EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automatic Removal of Physiological Artifacts in OPM-MEG: A Framework of Channel Attention Mechanism Based on Magnetic Reference Signal

Yong Li iD, Dawei Wang, Hao Lu iD, Yuyu Ma iD, Chunhui Wang, Binyi Su, Jianzhi Yang iD, Fuzhi Cao iD, Xiaolin Ning iD

Biosensors · 09.10.2025 · 15 (10) · 680

DOI: 10.3390/bios15100680 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biosensors, online erschienen am 09.10.2025. Verfasst von Yong Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Ultra-Weak Magnetic Field Measurement Technology, Ministry of Education, School of Instrumentation and Optoelectronic Engineering, …. Hauptthemen laut MEDLINE: Magnetoencephalography, Magnetometry. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Innovation Program for Quantum Science and Technology, Hefei National Laboratory, Hefei, 230088, China, the Key R&D Program of Shandong Province, Innovation Program for Quantum Science and Technology, Hefei National Laboratory.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The high spatiotemporal resolution of optically pumped magnetometers (OPMs) makes them an essential tool for functional brain imaging, enabling accurate recordings of neuronal activity. However, physiological signals such as eye blinks and cardiac activity overlap with neural magnetic signals in the frequency domain, resulting in contamination and creating challenges for the observation of brain activity and the study of neurological disorders. To address this problem, an automatic physiological artifact removal method based on OPM magnetic reference signals and a channel attention mechanism is proposed. The randomized dependence coefficient (RDC) is employed to evaluate the correlation between independent components and reference signals, enabling reliable recognition of artifact components and the construction of training and testing datasets. A channel attention mechanism is subsequently introduced, which fuses features from global average pooling (GAP) and global max pooling (GMP) layers through convolution to establish a data-driven automatic recognition model. The backbone network is further optimized to enhance performance. Experimental results demonstrate a strong correlation between the magnetic reference signals and artifact components, confirming the reliability of magnetic signals as artifact references for OPM-MEG. The proposed model achieves an artifact recognition accuracy of 98.52% and a macro-average score of 98.15%. After artifact removal, both the event-related field (ERF) responses and the signal-to-noise ratio (SNR) are significantly improved. Leveraging the flexible and modular characteristics of OPM-MEG, this study introduces an artifact recognition framework that integrates magnetic reference signals with an attention mechanism. This approach enables highly accurate automatic recognition and removal of OPM-MEG artifacts, paving the way for real-time, automated data analysis in both scientific research and clinical applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MagnetoencephalographyMagnetometryArtifactsHumansSignal-To-Noise RatioBrainAlgorithmsSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

channel attention mechanismevent-related fieldmagnetic reference signaloptically pumped magnetometerphysiological artifactsrandomized dependence coefficientsignal-to-noise ratio

Autor:innen und Institutionen

  • Key Laboratory of Ultra-Weak Magnetic Field Measurement Technology, Ministry of Education, School of Instrumentation and Optoelectronic Engineering, Beihang University, 37 Xueyuan Rd., Haidian District, Beijing 100083,…
  • Hangzhou Institute of National Extremely-Weak Magnetic Field Infrastructure, 465 Binan Rd., Binjiang District, Hangzhou 310000, China.
  • Beijing Microelectronics Technology Institute, Beijing 100076, China.
  • School of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin 300130, China.
  • Hefei National Laboratory, Gaoxin District, Hefei 230088, China.
  • Shandong Key Laboratory for Magnetic Field-Free Medicine & Functional Imaging, Institute of Magnetic Field-Free Medicine & Functional Imaging, Shandong University, 27 South Shanda Rd., Licheng District, Jinan 250100, Ch…

ORCID-Profile: Yong Li, Hao Lu, Yuyu Ma, Jianzhi Yang, Fuzhi Cao, Xiaolin Ning

Förderung

  • the Innovation Program for Quantum Science and Technology, Hefei National Laboratory, Hefei, 230088, China
  • the Key R&D Program of Shandong Province
  • Innovation Program for Quantum Science and Technology, Hefei National Laboratory
  • Key R&D Program of Shandong Province

Zitieren

APA

Li, Y., Wang, D., Lu, H., Ma, Y., Wang, C., Su, B., Yang, J., Cao, F., & Ning, X. (2025). Automatic Removal of Physiological Artifacts in OPM-MEG: A Framework of Channel Attention Mechanism Based on Magnetic Reference Signal. Biosensors, 15(10), 680. https://doi.org/10.3390/bios15100680

Vancouver

Li Y, Wang D, Lu H, Ma Y, Wang C, Su B, et al. Automatic Removal of Physiological Artifacts in OPM-MEG: A Framework of Channel Attention Mechanism Based on Magnetic Reference Signal. Biosensors. 2025;15(10):680. doi:10.3390/bios15100680

BibTeX
@article{Li2025,
  author = {Li, Yong and Wang, Dawei and Lu, Hao and Ma, Yuyu and Wang, Chunhui and Su, Binyi and Yang, Jianzhi and Cao, Fuzhi and Ning, Xiaolin},
  title = {Automatic Removal of Physiological Artifacts in OPM-MEG: A Framework of Channel Attention Mechanism Based on Magnetic Reference Signal},
  journal = {Biosensors},
  year = {2025},
  volume = {15},
  number = {10},
  pages = {680},
  doi = {10.3390/bios15100680}
}
Kostenlos starten →