A retinal blood vessel image segmentation method based on a multi-scale feature convolutional neural network

A convolutional neural network and retinal blood vessel technology, applied in biological neural network models, image analysis, image enhancement, etc., can solve problems such as a lot of energy and time, and the impact of subjective experience is large, achieving good results and expanding the receptive field. , the effect of reducing the training parameters

Inactive Publication Date: 2018-12-11
TIANJIN UNIV
View PDF8 Cites 62 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional supervision method requires manual design of relevant features, which requires a lot of energ

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
  • A retinal blood vessel image segmentation method based on a multi-scale feature convolutional neural network
  • A retinal blood vessel image segmentation method based on a multi-scale feature convolutional neural network
  • A retinal blood vessel image segmentation method based on a multi-scale feature convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0040] The invention proposes a retinal blood vessel segmentation method based on a convolutional neural network combined with multi-scale features. First, the retinal images are appropriately preprocessed, including limited contrast adaptive histogram equalization and gamma brightness adjustment. At the same time, we carried out data augmentation for the problem of less retinal image data, and cut the experimental image into blocks, which expanded the wide applicability of the present invention. Secondly, by constructing a retinal blood vessel segmentation network combined with multi-scale features, the present invention introduces spatial pyramid hole pooling into an encoder-decoder structure convolutional neural network, and autonomously optimizes model parameters through multiple iterations to realize automatic pixel-level retinal blood vessels. Segmentation process to obtain retinal blood vessel segmentation map. On the one hand, the encoding and decoding process combine...

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 belongs to the technical field of image processing, in order to realize automatic extraction and segmentation of retinal blood vessels, improve the anti-interference ability to factors such as blood vessel shadow and tissue deformation, and make the average accuracy rate of blood vessel segmentation result higher. The invention relates to a retinal blood vessel image segmentation method based on a multi-scale feature convolutional neural network. Firstly, retinal images are pre-processed appropriately, including adaptive histogram equalization and gamma brightness adjustment. Atthe same time, aiming at the problem of less retinal image data, data amplification is carried out, the experiment image is clipped and divided into blocks, Secondly, through construction of a multi-scale retinal vascular segmentation network, the spatial pyramidal cavity pooling is introduced into the convolutional neural network of the encoder-decoder structure, and the parameters of the model are optimized independently through many iterations to realize the automatic segmentation process of the pixel-level retinal blood vessels and obtain the retinal blood vessel segmentation map. The invention is mainly applied to the design and manufacture of medical devices.

Description

technical field [0001] The invention belongs to the field of artificial intelligence combined with the field of medical image processing, and relates to a retinal blood vessel segmentation method based on a convolutional neural network combined with multi-scale features, which can automatically extract and segment blood vessel tree images. Background technique [0002] Among many fundus diseases, cataract, glaucoma, age-related macular degeneration and diabetic retinopathy are the four major causes of blindness, with high incidence and serious harm. Since the fundus is the only part of the human body where blood vessels can be directly observed, the analysis and processing of fundus images has become the main way to prevent and diagnose fundus diseases. Among them, the blood vessel segmentation of fundus images is an important method for quantitative analysis of diseases, and many studies have been carried out on the blood vessel segmentation of fundus images. However, the ...

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): G06T7/12G06K9/62G06N3/04G06T5/40
CPCG06T5/40G06T7/12G06V2201/03G06N3/045G06F18/2411
Inventor 唐晨郑婷月邱岳
Owner TIANJIN 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