TF-MCL: Time-frequency Fusion and Multi-domain Cross-Loss for Self-supervised Depression Detection

TL;DR

This paper introduces TF-MCL, a self-supervised learning model that enhances depression detection from EEG signals by effectively capturing time-frequency information through fusion and multi-domain loss, outperforming existing methods.

Contribution

The paper proposes a novel time-frequency fusion and multi-domain cross-loss approach for self-supervised depression detection, improving representation learning from EEG data.

Findings

Achieved 5.87% higher accuracy on MODMA dataset

Achieved 9.96% higher accuracy on PRED+CT dataset

Outperformed state-of-the-art methods significantly

Abstract

In recent years, there has been a notable increase in the use of supervised detection methods of major depressive disorder (MDD) based on electroencephalogram (EEG) signals. However, the process of labeling MDD remains challenging. As a self-supervised learning method, contrastive learning could address the shortcomings of supervised learning methods, which are unduly reliant on labels in the context of MDD detection. However, existing contrastive learning methods are not specifically designed to characterize the time-frequency distribution of EEG signals, and their capacity to acquire low-semantic data representations is still inadequate for MDD detection tasks. To address the problem of contrastive learning method, we propose a time-frequency fusion and multi-domain cross-loss (TF-MCL) model for MDD detection. TF-MCL generates time-frequency hybrid representations through the use of a fusion mapping head (FMH), which efficiently remaps time-frequency domain information to the fusion domain, and thus can effectively enhance the model's capacity to synthesize time-frequency information. Moreover, by optimizing the multi-domain cross-loss function, the distribution of the representations in the time-frequency domain and the fusion domain is reconstructed, thereby improving the model's capacity to acquire fusion representations. We evaluated the performance of our model on the publicly available datasets MODMA and PRED+CT and show a significant improvement in accuracy, outperforming the existing state-of-the-art (SOTA) method by 5.87% and 9.96%, respectively.