Related Experiment Video
Updated: Jan 10, 2026
05:19
Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
Published on: July 7, 2023
3.2K
Sobel neural network for EEG-based major depressive disorder screening.
1Computer School (Huangshi Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence), Hubei Polytechnic University, Huangshi, China.
Frontiers in Psychiatry
|November 24, 2025
Summary
A new Sobel Network effectively screens for major depressive disorder (MDD) using electroencephalography (EEG) signals. This deep learning approach achieves high accuracy in distinguishing MDD patients from healthy controls.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Medical Diagnostics
Background:
- Early screening for major depressive disorder (MDD) is essential for timely intervention.
- Electroencephalography (EEG) shows promise for objective MDD assessment.
- Automated tools need sophisticated architectures to analyze complex EEG spatiotemporal features.
Purpose of the Study:
- To introduce the Sobel Network, a novel deep learning architecture for EEG-based MDD screening.
- To integrate Sobel-inspired operations within convolutional layers for end-to-end feature learning.
- To evaluate the network's performance in differentiating MDD patients from healthy controls.
Main Methods:
- Developed the Sobel Network, a neural architecture incorporating intrinsic Sobel-inspired operations.
- Applied the network to a public EEG dataset from the Hospital of Universiti Sains Malaysia.
- Compared the Sobel Network's performance against other deep learning models.
Main Results:
- The Sobel Network achieved high accuracy (98.67%), sensitivity (99.18%), and specificity (98.10%).
- The architecture effectively captured gradient patterns and edge-like information relevant to depression biomarkers.
- Outperformed existing deep learning models on the evaluated EEG dataset.
Conclusions:
- The Sobel Network offers a promising approach for accurate and robust automated EEG-based depression screening.
- This method has practical implications for clinical decision support systems.
- Further development can enhance the utility of EEG in diagnosing major depressive disorder.
