Mutual information and interaction-based medical image splicing method

A medical image and mutual information technology, applied in the field of medical image stitching, can solve the problems of unavailable panoramic images, low reliability, and large errors, and achieve the effect of convenient stitching process, meeting the needs of doctors, and strong robustness

Active Publication Date: 2013-08-07
SHANGHAI JIAO TONG UNIV
View PDF10 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the mechanical limitations of medical imaging equipment, generally only partial images can be obtained, and panoramic images cannot be obtained
When a doctor wants to observe the comprehensive

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
  • Mutual information and interaction-based medical image splicing method
  • Mutual information and interaction-based medical image splicing method
  • Mutual information and interaction-based medical image splicing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0063] In order to make the effect of the method more obvious, this embodiment selects two medical images with displacement deviations in the horizontal and vertical directions for splicing (such as Figure 5 As shown, height=width=2021), the main direction is horizontal splicing. The contrast of these two images is relatively appropriate, and there is no obvious noise, so the preprocessing link is omitted.

[0064] The registration in the horizontal direction is performed first. First select the initial region pair in the source image I1 and the target image I2, start to calculate the mutual information, and then follow the direction of the arrow, each time the width of the region increases by +2 (note that the two areas of the region pair are always The same), add one time to calculate the mutual information, and repeat until the end of the search is reached (the program defaults to search to 1 / 4 width, and the doctor can set it by himself after starting the interactive fun...

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 a mutual information and interaction-based medical image splicing method. According to the method, a strategy for searching for an image registration parameter is improved in a way that a target area and a comparison area are simultaneously enlarged, images are sequentially registered in a horizontal direction and a vertical direction, and are fused and seamlessly processed according to the obtained registration parameter, a linear weighting function is used for smoothly transiting an overlapped area, and a strategy for determining the size of the area of a spliced result image is also improved to realize the automatic and seamless splicing of images in any number to finally obtain an extra large-viewing angle medical image. In addition, in order to increase splicing speed and meet the requirements of a doctor, interaction with the doctor is added when the method is implemented, the doctor can manually divide an area to be matched, and a splicing process can be simplified according to needs. Experiments prove that a satisfactory splicing result can be obtained by the method and that the method has high clinical application value and is significant for researches.

Description

technical field [0001] The invention relates to the fields of computer vision and digital image processing, in particular to a new method for medical image stitching. Background technique [0002] In recent years, medical images have become one of the fastest growing fields in medical technology, especially the development of computer technology and the emergence of new imaging technologies and equipment such as X-ray, MRI, CT, PET, etc., making medical image processing technology more important for medical scientific research. and the growing role and influence of clinical practice. However, due to the mechanical limitations of medical imaging equipment, generally only partial images can be obtained, and panoramic images cannot be obtained. When a doctor wants to observe the comprehensive information of multiple images, he usually can only spatially align several images through his own observation. This method is often highly subjective, with low reliability and poor repea...

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
IPC IPC(8): G06T5/50G06T3/40G06T7/00
Inventor 李一君杨杰
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