2D image and 3D image registration method based on contour features

An image registration and contour feature technology, applied in the field of image processing, can solve the problems of unequal information amount, difficult to use gray information registration method, low quality of 2D real-time image, etc., and achieve the effect of increasing the amount of available information

Pending Publication Date: 2021-06-01
SHANGHAI JIAO TONG UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] 2D-3D registration can be regarded as a special case of 3D-3D registration, that is, one of the inputs is a 3D image with only one slice, and the two inputs have seriously unequal amounts of information. In addition, the intraoperative 2D real-time image quality Low, such problems are difficult to use the registration method based on gray information
This method solves the problem of unequal information in 2D-3D registration, but introduces optical positioning equipment, and it is necessary to collect enough images to cover the target volume to achieve 3D reconstruction

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
  • 2D image and 3D image registration method based on contour features
  • 2D image and 3D image registration method based on contour features
  • 2D image and 3D image registration method based on contour features

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0049] Such as figure 1 As shown, a method for registering 2D images and 3D images based on contour features provided by the present invention comprises the following steps:

[0050] Step 1: Acquire a 3D image, extract the 3D contour points of the target in the 3D image, and obtain a set of point clouds;

[0051]Step 2: Obtain multiple 2D images, and the relative positions between each 2D images are known, which are coaxial;

[0052] Step 3: Extract the 2D contour points of the same target in each 2D image, and combine the contour points in 3D space according to the relative positional relationship of each 2D image to obtain another set of point clouds;

[0053] Step 4: Use the point cloud registration algorithm to register two sets of point clouds to obtain a spatial transformation matrix to realize the registration and fusion of 2D images and 3D images.

[0054] In this example, the 2D image is a B-mode ultrasound image, the 3D image is an MRI image, and the contour featur...

example 2

[0077] Such as image 3 As shown, a method for registering 2D images and 3D images based on contour features provided by the present invention comprises the following steps:

[0078] Step 1: Acquire a 3D image, extract the 3D contour points of the target in the 3D image, and obtain a set of point clouds;

[0079] Step 2: Obtain multiple 2D images, and the relative positions between each 2D images are known, which are coaxial;

[0080] Step 3: Extract the 2D contour points of the same target in each 2D image, and combine the contour points in 3D space according to the relative positional relationship of each 2D image to obtain another set of point clouds;

[0081] Step 4: Use the point cloud registration algorithm to register two sets of point clouds to obtain a spatial transformation matrix to realize the registration and fusion of 2D images and 3D images.

[0082] In this example, the 2D image is a B-mode ultrasound image, the 3D image is an MRI image, and the contour featu...

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 relates to a 2D image and 3D image registration method based on contour features, and the method comprises the steps: (1) obtaining a 3D image, and extracting a 3D contour of a target in the 3D image; (2) obtaining a plurality of 2D images of different imaging planes, and extracting the 2D contour of the same target in each 2D image; (3) combining the 2D contours according to the relative position relation of the 2D images; and (4) registering the obtained contour point cloud by using an iterative nearest point algorithm, and registering and fusing the 2D image and the 3D image according to the spatial transformation relation obtained by point cloud registration. According to the method, the registration of the 2D image and the 3D image can be realized, the method can be applied to the registration fusion of the preoperative high-quality 3D medical image and the intra-operative 2D navigation image, and the quality of the intra-operative navigation image is enhanced, so that the problems of strong noise, low quality and unclear target contour of the intra-operative 2D navigation image are solved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for registering 2D images and 3D images based on contour features. Background technique [0002] 2D-3D image registration refers to finding a slice in a given 3D image that has optimal consistency with a given 2D image. It is generally used in image-guided surgical treatment, such as radiofrequency ablation, ultrasonic endoscopy, etc. 3D images such as MRI and CT are obtained before the operation for disease diagnosis, and 2D images such as B-mode ultrasound are used to monitor the operation situation during the operation. The 2D imaging during the operation is real-time and flexible, but the image noise is large and the quality is poor. Therefore, using 2D-3D image registration technology to fuse preoperative 3D images to intraoperative 2D images can effectively improve the quality of intraoperative images and enhance the effect of intraoperative image guidanc...

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): G06T7/00G06T7/12G06T7/13G06T7/33
CPCG06T7/0012G06T7/12G06T7/13G06T7/344G06T2207/10028G06T2207/10088G06T2207/10132
Inventor 白景峰吉翔杨聪周赟
Owner SHANGHAI JIAO TONG 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

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