EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning and predictive modelling for generating normalised muscle function parameters from signal images of mandibular electromyography

Taseef Hasan Farook, Tashreque Mohammed Haq, Lameesa Ramees, James Dudley

Medical & Biological Engineering & Computing · 2024

DOI: 10.1007/s11517-024-03047-6 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, 2024. Verfasst von Taseef Hasan Farook und 3 weiteren Autor:innen. Beteiligte Einrichtung: Adelaide Dental School, The University of Adelaide, Adelaide, SA, 5000, Australia. Taseef.farook@adelaide.edu.au. Hauptthemen laut MEDLINE: Electromyography, Deep Learning, Mandible, Signal Processing, Computer-Assisted. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Adelaide, The University of Adelaide.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Challenges arise in accessing archived signal outputs due to proprietary software limitations. There is a notable lack of exploration in open-source mandibular EMG signal conversion for continuous access and analysis, hindering tasks such as pattern recognition and predictive modelling for temporomandibular joint complex function. To Develop a workflow to extract normalised signal parameters from images of mandibular muscle EMG and identify optimal clustering methods for quantifying signal intensity and activity durations. A workflow utilising OpenCV, variational encoders and Neurokit2 generated and augmented 866 unique EMG signals from jaw movement exercises. k-means, GMM and DBSCAN were employed for normalisation and cluster-centric signal processing. The workflow was validated with data collected from 66 participants, measuring temporalis, masseter and digastric muscles. DBSCAN (0.35 to 0.54) and GMM (0.09 to 0.24) exhibited lower silhouette scores for mouth opening, anterior protrusion and lateral excursions, while K-means performed best (0.10 to 0.11) for temporalis and masseter muscles during chewing activities. The current study successfully developed a deep learning workflow capable of extracting normalised signal data from EMG images and generating quantifiable parameters for muscle activity duration and general functional intensity. Graphical Abstract

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectromyographyDeep LearningMandibleSignal Processing, Computer-AssistedHumansAdultMaleFemaleYoung AdultMasseter MuscleMasticationTemporomandibular Joint

Stichwörter der Autor:innen

ClusteringMasticationRange of motionSignal processingVariational autoencoder

Autor:innen und Institutionen

  • Adelaide Dental School, The University of Adelaide, Adelaide, SA, 5000, Australia. Taseef.farook@adelaide.edu.au.
  • Adelaide Dental School, The University of Adelaide, Adelaide, SA, 5000, Australia.

Förderung

  • University of Adelaide
  • The University of Adelaide

Zitieren

APA

Farook, T. H., Haq, T. M., Ramees, L., & Dudley, J. (2024). Deep learning and predictive modelling for generating normalised muscle function parameters from signal images of mandibular electromyography. Medical & Biological Engineering & Computing. https://doi.org/10.1007/s11517-024-03047-6

Vancouver

Farook TH, Haq TM, Ramees L, Dudley J. Deep learning and predictive modelling for generating normalised muscle function parameters from signal images of mandibular electromyography. Medical & Biological Engineering & Computing. 2024. doi:10.1007/s11517-024-03047-6

BibTeX
@article{Farook2024,
  author = {Farook, Taseef Hasan and Haq, Tashreque Mohammed and Ramees, Lameesa and Dudley, James},
  title = {Deep learning and predictive modelling for generating normalised muscle function parameters from signal images of mandibular electromyography},
  journal = {Medical & Biological Engineering & Computing},
  year = {2024},
  doi = {10.1007/s11517-024-03047-6}
}
Kostenlos starten →