Objective: This study aimed to evaluate an automated detection system to detect and classify permanent teeth on orthopantomogram (OPG) images using convolutional neural networks (CNNs). Methods: In total, 591 digital OPGs were collected from patients older than 18 years. Three qualified dentists performed individual teeth labelling on images to generate the ground truth annotations. A three-step procedure, relying upon CNNs, was proposed for automated detection and classification of teeth. Firstly, U-Net, a type of CNN, performed preliminary segmentation of tooth regions or detecting regions of interest (ROIs) on panoramic images. Secondly, the Faster R-CNN, an advanced object detection architecture, identified each tooth within the ROI determined by the U-Net. Thirdly, VGG-16 architecture classified each tooth into 32 categories, and a tooth number was assigned. A total of 17,135 teeth cropped from 591 radiographs were used to train and validate the tooth detection and tooth numbering modules. 90% of OPG images were used for training, and the remaining 10% were used for validation. 10-folds cross-validation was performed for measuring the performance. The intersection over union (IoU), F1 score, precision, and recall (i.e. sensitivity) were used as metrics to evaluate the performance of resultant CNNs. Results: The ROI detection module had an IoU of 0.70. The tooth detection module achieved a recall of 0.99 and a precision of 0.99. The tooth numbering module had a recall, precision and F1 score of 0.98. Conclusion: The resultant automated method achieved high performance for automated tooth detection and numbering from OPG images. Deep learning can be helpful in the automatic filing of dental charts in general dentistry and forensic medicine.

Background: Patient demand for oral and maxillofacial telehealth services increased during COVID-19. To explore the potential for their continued use post-COVID-19, an assessment was conducted by examining the association between the clinical and socio-demographic characteristics of consultants and the perceived facilitators and barriers influencing their future intent. Methods: Practicing oral and maxillofacial consultants were recruited through purposive and snowball sampling methods. Data were collected through surveys and key informant interviews. Chi-square tests were used to determine whether consultants’ clinical and socio-demographic characteristics and perceptions were associated with a willingness to use telehealth in the future. Coded interview transcripts were analyzed thematically to identify the main themes influencing their willingness. Results: Among the 42 respondents, 82% expressed a willingness to continue using telehealth services with the majority having at least 2 to 3 years (p = 0.028) of experience utilizing these services. The four main themes impacting consultants willingness include the accessibility of oral and maxillofacial healthcare, challenges addressing patient needs, the uncertainty of diagnostic accuracy and effectiveness as a post-operation observation tool. Conclusion: Most oral and maxillofacial consultants favored the routine use of telehealth services beyond COVID-19. Concern for patients’ needs was a key determinant of their continued use. Co-designing strategies to eliminate barriers and unmet needs for consultants and patients may improve oral and maxillofacial telehealth uptake.

We report a patient with a novel presentation of anti-neutrophil cytoplasmic antibody positive (ANCA+) vasculitis of the brain and oral mucosa. ANCA+ vasculitis of the brain is usually associated with pachymeningitis and hypophysitis, and there are no cases reported with simultaneous brain and oral mucosal involvement. A 35-year-old African Zambian man presented with headache and bleeding swollen gingiva. He was myeloperoxidase (MPO) antibody positive with cytoplasmic staining. His MRI showed stable small callosal, periventricular and subcortical white matter non-enhancing lesions, without change over 15 months—compatible with vasculitis. His gingival biopsy was consistent with vasculitis. His headache and oral lesions responded to oral corticosteroids and intravenous immunoglobulin which have induced clinical remission. Our patient expands the clinical syndrome of ANCA+ MPO+ C-type vasculitis of the central nervous system with headaches complicating cerebral vasculitis and oral mucosal involvement.