Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Ultrasonic simulation method and system based on medical tomographic image

A technology of tomographic imaging and simulation method, applied in the field of ultrasound imaging, can solve the problems of unrealistic results, lack of tissues and organs, low resolution, etc., and achieve the effect of good geometric shape

Pending Publication Date: 2022-01-18
SHANDONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] To sum up, the main problem facing the current ultrasound simulation is that the results of the simulation method based on medical tomographic images are not realistic enough, lack corresponding tissues and organs, and have low resolution.

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
  • Ultrasonic simulation method and system based on medical tomographic image
  • Ultrasonic simulation method and system based on medical tomographic image
  • Ultrasonic simulation method and system based on medical tomographic image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Embodiment 1 provides an ultrasound simulation system based on medical tomographic images, the system includes:

[0048] A calculation module, configured to calculate the acoustic impedance coefficient of each voxel of the tomographic image;

[0049] The first building block is used to perform reflection modeling on the tomographic image in combination with acoustic impedance coefficients to obtain an initial reflectivity map;

[0050] The second building block is used to process the initial reflectance map by using the reflectance generation network to obtain a complete reflectance map;

[0051] The third building block is used to simultaneously input the complete reflectance map and the real ultrasound image into the ultrasound deep learning network for realistic learning, and obtain the ultrasound virtual image.

[0052] In this embodiment 1, the ultrasound simulation method based on the medical tomographic image is realized by using the above-mentioned ultrasound s...

Embodiment 2

[0090] Such as figure 1 As shown, in this embodiment 2, an ultrasonic simulation method based on medical tomographic images is provided. First, the CT value is used to solve the acoustic impedance coefficient corresponding to each voxel by using the linear fitting method for the medical tomographic images; and then according to the obtained The acoustic impedance coefficient of the medical tomographic image is used for reflection modeling, and the method used is the traditional ray tracing algorithm; finally, the reflectance image generated by the modeling and the real ultrasound image data set are put into the deep learning network to generate the ultrasound simulation image . Include the following steps:

[0091] Step 1: Obtain the acoustic impedance coefficient of each voxel of the medical tomographic image;

[0092] Step 2: Use ray tracing algorithm to perform reflection modeling on the medical tomographic image injected with contrast agent;

[0093] Step 3: Use CUDA to...

Embodiment 3

[0136] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium. The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the above-mentioned medical-based An ultrasound simulation method for a tomographic image, the method comprising:

[0137] Calculate the acoustic impedance coefficient of each voxel of the tomographic image;

[0138] Combined with the acoustic impedance coefficient, the reflection modeling of the tomographic image is carried out to obtain the initial reflectivity map;

[0139] Use the albedo generation network to process the initial albedo map to obtain the complete albedo map;

[0140] The complete reflectance map and the real ultrasound image are simultaneously input into the ultrasound deep learning network for realistic learning, and the ultrasound virtual image is obtained.

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 an ultrasonic simulation method and system based on a medical tomographic image, and belongs to the technical field of ultrasonic imaging. The method comprises the following steps: calculating acoustic impedance coefficient of each voxel of the tomographic image; performing reflection modeling on the sectional image in combination with the acoustic impedance coefficient to obtain an initial reflectivity graph; processing the initial reflectivity graph by using a reflectivity generation network to obtain a complete reflectivity graph; and inputting the complete reflectivity image and the real ultrasonic image into an ultrasonic deep learning network at the same time to carry out realistic learning so as to obtain an ultrasonic virtual image. According to the method, the geometric shape of the image can be well kept, and the noise distribution and the light and shade effect of real ultrasound can be learned; the defect that the GAN cannot well maintain the geometrical shape is overcome, and texture information and other realistic information of the generated image can be maintained; and the method can be closer to the sense of reality of real ultrasound, and can better maintain the geometric shape of the human tissue corresponding to the generated simulated ultrasound.

Description

technical field [0001] The invention relates to the technical field of ultrasonic imaging, in particular to an ultrasonic simulation method and system based on medical tomographic images. Background technique [0002] At present, the existing methods of ultrasound imaging simulation are the technology of using three-dimensional medical image data to simulate the process of ultrasound imaging to obtain ultrasound virtual images. It is widely used in ultrasound-guided surgery, image processing, ultrasound education and training, etc. Because ultrasound can achieve real-time imaging and the equipment is easy to use, doctors use ultrasound images to judge the surgical location during surgery. [0003] However, due to the weak position of the ultrasound image information and the low imaging quality, there will be errors. Therefore, using ultrasound simulation technology, the patient can be CT scanned in advance and the volume data of the patient can be stored. During the operat...

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): G06T17/00A61B8/00A61B8/08G06K9/62G06N3/04G06N3/08
CPCG06T17/00G06N3/084A61B8/4411A61B8/5215G06N3/045G06F18/214
Inventor 周元峰王晓洁孙艳增白贺
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com