.

[0023] Step 2: Collect the T obtained in Step 1 1 CT image and PET image at time, T 2The CT images and PET images at each moment are input into the deep learning network for training. The deep learning network used here is selected from UNet and GAN (General Adversarial Network). Su...

Embodiment 2

[0027] The present invention is a kind of CT image generation method that is used for PET image attenuation correction, and this method comprises the following steps:

[0028] Step 1: Use PET / CT equipment to collect several patients at T 1 The CT image and PET image at the moment, the collection T 1 The moment of CT image acquisition with T 1 The pixels with the same coordinates of the PET image at any time correspond to the same position in the body; non-rigid deformation models such as thin-plate spline curves or B-spline curves are used for T 1 The CT images and PET images collected at all times are added with a deformation to generate T 2 PET images and CT images at the moment.

[0029] Step 2: Collect the T obtained in Step 1 1 CT image and PET image at time, T 2 The CT images and PET images at each moment are input into the deep learning network for training. The deep learning network used here is selected from UNet and GAN (General Adversarial Network). to T 1 CT...

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 computed tomography (CT) image generation method used for attenuation correction of positron emission tomography (PET) images. According to the method, CT images and PET images at the moment T1 and PET images at the moment T2 are acquired and input into a trained deep learning network, CT images at the moment T2 are acquired, the CT images can be applied to the attenuation correction of the PET images, and therefore, relatively accurate PETAC (attenuation correction) images can be obtained. According to the method, the dosage of X-rays received by a patient in the whole image acquisition stage can be reduced, and physiological and psychological pressure of the patient is relieved. Besides, the later image acquisition only needs PET imaging equipment, PET / CT equipment is not needed, cost of imaging resource distribution can be reduced, and the imaging expense of the whole stage is reduced.

Description

technical field [0001] The present invention relates to the field of medical image reconstruction, in particular to a CT image generation method based on deep learning and used for PET image attenuation correction. Background technique [0002] The full name of PET (Positron Emission Tomography, PET) is positron emission computed tomography. It is a medical imaging technology widely used in anatomical morphology for functional, metabolic and receptor imaging. advanced technology. Different from the anatomical imaging of CT (Computed Tomography, CT) and MRI (Magnetic Resonance Imaging, MRI), PET can observe the physiological and biochemical changes in the metabolic process, so that abnormalities can be found before changes in biochemical blood concentration or body structure. PET is widely used in clinical tumor detection. [0003] Before performing PET scanning, isotope tracers are injected into living organisms. When the tracers participate in physiological metabolism, th...

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): A61B6/03
CPCA61B6/032A61B6/037A61B6/582A61B6/52A61B6/5235G06T2207/30096G06T2207/20084G06T2207/20081G06T5/008G06T2207/10081G06T5/50G06T2207/10104G06T7/0012
Inventor 饶璠朱闻韬杨宝陈凌叶宏伟
Owner ZHEJIANG LAB
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