Major depressive disorder (MDD) is a prevalent mental illness characterized by persistent sadness, loss of interest in activities, and significant functional impairment. It poses severe risks to individuals’ physical and psychological well-being. The development of automated diagnostic systems for MDD is essential to improve diagnostic accuracy and efficiency. Electroencephalography (EEG) has been extensively utilized in MDD diagnostic research. However, studies employing deep learning methods still face several challenges, such as difficulty in extracting effective information from EEG signals and risks of data leakage due to experimental designs. These issues result in limited generalization capabilities when models are tested on unseen individuals, thereby restricting their practical application. In this study, we propose a novel deep learning approach, termed TSF-MDD, which integrates temporal, spatial, and frequency-domain information. TSF-MDD first applies a data reconstruction scheme to obtain a four-dimensional temporal–spatial–frequency representation of EEG signals. These data are then processed by a model based on 3D-CNN and CapsNet, enabling comprehensive feature extraction across domains. Finally, a subject-independent data partitioning strategy is employed during training and testing to eliminate data leakage. The proposed approach achieves an accuracy of 92.1%, precision of 90.0%, recall of 94.9%, and F1-score of 92.4%, respectively, on the Mumtaz2016 public dataset. The results demonstrate that TSF-MDD exhibits excellent generalization performance.

Magnetoencephalography (MEG) is a non-invasive imaging technique that captures neural activity with high spatio-temporal resolution. In recent years, novel wearable devices based on Optically Pumped Magnetometer (OPM) have emerged as a new driving force for advancing MEG due to their cost-effectiveness, portability, and mobility. In practical applications, MEG signals are frequently influenced by various interference sources, resulting in degradation of signal quality. Consequently, numerous suppression techniques have been proposed to overcome these challenges. This manuscript presents a comprehensive review of the most advanced methods for suppressing MEG noise or artifacts, with a specific focus on mitigating background noise, physiological artifacts (such as those caused by heartbeat, eye movements, and muscle contractions), as well as technical artifacts (including system-related artifacts associated with devices, motion-induced artifacts, and metal-induced artifacts). Additionally, the current limitations and challenges of these approaches in real-world scenarios are highlighted. Reviewing nearly a decade of research, there is an urgent need for a lightweight noise analysis framework in the complex measurement environment of wearable OPM-MEG devices. This framework should be capable of effectively detecting, classifying, and suppressing individual and combined MEG interference. By addressing this need, we can enhance the reliability and practicality of MEG signals while advancing brain science research.

The optically pumped magnetometer (OPM) based magnetoencephalography (MEG) system offers advantages such as flexible layout and wearability. However, the position instability or jitter of OPM sensors can result in bad channels and segments, which significantly impede subsequent preprocessing and analysis. Most common methods directly reject or interpolate to repair these bad channels and segments. Direct rejection leads to data loss, and when the number of sensors is limited, interpolation using neighboring sensors can cause significant signal distortion and cannot repair bad segments present in all channels. Therefore, most existing methods are unsuitable for OPM-MEG systems with fewer channels. We introduce an automatic bad segments and bad channels repair method for OPM-MEG, called Repairbads. This method aims to repair all bad data and reduce signal distortion, especially capable of automatically repairing bad segments present in all channels simultaneously. Repairbads employs Riemannian Potato combined with joint decorrelation to project out artifact components, achieving automatic bad segment repair. Then, an adaptive algorithm is used to segment the signal into relatively stable noise data chunks, and the source-estimate-utilizing noise-discarding algorithm is applied to each chunk to achieve automatic bad channel repair. We compared the performance of Repairbads with the Autoreject method on both simulated and real auditory evoked data, using five evaluation metrics for quantitative assessment. The results demonstrate that Repairbads consistently outperforms across all five metrics. In both simulated and real OPM-MEG data, Repairbads shows better performance than current state-of-the-art methods, reliably repairing bad data with minimal distortion. The automation of this method significantly reduces the burden of manual inspection, promoting the automated processing and clinical application of OPM-MEG.

Optically pumped magnetometer-based magnetoencephalography (OPM-MEG) is an novel non-invasive functional imaging technique that features more flexible sensor configurations and wearability; however, this also increases the requirement for environmental noise suppression. Subspace projection algorithms are widely used in MEG to suppress noise. However, in OPM-MEG systems with a limited number of channels, subspace projection methods that rely on spatial oversampling exhibit reduced performance. The homogeneous field correction (HFC) method resolves this problem by constructing a low-rank spatial model; however, it cannot address complex non-homogeneous noise. The spatiotemporal extended homogeneous field correction (teHFC) method uses multiple orthogonal projections to suppress disturbances. However, the signal and noise subspace are not completely orthogonal, limiting enhancement in the capabilities of the teHFC. Therefore, we propose an extended homogeneous field correction method based on oblique projection (opHFC), which overcomes the issue of non-orthogonality between the signal and noise subspace, enhancing the ability to suppress complex interferences. The opHFC constructs an oblique projection operator that divides the signals into internal and external components, eliminating complex interferences through temporal extension. We compared the opHFC with four benchmark methods by simulations and auditory and somatosensory evoked OPM-MEG experiments. The results demonstrate that opHFC provides superior noise suppression with minimal distortion, enhancing the signal quality at the sensor and source levels. Our method offers a novel approach to reducing interference in OPM-MEG systems, expanding their application scenarios, and providing high-quality signals for scientific research and clinical applications based on OPM-MEG.

Source imaging algorithms have been widely used to localize functional and lesion areas. Brain source reconstruction is limited by complex experimental environments (noise interference, distributed brain activity, acquisition systems, etc.), and range estimation is not accurate. This study proposes a variational sparse source imaging method based on the time basis matrix (VSSI-TBM) algorithm. VSSI-TBM permits the source spatial signal to consist of several temporal basis functions by using low-rank decomposition to extract effective signals. In a compressed space, mixed-norm constraints and a cortical source variation operator ensure spatial sparsity and smoothness. In clinical examinations or research, other a priori information regarding brain activity may be available. VSSI-TBM using lead field guide constraints can further enhance the reconstruction results. The simulation results demonstrate the robust performance of VSSI-TBM in environments with a low signal-to-noise ratio (SNR), large sources (>11cm²), and multiple sources. Additionally, integrating prior information enhances the imaging performance in complex environments. The algorithm is evaluated using an open-source dataset and an optically pumped magnetometer-based magnetoencephalography (OPM-MEG) system with a noisy 30-channel uniform layout. The results reveal a strong robustness of the spatial range reconstruction. Moreover, the combination of prior information effectively improves the imaging performance of the OPM-MEG system.

The Magnetoencephalography (MEG) based on optically pumped magnetometers (OPMs) has emerged as a transformative wearable neuroimaging modality, offering significant advantages such as flexible sensor placement and closer proximity to neural sources. However, these very characteristics impose more stringent requirements on the environmental noise suppression. Among spatial filtering approaches, signal space projection (SSP) estimates the noise subspace directly from empty-room recordings and can be implemented without dense spatial sampling, detailed sensor-geometry modeling, or subject-specific forward models. However, as a covariance-based subspace projection method, SSP may yield biased estimates of the noise subspace eigenvectors when the empty-room covariance is contaminated by both environmental interference and sensor noise, leading to incomplete noise removal and potential signal distortion. To address this challenge, this paper proposes a bias-correction subspace projection (BCSP) method. This method constructs a coupling model between sensor noise and the background magnetic field, elucidates the underlying cause of subspace estimation bias in conventional SSP, and estimates bias via least-squares optimization. Combined with an eigenvector correction strategy based on nonlinear soft thresholding, the BCSP method adaptively reduces the bias in the estimated noise subspace eigenvectors, improving background-noise suppression. Both simulation and experimental results consistently demonstrate the proposed method's superior signal-to-noise ratio performance. In auditory evoked field experiments, it robustly preserves the waveform characteristics of the N100 component and generates highly focal cortical activation maps. This method provides a novel approach for noise suppression in OPM-MEG, and holds significant potential to advance the application of this technology in clinical medicine and neuroscience.