Unlock instant, AI-driven research and patent intelligence for your innovation.

A 3D/2D medical image registration method based on log operator

A medical image and 3D technology, which is applied in the field of 3D/2D medical image registration based on LoG operator, can solve problems such as difficulty in obtaining and ensuring registration accuracy, achieve fewer iteration steps, solve time efficiency problems, and improve The effect of globally optimal capabilities

Active Publication Date: 2021-12-10
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The registration method based on deep learning achieves end-to-end parameter prediction through the neural network, which is difficult to guarantee high registration accuracy, and requires a large number of paired real medical images for training, which is difficult to obtain in practice

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 3D/2D medical image registration method based on log operator
  • A 3D/2D medical image registration method based on log operator
  • A 3D/2D medical image registration method based on log operator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] For the convenience of description, the relevant technical terms appearing in the specific implementation are explained first:

[0043] GPU (Graphic Processing Unit): graphics processing unit;

[0044] DRR (Digitally Reconstructed Radiographs): Digitally reconstructed radiographs;

[0045] NCC (Normalized Cross Correlation): normalized cross correlation;

[0046] LoG (Laplacian of Gaussian): Laplacian of Gaussian.

[0047] figure 1 It is a flowchart of a 3D / 2D medical image registration method based on a LoG operator in the present invention.

[0048] In this example, if figure 1 Shown, a kind of 3D / 2D medical image registration method based on LoG operator of the present invention comprises the following steps:

[0049] S1, acquiring 2D and 3D medical images;

[0050] Obtain the intraoperative X-ray image as the 2D reference image in the registration process, obtain the preoperative CT sequence as the 3D floating image to be registered in the registration process...

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 3D / 2D medical image registration method based on a LoG operator, which first acquires 2D and 3D medical images and performs denoising preprocessing, and then establishes a projection coordinate system according to an X-ray imaging calculation model and a rigid body transformation model; Then use the parallel computing of the GPU to complete the rapid generation process of the DRR image, and establish a similarity measurement function based on the LoG operator, and finally use the hybrid optimization algorithm to iteratively optimize the similarity measurement function to find the rigid body transformation parameters that meet the precision registration , the iteration stops and the registration process is completed.

Description

technical field [0001] The invention belongs to the technical field of image registration, and more specifically relates to a LoG operator-based 3D / 2D medical image registration method. Background technique [0002] With the development of medical imaging technology, medical images of different dimensions are required to provide navigation for surgery. The 2D images taken during surgery can provide real-time information to doctors, but lose the three-dimensional spatial information of organs and tissues. These spatial information are essential for surgical image navigation. It is very important, but it is difficult to obtain three-dimensional images intraoperatively. In order to effectively use the preoperative 3D image information during the operation, it is necessary to determine the position information and direction information of the preoperative 3D image and the intraoperative 2D image, and adjust the pose of the 3D image through space transformation to make the preope...

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): G06T7/32
CPCG06T7/32G06T2207/10116G06T2207/30004
Inventor 郑文锋杨波王杨刘珊曾庆川
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA