Deep Learning for Ultrasonographic Assessment of Temporomandibular Joint Morphology
Tomography · 2025
DOI: 10.3390/tomography11030027 ↗Kurz gefasst
Fachartikel in der Zeitschrift Tomography, 2025. Verfasst von Julia Lasek und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Geology, Geophysics and Environmental Protection, AGH University of Krakow, 30-059 Krakow, Poland. Hauptthemen laut MEDLINE: Deep Learning, Temporomandibular Joint, Temporomandibular Joint Disorders. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Temporomandibular joint (TMJ) disorders are a significant cause of orofacial pain. Artificial intelligence (AI) has been successfully applied to other imaging modalities but remains underexplored in ultrasonographic evaluations of TMJ.
Objective
This study aimed to develop and validate an AI-driven method for the automatic and reproducible measurement of TMJ space width from ultrasonographic images.
Methods
A total of 142 TMJ ultrasonographic images were segmented into three anatomical components: the mandibular condyle, joint space, and glenoid fossa. State-of-the-art architectures were tested, and the best-performing 2D Residual U-Net was trained and validated against expert annotations. The algorithm for joint space width measurement based on TMJ segmentation was proposed, calculating the vertical distance between the superior-most point of the mandibular condyle and its corresponding point on the glenoid fossa.
Results
The segmentation model achieved high performance for the mandibular condyle (Dice: 0.91 ± 0.08) and joint space (Dice: 0.86 ± 0.09), with notably lower performance for the glenoid fossa (Dice: 0.60 ± 0.24), highlighting variability due to its complex geometry. The TMJ space width measurement algorithm demonstrated minimal bias, with a mean difference of 0.08 mm and a mean absolute error of 0.18 mm compared to reference measurements.
Conclusions
The model exhibited potential as a reliable tool for clinical use, demonstrating accuracy in TMJ ultrasonographic analysis. This study underscores the ability of AI-driven segmentation and measurement algorithms to bridge existing gaps in ultrasonographic imaging and lays the foundation for broader clinical applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Geology, Geophysics and Environmental Protection, AGH University of Krakow, 30-059 Krakow, Poland.
- Department of Algorithmics and Software, Silesian University of Technology, 44-100 Gliwice, Poland.
- Department of Biocybernetics and Biomedical Engineering, AGH University of Krakow, 30-059 Krakow, Poland.
- Institute of Electronics, Lodz University of Technology, 93-590 Lodz, Poland.
- Department of Diagnostic Imaging, Jagiellonian University Medical College, 30-663 Krakow, Poland.
ORCID-Profile: Julia Lasek, Karolina Nurzynska, Adam Piórkowski, Michał Strzelecki, Rafał Obuchowicz
Zitieren
APA
Lasek, J., Nurzynska, K., Piórkowski, A., Strzelecki, M., & Obuchowicz, R. (2025). Deep Learning for Ultrasonographic Assessment of Temporomandibular Joint Morphology. Tomography. https://doi.org/10.3390/tomography11030027
Vancouver
Lasek J, Nurzynska K, Piórkowski A, Strzelecki M, Obuchowicz R. Deep Learning for Ultrasonographic Assessment of Temporomandibular Joint Morphology. Tomography. 2025. doi:10.3390/tomography11030027
BibTeX
@article{Lasek2025,
author = {Lasek, Julia and Nurzynska, Karolina and Piórkowski, Adam and Strzelecki, Michał and Obuchowicz, Rafał},
title = {Deep Learning for Ultrasonographic Assessment of Temporomandibular Joint Morphology},
journal = {Tomography},
year = {2025},
doi = {10.3390/tomography11030027}
}
EUVIMED