Supercharge Your Innovation With Domain-Expert AI Agents!

Epilepsy prediction system and method based on electrical impedance imaging and electroencephalogram signals

An electrical impedance imaging and prediction system technology, applied in the medical field, can solve the problems of low measurement efficiency, single real-time monitoring data, lack of technical means for brain electrical impedance imaging and EEG signals, etc., to achieve accurate prediction, high temporal and spatial resolution. Monitoring the effect

Active Publication Date: 2021-01-08
深圳市丰盛生物科技有限公司
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above problems, the purpose of the present invention is to solve the problems of low measurement efficiency of current epilepsy detection methods, single real-time monitoring data, and the lack of technical means for brain electrical impedance imaging and EEG signals to be applied to epilepsy prediction, so as to realize the use of electrical impedance Imaging and EEG signals on seizure probability and possible distribution of onset sites

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
  • Epilepsy prediction system and method based on electrical impedance imaging and electroencephalogram signals
  • Epilepsy prediction system and method based on electrical impedance imaging and electroencephalogram signals
  • Epilepsy prediction system and method based on electrical impedance imaging and electroencephalogram signals

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0091] A, the EEG frequency-domain feature training unit 6 inputs the EEG frequency-domain feature into a convolutional neural network for training to generate a full-connected layer of EEG frequency-domain features, and the specific process is as follows:

[0092] For the first convolution, the input size is 4097×1, and the input layer is convolved with 5 convolution kernels with a size of 8×1, the moving step is 1, and the output size is 4090×1;

[0093] For the first pooling, the maximum pooling with a size of 2×2 is adopted, and the output size is 2045×1;

[0094] For the second convolution, the input size is 2045×1, and the input layer is convolved with 5 convolution kernels with a size of 6×1, the moving step is 1, and the output size is 2040×1;

[0095] For the second pooling, the maximum pooling with a size of 2×2 is adopted, and the output size is 1020×1;

[0096] For the third convolution, the input size is 1020×1, and the input layer is convolved with 10 convolutio...

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 discloses an epilepsy prediction system and method based on electrical impedance imaging and electroencephalogram signals. The epilepsy prediction system comprises an acquisition module,a deep feature generation module, a superficial feature generation module, a classification module and a prediction module. The system can collect brain function three-dimensional images and electroencephalogram signal time-frequency characteristics in real time, high temporal-spatial resolution monitoring of electroencephalogram signal changes is achieved, and the electroencephalogram signal characteristics and the three-dimensional function imaging characteristics are fused; through classification training of shallow layer characteristics and deep layer characteristics, a time period category and a time domain waveform category are output quickly and conveniently in real time, and epilepsy can be predicted more accurately.

Description

technical field [0001] The invention relates to the field of medical technology, in particular to an epilepsy prediction system and method based on electrical impedance imaging and electroencephalogram signals. Background technique [0002] Epilepsy is a common disease of the brain and nervous system. It originates from abnormal discharge of brain neurons and leads to transient brain dysfunction. At present, the clinical prediction of epilepsy mainly depends on the doctor's visual observation of the EEG, and its detection efficiency is low. , the judgment basis information is not rich enough. The electrode array of non-invasive scalp electroencephalography (EEG) is located on the surface of the scalp, which can collect electrical signal information of the brain with high temporal resolution, but the effect of real-time acquisition of high spatial resolution signal is poor, and it fails to detect the abnormal electrical signal physiologically. Bioelectrical impedance tomogra...

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): G06K9/62G06N3/04G06N3/08G06F17/14A61B5/369A61B5/374
CPCG06N3/08G06F17/142A61B5/4094A61B5/7282A61B5/7267G06N3/045G06F18/2414G06F18/253
Inventor 陈世雄黄为民朱明星黄保发方贤权黄俊李永秀王程
Owner 深圳市丰盛生物科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More