Retinal vessel segmentation method based on middle-layer block space structure
A retinal blood vessel and spatial structure technology is applied in the field of retinal blood vessel segmentation based on the spatial structure of the middle block, which can solve the problems of segmentation time delay, affect the application of retinal blood vessel segmentation technology, and cannot meet real-time segmentation, and achieve fast segmentation time and speed. , the effect of high reliability
Active Publication Date: 2019-08-30
CENT SOUTH UNIV
View PDF3 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the existing supervised learning methods still cannot meet the requirements of real-time segmentation, and the segmentation time has a large delay, which seriously affects the application of retinal vessel segmentation technology.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0031] Such as figure 1 Shown is the schematic flow chart of the method of the present invention method: the retinal vessel segmentation method based on the middle layer block spatial structure provided by the present invention comprises the following steps:
[0032] S1. Construct a sample set; specifically, the following steps are used to construct a sample set:
[0033] A. The original image is represented by Z, which is a Num×Num blood vessel label structure block, A is a model composed of structure block features and the size is K×Num×Num, X is a sparsely represented K-dimensional vector, and N is the number of structure blocks , and Z≈A*X;
[0034] B. Select a number of images with a size of Num1×Num1 in the database, scan each pixel of the selected image, and when the blood vessel point is scanned, extract a structure block with a size of Num×Num centered on the blood vessel point, and record the extracted The center pixel position of the structure block;
[0035] C. ...
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
Login to View More Abstract
The invention discloses a retinal vessel segmentation method based on a middle-layer block space structure. The method comprises the following steps: constructing a sample set; extracting blood vesselstructure label values corresponding to the feature expressions from the structure blocks of the color image sample set; constructing a random forest classifier, classifying the structure blocks, andusing a content linear combination in the feature integration model to represent a blood vessel structure on the new image; inputting a to-be-analyzed color fundus image, extracting characteristics,detecting the blood vessel structure category to which the structure block belongs by adopting a random forest classifier, representing the blood vessel structure in the color image by using content sparse linearity in the model, matching blood vessel label values, and finishing image segmentation by calculating the probability of overlapping the structure block label values on a single pixel point. The method can rapidly and accurately segment the retinal vessel, and is high in reliability and short in algorithm operation time.
Description
technical field [0001] The invention belongs to the field of image processing, and in particular relates to a method for segmenting retinal blood vessels based on the spatial structure of middle layer blocks. Background technique [0002] With the improvement of economic level, people are more and more concerned about their health. With the popularity and extensive use of smart phones, eye diseases have seriously endangered and affected people's daily lives. Relevant data show that glaucoma, congenital and hereditary eye diseases, and fundus lesions account for 8.8%, 5.1%, and 8.4% of the blinding ratios, respectively. Fundus diseases such as diabetic retinopathy and glaucoma are characterized by irreversibility and high incidence, which are extremely harmful to the lives of patients suffering from these diseases. [0003] The color fundus image is an important basis for medical clinical diagnosis of ophthalmic diseases, and the analysis of its structure can be used as an ...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/10G06K9/62
CPCG06T7/0012G06T7/10G06T2207/10024G06T2207/20081G06T2207/30041G06F18/214G06F18/24323
Inventor 赵荣昌
Owner CENT SOUTH UNIV