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

B-COSFIER-based retinal blood vessel segmentation method for eye fundus image

A technology for retinal blood vessels and fundus images, applied in the field of medical image recognition, can solve the problems of unstable processing effect and low accuracy

Active Publication Date: 2018-10-16
CENT SOUTH UNIV
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the future, it is hoped that it can be applied to ophthalmology image disease screening and other image processing fields, and provide assistance for ophthalmology auxiliary diagnosis and treatment and other application fields; in the existing technology of using COSFIRE method for blood vessel segmentation, there are The disadvantages of low accuracy and unstable processing effect

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
  • B-COSFIER-based retinal blood vessel segmentation method for eye fundus image
  • B-COSFIER-based retinal blood vessel segmentation method for eye fundus image
  • B-COSFIER-based retinal blood vessel segmentation method for eye fundus image

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0083] Apply the method of the present invention to Figure 6 (a) The color fundus image taken from the DRIVE dataset is used for blood vessel segmentation. The schematic diagram of the segmentation process is (b) the green channel image, (c) the image after the CLAHE operation, (d) the image after the B-COSFIRE filter operation , (e) the map after morphological top-hat transformation, (f) the map after the binarization operation, and (g) the final blood vessel segmentation map.

example 2

[0085] Apply the method of the present invention to Figure 7 (a) The color fundus image taken from the STARE dataset is used for blood vessel segmentation. The schematic diagram of the segmentation process is (b) the green channel image, (c) the image after the CLAHE operation, and (d) the B-COSFIRE filter operation. The final image, (e) is the image after morphological top hat transformation, (f) is the image after binarization operation, and (g) is the final blood vessel segmentation image.

[0086] It can be seen from the segmentation and extraction diagrams of Example 1 and Example 2 that the blood vessel segmentation of the fundus image using the method of the present invention has a high accuracy rate, and the segmentation process is easy to operate.

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 B-COSFIER-based retinal blood vessel segmentation method for an eye fundus image. The method comprises the steps of firstly highlighting blood vessel features and reducing noises through operations of green channel taking, CLAHE and the like; secondly performing response filtration by using a B-COSFIER filter; and finally improving a segmentation effect through morphological top-hat transformation and connected domain-based postprocessing operation. Through special configuration of the B-COSFIER filter, the B-COSFIER filter has an accurate response to the eye fundus image; and the method is of important significance for establishing an efficient and reliable computer aided medical system, and provides a more effective blood vessel segmentation basis for improvingthe precision and efficiency of the aided medical system, and even clinical diagnosis, curative effect assessment, early disease symptom screening and the like.

Description

technical field [0001] The invention relates to the field of medical image recognition, in particular to a B-COSFIRE-based retinal vessel segmentation method for fundus images. Background technique [0002] At present, the main methods for analyzing and researching ophthalmic images include machine learning methods, including supervised learning and unsupervised learning methods, deep learning methods, and traditional morphology-based methods. Deep learning methods are basically used in various fields of ophthalmic image analysis, and have almost unsurpassed results in accuracy, but deep learning requires a lot of time to train neural networks. Although the ordinary machine learning method takes less time than deep learning, it also takes a certain amount of time to train the classifier, and with the increase in the dimension of the selected feature vector, the training time is greatly increased, and the results obtained are good or bad. It is also closely related to the se...

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): G06T7/155G06T7/136G06K9/32G06K9/40
CPCG06T2207/30041G06T2207/30101G06V10/25G06V10/30
Inventor 邹北骥张子谦朱承璋崔锦恺陈瑶王俊
Owner CENT SOUTH UNIV