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

Blood vessel extraction method and device and computer readable storage medium

An extraction method and blood vessel technology, applied in the field of image processing, can solve the problems of noise sensitivity, difficult clinical application, and difficult to achieve automaticity, etc., to achieve the effect of suppressing noise interference, improving extraction accuracy, and ensuring accuracy

Active Publication Date: 2019-06-14
杭州晟视科技有限公司
View PDF12 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the active contour segmentation process can resist noise interference, the pros and cons of this process depend on the position of the initial curve, and the presence of noise makes it more difficult to determine a suitable initial curve
[0004] The traditional method has achieved a good segmentation effect within a certain range, but the common point is that the segmentation effect is heavily dependent on empirical knowledge, requires a lot of manual intervention, and is very sensitive to noise, and the segmentation efficiency is not high.
Therefore, it is difficult for this kind of method to be truly automatic in medical image segmentation, and it can only be used by medical personnel without relevant professional knowledge, and it is difficult to truly put it into clinical application.

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
  • Blood vessel extraction method and device and computer readable storage medium
  • Blood vessel extraction method and device and computer readable storage medium
  • Blood vessel extraction method and device and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 As shown, the blood vessel extraction method specifically includes:

[0041] Step 101: Obtain N slice images of the target blood vessel, where each slice image contains velocity field images in M ​​directions, and both N and M are positive integers;

[0042] Step 102: Based on the image preprocessing algorithm, perform preprocessing on each slice image in the N layer slice image to obtain the first type N layer image; wherein, the image preprocessing algorithm includes at least one neighborhood processing algorithm;

[0043] Step 103: based on a preset image segmentation algorithm, segment a target area containing target blood vessels from each layer image in the first type N layer image to obtain a second type N layer image;

[0044] Step 104: Based on the image sequence of N-layer sliced ​​images, merge the second type of N-layer images to obtain an initial three-dimensional point cloud model of the target blood vessel.

[0045] Here, the execution ...

Embodiment 2

[0066] In order to better reflect the purpose of this application, on the basis of Example 1 of this application, a further example is given. The blood vessel extraction method specifically includes:

[0067] Step 201: Obtain N slice images of the target blood vessel, where each slice image contains velocity field images in M ​​directions, and N and M are both positive integers;

[0068] Step 202: Based on the first neighborhood processing algorithm, perform neighborhood processing on the velocity field images in each direction in the N-layer slice images to obtain N template images;

[0069] Specifically, the method for obtaining N template images includes: based on the first neighborhood processing algorithm, performing neighborhood processing on the velocity field images in each direction in the N-layer slice images to obtain N×M neighborhood-processed images , merge the velocity field images in M ​​directions in each layer of N×M images to obtain N images; determine the op...

Embodiment 3

[0094] In order to better reflect the purpose of this application, on the basis of Embodiment 1 and Embodiment 2 of this application, further illustrations are made. The blood vessel extraction method specifically includes:

[0095] Step 301: Obtain N slice images of the target blood vessel, where each slice image contains velocity field images in M ​​directions, and N and M both take positive integers;

[0096] Step 302: Based on the user selection information, determine the area to be enhanced in the velocity field image of each direction in the N slice image; wherein, the area to be enhanced includes at least part of the blood vessels of the target blood vessel;

[0097] In practical applications, if the features of some areas in the target blood vessel are not obvious, the above-mentioned blood vessel extraction method may not be able to accurately extract these areas with inconspicuous features. Therefore, it is necessary to perform enhancement processing on these areas. ...

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 embodiment of the invention discloses a blood vessel extraction method and device and a computer readable storage medium, and the method comprises the steps of obtaining N layers of slice images of a target blood vessel, wherein each layer of slice image comprises velocity field images in M directions, and N and M are positive integers; based on an image preprocessing algorithm, preprocessingeach layer of slice image in the N layers of slice images to obtain a first type of N layers of images, wherein the image preprocessing algorithm comprises at least one neighborhood processing algorithm; segmenting a target area containing the target blood vessel from each layer of image in the first type of N-layer images based on a preset image segmentation algorithm to obtain a second type of N-layer images; and combining the second type of N-layer images based on the image sequence of the N-layer slice images to obtain an initial three-dimensional point cloud model of the target blood vessel.

Description

technical field [0001] The present application relates to image processing technology, and in particular to a blood vessel extraction method, device and computer-readable storage medium. Background technique [0002] With the continuous development of computer technology, modern medical imaging technology has made many innovations and breakthroughs in the field of medical diagnosis and is widely used in clinical diagnosis. Traditional image diagnosis mostly relies on professional medical personnel for analysis. Although manual operation has the advantage of high precision, the increasingly large demand for image data and diagnosis makes the work intensity of medical personnel continue to increase, resulting in a decrease in work quality. . Therefore, compared with the traditional imaging diagnosis methods, computer-aided diagnosis can greatly reduce the workload of clinicians, improve the accuracy of diagnosis, and avoid misdiagnosis and missed diagnosis. For example: CT A...

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): G06T7/11G06T7/136G06T5/30G06T5/00
Inventor 魏润杰李博文高琪吴鹏
Owner 杭州晟视科技有限公司