Purpose: Cone beam computed tomography (CBCT) is widely used to evaluate the temporomandibular joint (TMJ). For the three-dimensional (3D) assessment of the TMJ, segmentation of the mandibular condyle and articular fossa is essential. This study aimed to perform deep learning-based 3D segmentation of the mandibular condyle on CBCT images and evaluate the performance of the segmentation. Methods: CBCT scan data from 99 patients (mean age: 53.3±19.2 years) diagnosed with TMJ disorders were analyzed. From the CBCT images, sagittal, coronal, and axial planes showing the mandibular condyle were selected and combined to form two-dimensional (2D) images. The U-Net deep learning model was used to exclusively segment the mandibular condyle area from the 2D images. From these results, 3D images of the mandibular condyle were reconstructed. Accuracy, precision, recall, and the Dice coefficient were calculated to appraise segmentation performance in each plane. Results: The average Dice coefficient was 0.92 for the coronal and axial planes and 0.82 for the sagittal plane. The CBCT image-based segmentation performance of the mandibular condyle in the coronal and axial planes exceeded that in the sagittal plane. The sharpness and uniformity of the 2D images affected segmentation performance, with segmentation errors more likely occurring in non-uniform images. Certain segmentation errors were corrected through software processing. Finally, the segmented mandibular condyle images were applied to the CBCT data to reconstruct a 3D TMJ model. Conclusions Mandibular condyle 3D segmentation on CBCT images using U-Net may help evaluate and diagnose TMJ disorders. The proposed segmentation method may assist clinicians in efficiently analyzing CBCT images, particularly in cases involving anatomical abnormalities.

Defects due to mandibulectomy often cause hard and soft tissue loss and result in esthetic problems and functional disorders such as mastication, swallowing, and pronunciation. After the mandibular reconstruction, several complications including loss of alveolar bone can cause limitations in maintenance or supporting of removable prosthesis. For these patients, implant-supported fixed restorations have been an appropriate prosthetic restorative method. In this case report, we report the patient who underwent mandibulectomy and mandibular reconstruction owing to oral cancer, and then restored the current dentition functionally and aesthetically by applying zirconia frameworks and monolithic zirconia crowns by computer-aided design and computer-aided manufacturing.
Carcinoma, Squamous Cell ; Computer-Aided Design ; Crowns ; Deglutition ; Dental Prosthesis, Implant-Supported ; Dentition ; Humans ; Mandibular Reconstruction ; Mastication ; Methods ; Mouth Neoplasms ; Mouth Rehabilitation* ; Mouth* ; Prostheses and Implants

The purpose of laboratory tests in the field of oral medicine can be divided into two categories: (1) medical evaluation of patients with systemic diseases that are planning to receive dental care and (2) diagnosis of patients with certain oral diseases. First, laboratory tests are commonly used to evaluate patients with systemic diseases who need dental management. A combination of multiple tests is usually prescribed as a test panel to diagnose and assess a specific disease. Test panels closely related to oral medicine include those for rheumatoid arthritis, connective tissue disease/lupus, liver function, thyroid screening, anemia, and bleeding disorders. Second, laboratory tests are used as auxiliary diagnostic methods for certain oral diseases. They often provide crucial diagnostic information for infectious diseases caused by bacteria, fungi, and viruses that are associated with pathology in the oral and maxillofacial regions. Laboratory tests for infectious diseases are composed of growth-dependent methods, immunologic assays, and molecular biology. As the field develops, further application of laboratory tests, including synovial fluid analysis in temporomandibular joint disorders, salivary diagnostics, and hematologic biomarkers associated with temporomandibular disorders and orofacial pain conditions, is currently under scrutiny for their reliability as diagnostic tools.