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

Fundus blood vessel automatic segmentation method and equipment

An automatic segmentation and blood vessel technology, applied in the field of ophthalmology, can solve the problems that the segmentation method cannot effectively deal with interference, photo axial interference, lateral interference, etc., to improve the resolution of XY axes, reduce axial interference, and direction strong effect

Pending Publication Date: 2021-06-01
WUXI INST OF ARTS & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Photos taken by general shooting devices are prone to axial interference and lateral interference, and the segmentation method cannot effectively deal with the interference problem

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
  • Fundus blood vessel automatic segmentation method and equipment
  • Fundus blood vessel automatic segmentation method and equipment
  • Fundus blood vessel automatic segmentation method and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] Please refer to Figure 1, a method for automatic fundus blood vessel segmentation, characterized in that it comprises the following steps:

[0060] S1. Use the image acquisition device to shoot the bottom of the eyeball to obtain a high-definition image of the fundus;

[0061] S2. Preprocessing the acquired image, the image preprocessing includes enhancing contrast and weakening background noise;

[0062] S3. Divide the fundus image into different depths for separate processing to reduce the interference of the Z-axis on the image;

[0063] S4. Using a computer to analyze the multi-layer images at the same position, and then using computer intelligence to calculate the diameter of the blood vessel at this position;

[0064] S5, superimposing images of different depths into one;

[0065] S6. Using the calculated diameter of the blood vessel to intelligently fill the superimposed image, and complete binarization to complete the blood vessel segmentation.

[0066] The p...

Embodiment 2

[0081] Please refer to Fig. 2-5, a kind of fundus blood vessel automatic segmentation equipment, comprises supporting device 1, and supporting device 1 comprises base plate 101, and the top of base plate 101 is welded with main frame 102, and the top of main frame 102 is welded with working platform 103, and working platform The top of 103 is connected with image acquisition device 2, and the inside of main frame 102 is connected with image processing device 3, and image processing device 3 comprises computer 301 and display 302, and computer 301 is placed in the inside of main frame 102, and display 302 is placed on working platform 103 The top of the image acquisition device 2 includes an auxiliary device 4 and a photographing device 5, the bottom of the auxiliary device 4 is connected to the top of the working platform 103, the bottom of the photographing device 5 is connected to the top of the auxiliary device 4, and on the right inner wall of the photographing device 5 A h...

Embodiment 3

[0086] Please refer to Figures 6-8, the difference in connection with the basis of Embodiment 2 is that the horizontal scanning control device 6 includes a protective shell and a horizontal control motor 601, the protective shell is connected with the inner wall of the shell 501, and the horizontal control motor 601 is connected to the protective shell. The inner wall of the horizontal control motor 601 is connected with a driving wheel 602, the outer surface of the driving wheel 602 is connected with a belt 603, the belt 603 and the driving wheel 602 are frictionally driven, and the inner surface of the other end of the belt 603 is connected with a driven wheel 605 , the middle surface of the belt 603 is connected with a large guide wheel 604, the horizontal scanning control device 6 also includes two groups of mobile modules, the two groups of mobile modules are respectively located on the right side of the pinhole device 506 and the pinhole sensor 509, and the mobile modules ...

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 fundus blood vessel automatic segmentation method and equipment, and belongs to the technical field of visible light. According to the method provided by the invention, a plurality of groups of high-definition photos with different depths are shot by utilizing a light focusing technology, and then the high-definition photos are intelligently analyzed to calculate the diameter of the blood vessel, so that the fundus blood vessel photos become more stereoscopic, and the fundus blood vessel automatic segmentation equipment is utilized in the method and comprises a supporting device, the top of the supporting device is connected with an image obtaining device, the interior of the supporting device is connected with an image processing device, the image obtaining device comprises an auxiliary device, the bottom of the auxiliary device is connected with the top of the working platform, and the top of the auxiliary device is connected with a shooting device; and a horizontal scanning control device and a vertical scanning control device are mounted in the shooting device. According to the invention, the problems that a picture shot by a common shooting device is liable to be subjected to axial interference and lateral interference, and a segmentation mode cannot effectively process interference are solved.

Description

technical field [0001] The invention relates to the technical field of ophthalmology and optics, and more specifically, to a method and equipment for automatically segmenting fundus blood vessels. Background technique [0002] Human fundus blood vessels can reflect people's physical condition, so modern medicine often takes pictures and analyzes of fundus blood vessels. To obtain more intuitive fundus blood vessel images, the steps are divided into two steps. The first is the acquisition of high-definition fundus images, and the second is to The acquired images are intelligently segmented. Currently, the segmentation methods on the market vary greatly, but the accuracy of the segmentation results is always inseparable from the support of high-definition images. Therefore, the acquisition of high-definition images is very important, but most of the shooting equipment currently on the market uses White LED lighting illuminates the retina, images the fundus image on the sensor,...

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): G06T7/11G06T5/40
CPCG06T5/40G06T2207/10008G06T2207/20016G06T2207/30041G06T7/11
Inventor 张家骅马玉莹孟腾云
Owner WUXI INST OF ARTS & TECH