Automatic arrhythmia analysis method based on compressed graph neural network
A neural network, arrhythmia technology, applied in the field of medical signal processing, can solve the problem that the arrhythmia analysis system is not enough to meet the accuracy requirements
Active Publication Date: 2019-10-15
烽想(山东)医疗科技有限公司
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of the present invention is to solve the problem that the existing arrhythmia analysis system is not enough to meet the accuracy requirements of clinical applications, and to provide an automatic arrhythmia analysis method based on the compressed graph neural network
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 1
[0022] Embodiment 1 Automatic arrhythmia analysis method based on deep neural network
[0023] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
[0024] A specific example is the MIT-BIH Arrhythmia Database (mitdb), an internationally accepted electrocardiogram database. The data and usage instructions of this database are disclosed on the well-known physiionet.org website in the industry; And it has passed manual labeling by cardiologists; from the data set, four heartbeat category combinations classified according to the AAMI standard are selected as the basis for effect evaluation, including N category (normal heartbeat or bundle branch block heartbeat), S category ( supraventricular abnormal heartbeat), V category (abnormal ventricular heartbeat), and F category (fusion heartbeat); the labels of these four categories and the corresponding relationship with the categories in the mitdb dataset are s...
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 an automatic arrhythmia analysis method based on a compressed graph neural network, which includes: two sampling methods to generate multi-channel electrocardiogram samples; the obtained 600-dimensional electrocardiographic signals are spliced along the second dimension, and the original electrocardiographic signals are two When leading, it is equivalent to 4*600*1-dimensional ECG signal samples, and the input signals of four channels are input to the merging layer to merge, and output 600*4-dimensional signals. There is an image encoding layer between the merging layer unit and the convolutional layer unit for encoding the ECG signal from one-dimensional to two-dimensional image. Three layers of convolutional layer units are connected in series after the image coding layer; the convolutional layer unit includes a convolutional layer that uses two-dimensional convolution to extract the features of two-dimensional electrocardiographic signal encoded pictures, and sequentially connects an excitation unit operation and a pooling layer operation; A fully connected layer whose excitation unit is softmax is connected in series; output; learn the parameters of the deep neural network, and automatically identify samples; solve the problem that the existing arrhythmia analysis system is not enough to meet the accuracy requirements of clinical applications.
Description
technical field [0001] The invention relates to the technical field of medical signal processing, more precisely, the invention relates to an automatic arrhythmia analysis method based on a compressed graph neural network. Background technique [0002] In recent years, auxiliary diagnostic equipment for electrocardiograms has developed rapidly. With the advancement of science and technology in the information field, especially with the development of pattern recognition technology, the function of electrocardiogram equipment is no longer just to obtain electrocardiogram signals and print electrocardiograms, but to Mining the effective data in the electrocardiogram and developing in the direction of automatic identification and statistical heart beat information. The analysis equipment with the function of automatic heartbeat recognition can provide doctors with more intuitive and effective ECG information, effectively save diagnosis time and improve the diagnosis efficiency ...
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 Patents(China)
IPC IPC(8): G16H50/70G16H50/20G06K9/00A61B5/0402G06K9/62G06N3/04
CPCG16H50/20G16H50/70A61B5/318G06N3/045G06F2218/12G06F18/2411G06F18/214
Inventor 刘通危义民臧睦君邹海林贾世祥柳婵娟周树森
Owner 烽想(山东)医疗科技有限公司