Related Experiment Video
Updated: Jul 30, 2025
11:28
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
Published on: June 30, 2018
11.7K
Automatic identification of schizophrenia based on EEG signals using dynamic functional connectivity analysis and 3D
Mingkan Shen1, Peng Wen1, Bo Song1
1School of Engineering, University of Southern Queensland, Toowoomba, Australia.
Computers in Biology and Medicine
|May 15, 2023
Summary
This study identifies schizophrenia using electroencephalogram (EEG) signals and deep learning. The novel approach achieved high accuracy in distinguishing schizophrenia patients from healthy individuals.
Area of Science:
- Neuroscience
- Computational Psychiatry
- Biomedical Engineering
Background:
- Schizophrenia (ScZ) significantly impacts individuals and healthcare systems.
- Deep learning and functional connectivity analysis are emerging tools for analyzing brain data.
- Research exploring electroencephalogram (EEG) signals for ScZ identification is growing.
Purpose of the Study:
- To investigate the identification of ScZ using EEG signals.
- To apply dynamic functional connectivity analysis and deep learning methods for ScZ detection.
- To explore differences in brain connectivity between ScZ and healthy control (HC) subjects.
Main Methods:
- Utilized a time-frequency domain functional connectivity analysis with the cross-mutual information algorithm.
- Extracted features from the alpha band (8-12 Hz) of EEG signals.
- Employed a 3D convolutional neural network (CNN) for classification of ScZ and HC subjects using the LMSU public ScZ EEG dataset.
Main Results:
- Achieved high classification performance: 97.74% accuracy, 96.91% sensitivity, and 98.53% specificity.
- Identified significant differences in functional connectivity within the default mode network.
- Found significant connectivity differences between temporal lobe regions in ScZ and HC subjects.
Conclusions:
- The proposed method effectively identifies ScZ using EEG signals and deep learning.
- Dynamic functional connectivity analysis in the alpha band is a promising feature extraction technique.
- Specific brain network connectivity alterations are characteristic of schizophrenia.
