This review systematically analyzes the latest advancements in preprocessing techniques for Electrocardiography (ECG) and Magnetocardiography (MCG) signals over the past decade. ECG and MCG play crucial roles in cardiovascular disease (CVD) detection, but both are susceptible to noise interference. This paper categorizes and compares different ECG denoising methods based on noise types, such as baseline wander (BW), electromyographic noise (EMG), power line interference (PLI), and composite noise. It also examines the complexity of MCG signal denoising, highlighting the challenges posed by environmental and instrumental interference. This review is the first to systematically compare the characteristics of ECG and MCG signals, emphasizing their complementary nature. MCG holds significant potential for improving the precision of CVD clinical diagnosis. Additionally, it evaluates the limitations of current denoising methods in clinical applications and outlines future directions, including the potential of explainable neural networks, multi-task neural networks, and the combination of deep learning with traditional methods to enhance denoising performance and diagnostic accuracy. In summary, while traditional filtering techniques remain relevant, hybrid strategies combining machine learning offer substantial potential for advancing signal processing and clinical diagnostics. This review contributes to the field by providing a comprehensive framework for selecting and improving denoising techniques, better facilitating signal quality enhancement and the accuracy of CVD diagnostics.

Bio-electric fields—manifested as Electroencephalogram (EEG), Electrocardiogram (ECG), Electromyogram (EMG), and Electrooculogram (EOG)—are fundamental to modern medical diagnostics but often suffer from severe data imbalance, scarcity, and environmental noise. Generative Adversarial Networks (GANs) offer a powerful, nonlinear solution to these modeling hurdles. This review presents a comprehensive survey of GAN methodologies specifically tailored for bio-electric signal processing. We first establish a theoretical foundation by detailing GAN principles, training mechanisms, and critical structural variants, including advancements in loss functions and conditional architectures. Subsequently, the paper extensively analyzes applications ranging from high-fidelity signal synthesis and noise reduction to multi-class classification. Special attention is given to clinical anomaly detection, specifically covering epilepsy, arrhythmia, depression, and sleep apnea. Furthermore, we explore emerging applications such as modal transformation, Brain–Computer Interfaces (BCI), de-identification for privacy, and signal reconstruction. Finally, we critically evaluate the computational trade-offs and stability issues inherent in current models. The study concludes by delineating prospective research avenues, emphasizing the necessity of interdisciplinary synergy to advance personalized medicine and intelligent diagnostic systems.

The human brain undergoes tremendous changes during the first decade of life. The susceptibility of the immature central nervous system to factors such as adverse environments and genetic factors is attributed to its plasticity. Neurodevelopmental disorders (NDDs) occur once the immature brain veers off the typical developmental trajectory. However, little is known about the neurophysiological traits of atypically developing children because it is challenging for them to remain still during recording. Magnetoencephalography (MEG) is a noninvasive neuroimaging technique with high-spatiotemporal resolution. An ultralow magnetic field produced by neural electrical activity can be detected using a highly sensitive whole-head magnetometer array. Current cryogenic SQUID-MEG combined with individual MRI has shown great potential in reflecting neural activity under resting states and during tasks. MEG instrumentation for children is expected to be an effective tool for investigating brain dynamics, which provides neuropsychological evidence for atypical development in communication ability. In this paper, the advantages of pediatric MEG in neurodevelopmental disorder studies are discussed first and compared with those of several noninvasive functional imaging modalities. Existing commercial pediatric MEG systems are summarized based on their respective characteristics and parameters. State-of-the-art newly emerging sensing techniques based on spin-exchange relaxation-free (SERF) along with their application in detecting infants' brain responses are introduced. Recent discoveries on MEG biomarkers in children with NDDs are then summarized concerning disorders that have comorbidities in communication, such as specific language impairment (SLI), autism spectrum disorders (ASD), dyslexia and stuttering. Progress on multimodality research and total-field wearable SERF magnetometers offers insight into the neuropsychological substrates of communication disorders.

Magnetocardiography (MCG) is gaining prominence in medical technology. However, owing to the semi-open magnetic shielding, MCG is still severely interfered by low-frequency, non-Gaussian noise, particularly in clinical settings. The spatial distribution of low-frequency non-Gaussian noise is not accurately captured by linear mixing models. In addition, this noise completely overlaps with MCG signals in both the time and frequency domains, distorting the physiological information encoded in the waveform morphology and two-dimensional MCG image, which is important for diagnosis. To address this, we propose a multi-channel non-local means (NLM) method based on Hermite approximation, exploiting the high synchronization between channels and the repeatability within each channel without requiring additional reference channels. First, a matrix that contains magnetocardiographic image morphology information is computed through Hermite approximation of the reference channels. Next, clustering is performed on all data, and the standard deviation of the clustering results is utilized to calculate the adaptive Gaussian smoothing parameters. Finally, the multi-channel adaptive NLM algorithm is applied to denoise the MCG signals. Simulation, semi-physical, and real-case experiments using self-developed MCG equipment demonstrate that the proposed method effectively restores the waveform characteristics and time-frequency domain information of MCG images under low-frequency non-Gaussian noise. This method outperforms existing techniques in noise reduction and establishes a solid foundation for future clinical applications.

This paper proposes Temporal-decomposition and Attention-based Denoising Network (TADNet) for magnetocardiography (MCG) signal denoising. The raw time-series data are decomposed into trend and seasonal components. The trend component is modeled using a multi-layer perceptron to capture the trend of the data. For seasonal component, a multi-layer convolutional neural network is employed to perform segmentation and extract local temporal features. These fine-grained features are processed by a Transformer-based self-attention mechanism to capture long-range temporal dependencies. Finally, deconvolution operations are applied to reconstruct the signal, achieving effective noise reduction for MCG data. This paper conducts in-depth studies on effects of time, wavelet, and Fourier style attention on model performance, enhancing the interpretability of the model. Extensive experiments on clinical MCG data under various noise conditions demonstrate that TADNet outperforms traditional algorithms, proving its effectiveness and robustness. The research results indicate that TADNet provides a highly efficient and accurate solution for MCG signal denoising.

Background: Myocardial ischemia (MI) is a major cause of morbidity and mortality worldwide and requires timely and reliable detection. Although Spin-Exchange Relaxation-Free (SERF) magnetocardiography (MCG) provides femtotesla-level sensitivity for identifying non-linear cardiac repolarization anomalies, its clinical deployment is currently impeded by the computational bottlenecks inherent to portable edge platforms. Methods: We propose a “Sensor-to-Image” Edge-AI framework that links quantum sensing with computer vision. Single-channel SERF-MCG signals from a large cohort of 2118 subjects (1135 Healthy, 983 Ischemia) were transformed into phase-space images using three distinct encoding modalities: Recurrence Plots (RP), Gramian Angular Summation Fields (GASF), and Markov Transition Fields (MTF). These visual representations were subsequently analyzed by a streamlined MobileNetV3-Small architecture, optimized for low-latency inference. To maximize diagnostic precision, an adaptive weighted fusion mechanism was engineered to combine the chaotic specificity captured by RP with the morphological sensitivity of GASF through a validation-optimized fixed global weighting strategy. Results: In our experiments, the fusion model achieved an Area Under the Curve (AUC) of 0.865, which was higher than the 1D-CNN baseline (AUC 0.857) and the single-modality models. Notably, the fusion strategy significantly elevated sensitivity to 88.3% while maintaining a specificity of 66.5%. Although specificity is moderate, this trade-off prioritizes high sensitivity to minimize false negatives in pre-hospital screening scenarios. The average inference time was 4.7 ms per sample on a standard CPU, suggesting suitability for real-time Point-of-Care (PoC) scenarios under further on-device validation. Conclusions: The results suggest that multi-view phase-space fusion can capture subtle spatio-temporal changes associated with ischemia. The proposed lightweight framework may support the development of portable SERF-MCG systems with embedded AI screening.