Electroencephalography-Based Source Localization for Depression Using Standardized Low Resolution Brain...

Area of Science:

• Neuroscience
• Biomedical Engineering
• Signal Processing

Background:

• Electroencephalography (EEG) is a valuable tool for diagnosing neurological disorders.
• EEG source localization is crucial for real-time brain monitoring but faces accuracy challenges due to the inverse problem.
• Existing methods struggle with noise, impacting diagnostic precision.

Purpose of the Study:

• To develop and evaluate a novel EEG source localization method for diagnosing depression.
• To enhance the accuracy of EEG signal processing in clinical applications.
• To compare the proposed method's effectiveness on real EEG data from depression patients.

Main Methods:

• Variational Mode Decomposition (VMD) was used to decompose real EEG recordings from depression patients into distinct mode functions.
• Standardized Low Resolution Brain Electromagnetic Tomography (sLORETA) was applied for inverse modeling and source localization of the decomposed EEG signals.
• Simulations on real EEG databases for depression were conducted to validate the proposed techniques.

Main Results:

• The proposed VMD-sLORETA method demonstrated improved accuracy and robustness in EEG source localization for depression.
• Performance was assessed using localization error (LE), mean square error, and signal-to-noise ratio, showing effective noise suppression.
• The study highlighted the methodology's potential for precise spatial resolution of cortical potential distribution.

Conclusions:

• The developed algorithm effectively mitigates noise interference in EEG inverse problems, crucial for depression signal analysis.
• This approach offers a promising pre-processing step for automated depression detection systems, potentially reducing diagnostic delays.
• The findings suggest a significant advancement in objective diagnostic tools for mental health disorders using EEG.