Unlock instant, AI-driven research and patent intelligence for your innovation.

A method for removing bcg artifacts from synchronous eeg-fmri EEG signals

A technology of EEG signals and electrical signals, applied in the field of BCG artifacts, can solve problems such as inability to obtain EEG signals, achieve the effects of retaining EEG information, avoiding processing errors, and reducing equipment requirements

Active Publication Date: 2022-04-01
HANGZHOU DIANZI UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are few studies on this kind of unpaired EEG signal conversion problem (that is, the contaminated EEG signal and the pure EEG signal at the same time cannot be obtained for supervised signal conversion in practice).

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 method for removing bcg artifacts from synchronous eeg-fmri EEG signals
  • A method for removing bcg artifacts from synchronous eeg-fmri EEG signals
  • A method for removing bcg artifacts from synchronous eeg-fmri EEG signals

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The method of the BCG crack in the EEG signal acquired by depth learning, which is based on deep learning, is described in connection with the accompanying drawings.

[0071] Such as figure 1 As shown, a method of depth learning to removal of the EEG-FMRI collected EEG-FMRI, including the following steps:

[0072] Step 1, EEG Data Acquisition: Under the supervision of experienced clinicians, the subjects are collected by the person in the ordinary environment and the blink of blinking in the nuclear magnetic resonance environment, respectively. Signal Acquisition uses a 32-channel MRI-compatible BP product record EEG data, the impedance is adjusted to 10kΩ, and the sample rate is 5000 Hz. According to the standard 10-20 system, 30 brain electrodes (FP1, FP2, F3, F4, C3, C4, P3, P4, O1, O2, F7, F8, T7, T8, P7, P8, FZ, CZ, Pz Oz, FC1, FC2, CP1, CP2, Fc5, Fc6, CP5, CP6, A1, A2) are placed on the brain skin, such as figure 2 Indicated. In order to ensure the time stability of t...

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 a method for removing BCG artifacts from synchronous EEG-fMRI electroencephalogram signals. Collect and preprocess the multi-channel scalp EEG signals of eye-opening and eye-closing states in ordinary environment and MRI environment, and then perform data segmentation to construct eye-opening and eye-closing state data sets; use the above-mentioned eye-opening and eye-closing states The eye-closed state data set is trained with the eye-opening network model and the eye-closing network model to remove BCG artifacts respectively; the model adopts the BCGGAN network architecture model based on CycleGAN; BCGGAN includes CycleGAN, autoencoder constraints, and intermediate feature constraints. The invention can better and effectively retain EEG information while removing BCG artifacts as much as possible.

Description

Technical field [0001] The present invention relates to the field of electromal signal pretreatment, and more particularly to a method of depth learning-based intermediate signals collected in EEG-FMRI. Background technique [0002] With the development of brain science research, the combination of EEG (EEG) and Function Magnetic Resonance Imaging (FMRI) has caused extensive attention and research. The ecpoC signal is directly measured by the brain neuron discharge activity, and has a time resolution of milliseconds; functional magnetic resonance imaging indirectly measures brain activity by measuring the change in cerebroic oxygen levels, with millimeter-level spatial resolution. Eeg and FMRI complementarity in time and space resolution makes synchronous EEG-FMRIs provide more in-depth and comprehensive information for brain function research. [0003] Synchronous EEG-FMRI research is first facing the fake removal problem, where the EEG acquisition system introduced to the FMRI ...

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 Patents(China)
IPC IPC(8): A61B5/369A61B5/372A61B5/00G06N3/04G06N3/08
CPCA61B5/7235A61B5/7203G06N3/084G06N3/045G06N3/044
Inventor 林广任彬刘予晞张建海
Owner HANGZHOU DIANZI UNIV