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

A GPU-based three-dimensional medical image registration similarity calculation method

A similarity calculation and medical image technology, applied in the fields of medical imaging and medical image registration, can solve the problem of high-dimensional matrix taking a long time, improve registration efficiency, improve registration accuracy and robustness, repeatability The effect of analytical methods

Active Publication Date: 2019-06-21
樾脑云符医学信息科技(浙江)有限公司
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the time-consuming problem of calculating high-dimensional matrices in the above-mentioned regional mutual information measurement, the present invention provides a GPU-based method for calculating the similarity of 3D medical image registration, which can greatly shorten the running time, thereby improving the accuracy and accuracy of registration. Robustness, so that the regional mutual information measurement method can be better applied to the registration technology

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
  • A GPU-based three-dimensional medical image registration similarity calculation method
  • A GPU-based three-dimensional medical image registration similarity calculation method
  • A GPU-based three-dimensional medical image registration similarity calculation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with accompanying drawing.

[0032] refer to Figure 1 ~ Figure 3, a GPU-based 3D medical image registration similarity calculation method, comprising the following steps:

[0033] Step 1, read the data, open up memory space in the CPU memory, read in two 3D medical image data with the same resolution, record the two images as reference image R and floating image F respectively, and mark the 3D medical image, because The main information of the image in the medical image is located in the center of the image, ignoring the influence of voxel points on the edge of the image on the final information entropy, the total number of pixels in the three-dimensional image N=(x-2r)(y-2r)(z-2r), Among them, x, y, z are the three-dimensional image resolution, and r is the radius of the adjacent point;

[0034] Create a column vector array based on neighborhood spatial information in CPU memory, each column vector...

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 GPU-based three-dimensional medical image registration similarity calculation method. An operation platform with an NVIDIA GeForce series display card is used, a thread execution kernel function is reasonably distributed, three-dimensional image gray scale information is calculated and processed through combination of a CPU and serial and parallel, regional mutual information is obtained, and similarity measurement can be conducted on three-dimensional medical image registration. Compared with a common mutual information method, more accurate evaluation data can be obtained, the processing speed is greatly increased through GPU parallel computing, and an accurate, stable and repeatable method can be provided for the three-dimensional medical image registration process.

Description

technical field [0001] The invention relates to the fields of medical imaging and medical image registration under information technology computer graphics, in particular to a GPU-based three-dimensional medical image registration similarity calculation method. Background technique [0002] With the development of medical imaging technology and the innovation of computer equipment, the resolution and imaging accuracy of medical images have been continuously improved, making medical images widely used in clinical and medical research. Image registration technology is an indispensable and important technology in many medical image applications. It matches various types of information into the same space to facilitate disease analysis and diagnosis. [0003] The process of 3D medical image registration mainly consists of five parts: image preprocessing, image transformation, grayscale interpolation, objective function optimization and similarity measure calculation. The ultima...

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): G06T7/33G06T1/20G06K9/62
Inventor 冯远静李思琦谭志豪张驰曾庆润陈余凯诸葛启钏
Owner 樾脑云符医学信息科技(浙江)有限公司
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