Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Coronary vessel segmentation method based on attention mechanism and full convolutional neural network

A convolutional neural network and full convolutional network technology, applied in the field of medical image processing, can solve the problems of insufficient image clarity, time-consuming, and low accuracy, and achieve high accuracy, high overall efficiency, and fast judgment speed Effect

Inactive Publication Date: 2019-09-27
SHANGHAI UNIV OF ENG SCI
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Today's manual segmentation of coronary arteries is time-consuming and determined by the operator's subjective consciousness. The accuracy is low and the image clarity is not enough. This makes the need for automatic segmentation technology in the current clinical medical image recognition processing obvious.

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
  • Coronary vessel segmentation method based on attention mechanism and full convolutional neural network
  • Coronary vessel segmentation method based on attention mechanism and full convolutional neural network
  • Coronary vessel segmentation method based on attention mechanism and full convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] Such as figure 1 Shown is the stage module diagram of the overall method of the present invention, including: the data preparation module, which marks the coronary blood vessel parts through the method of manual labeling by experts, and the original data and the label data exist in pairs, and the deep learning module makes the paired coronary vessels The vascular data are sent to the 3D full convolutional network of the joint attention mechanism to train the model, and the trained model is used to predict and segment the blood vessel parts. The traditional algorithm optimizes the module and uses the level set function to iteratively optimize the initial results of the network segmentation. , the deep learning module uses a three-dimensional fully convolutional network model integrated with the attention mechanism to perform preliminary prediction and segmentation of coronary vessels to improve the accuracy of segmentation.

[0041] Such as figure 2 Shown is the schema...

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 relates to a coronary vessel segmentation method based on an attention mechanism and a full convolutional neural network. The segmentation method comprises the following steps of 1, obtaining the input data for neural network training; 2, training a three-dimensional full convolutional network model integrated with the attention mechanism by utilizing the input data; 3, performing the coronary vessel preliminary prediction segmentation on an actual patient image by using the trained three-dimensional full convolutional network model; and 4, performing iterative optimization on the preliminary prediction segmentation result through a traditional algorithm, and obtaining a final coronary vessel segmentation result. Compared with the prior art, the method has the advantages of good segmentation result definition, high accuracy and the like.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a coronary vessel segmentation method based on an attention mechanism and a fully convolutional neural network. Background technique [0002] Coronary heart disease is one of the biggest health problems in the world today. By segmenting coronary arteries in medical images and examining them, important information can be found about abnormal narrowing and plaques, which are the main causes of these diseases. [0003] Today's manual segmentation of coronary arteries is time-consuming and determined by the operator's subjective consciousness, the accuracy is low, and the image clarity is not enough, which makes the need for automatic segmentation technology in the current clinical medical image recognition processing obvious. Contents of the invention [0004] The purpose of the present invention is to provide a coronary vessel segmentation method based on an att...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/11G06N3/04G06N3/08
CPCG06T7/11G06N3/084G06T2207/30101G06T2207/20112G06N3/045
Inventor 方志军沈烨高永彬刘敏
Owner SHANGHAI UNIV OF ENG SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com