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

Method for calculating coronary artery calcification ratio based on end-to-end reasoning of convolutional neural network

A convolutional neural network, coronary artery technology, applied in the field of medical image processing

Pending Publication Date: 2020-08-28
北京小白世纪网络科技有限公司
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention solves the problem of how to simulate multiple judgments by radiologists in the process of judging the calcification of a case, provides an end-to-end neural network capable of layer-by-layer reasoning, and predicts and evaluates coronary CT calcification areas

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
  • Method for calculating coronary artery calcification ratio based on end-to-end reasoning of convolutional neural network
  • Method for calculating coronary artery calcification ratio based on end-to-end reasoning of convolutional neural network
  • Method for calculating coronary artery calcification ratio based on end-to-end reasoning of convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038]An embodiment of the present invention provides a method for end-to-end reasoning calculation of coronary artery calcification ratio based on convolutional neural network, which is characterized in that the method includes: Step 1: Determine the CT image group to be input, and the CT image group represents the patient After completing all the image information of the CT examination, normalize the CT image group to reduce the difference between the images; Step 2: Then divide the CT image group into squares with a size of 64*64*64 3D image, and there is a label above each grid 3D image, each grid 3D image has position information, and the label includes five types of labels; Step 3: the grid 3D image with the first type of label The information is input into the 3D convolutional neural network to extract abstract features. After the first fully connected layer, the neural network training of whether the square 3D image is a heart is carried out. The neural network training...

Embodiment 2

[0055] According to an embodiment of the present invention, the present invention provides a device for end-to-end reasoning calculation of coronary artery calcification ratio based on convolutional neural network, including: a memory, a processor, and stored in the memory and can be stored on the processor A running computer program, when the computer program is executed by the processor, the steps of the method for calculating the coronary artery calcification ratio based on convolutional neural network end-to-end reasoning as described in the first embodiment above are realized.

Embodiment 3

[0057] According to an embodiment of the present invention, the present invention provides a computer-readable storage medium, and the computer-readable storage medium stores a program for implementing information transmission, and when the program is executed by a processor, the above-mentioned embodiment 1 is implemented. Steps in a method for computing coronary artery calcium ratios based on convolutional neural network end-to-end inference.

[0058] Through the above descriptions about the implementation manners, those skilled in the art can clearly understand that the present application can be realized by software and necessary general-purpose hardware, and of course it can also be realized by hardware. Based on this understanding, the essence of the technical solution of this application or the part that contributes to related technologies can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media...

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 method for calculating a coronary artery calcification ratio based on end-to-end reasoning of a convolutional neural network. The method comprises the following steps: determining a CT image group to be input; then, segmenting the CT image group into grid 3D images; inputting the information of the image into a neural network to extract abstract features; performing neural network training on whether the image is a heart or not through a first full connection layer; performing neural network training for judging whether the image has coronary artery or not through asecond full connection layer; performing neural network training for judging whether calcification exists in coronary artery of the image or not through a third full connection layer; performing neural network training on the position of the coronary artery of the image through a fourth full connection layer; and performing neural network training of the calcification proportion of the coronary artery of the image through a fifth full connection layer. The method solves the problem of how to simulate a plurality of judgments performed by an imaging doctor in the process of judging the calcification of a case, and provides the end-to-end neural network capable of performing layer-by-layer reasoning.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method for calculating coronary artery calcification ratio based on convolutional neural network end-to-end reasoning. Background technique [0002] At present, with the large-scale growth of image data on the Internet, image classification and discrimination technology has been widely concerned and applied. Especially in the classification and judgment in the medical field, most of the current technologies are discriminant models or classification models based on convolutional neural networks. Due to the strong abstraction and recognition capabilities of neural networks, many scientific research institutions have done a lot of research in this area and made many breakthroughs. The more popular mainstream networks are VGG, ResNet, DenseNet and Google Inception. [0003] The existing medical segmentation technology is based on the traditional computer vision t...

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): G06T7/00G06N3/04G06N3/08
CPCG06T7/0012G06N3/08G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30048G06T2207/30101G06N3/045
Inventor 杜强李剑楠郭雨晨聂方兴张兴
Owner 北京小白世纪网络科技有限公司
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