Deep Learning for Ultrasonographic Assessment of Temporomandibular Joint Morphology

• Published in: Tomography (Ann Arbor) Vol. 11; no. 3; p. 27
• Main Authors: Lasek, Julia, Nurzynska, Karolina, Piórkowski, Adam, Strzelecki, Michał, Obuchowicz, Rafał
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 27.02.2025; MDPI
• Subjects: Adult; Algorithms; Artificial intelligence; Deep Learning; Female; Humans; Male; Mandibular Condyle - diagnostic imaging; Medical imaging equipment; Middle Aged; Reproducibility of Results; Temporomandibular Joint - anatomy & histology; Temporomandibular Joint - diagnostic imaging; Temporomandibular Joint Disorders - diagnostic imaging; temporomandibular joints; ultrasonography; Ultrasonography - methods; Young Adult; Poland; United States; deep learning; temporomandibular joints; ultrasonography; artificial intelligence
• ISSN: 2379-139X; 2379-1381; 2379-139X
• DOI: 10.3390/tomography11030027

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.