Automated detection of posterior restorations in permanent teeth using artificial intelligence on intraoral photographs.

OBJECTIVES: Intraoral photographs might be considered the machine-readable equivalent of a clinical-based visual examination and can potentially be used to detect and categorize dental restorations. The first objective of this study was to develop a deep learning-based convolutional neural network (CNN) for automated detection and categorization of posterior composite, cement, amalgam, gold and ceramic restorations on clinical photographs. Second, this study aimed to determine the diagnostic accuracy for the developed CNN (test method) compared to that of an expert evaluation (reference standard). METHODS: The whole image set of 1761 images (483 of unrestored teeth, 570 of composite restorations, 213 of cements, 278 of amalgam restorations, 125 of gold restorations and 92 of ceramic restorations) was divided into a training set (N = 1407, 401, 447, 66, 231, 93, and 169, respectively) and a test set (N = 354, 82, 123, 26, 47, 32, and 44). The expert diagnoses served as a reference standard for cyclic training and repeated evaluation of the CNN (ResNeXt-101-32 × 8d), which was trained by using image augmentation and transfer learning. Statistical analysis included the calculation of contingency tables, areas under the receiver operating characteristic curve and saliency maps. RESULTS: After training was complete, the CNN was able to categorize restorations correctly with the following diagnostic accuracy values: 94.9% for unrestored teeth, 92.9% for composites, 98.3% for cements, 99.2% for amalgam restorations, 99.4% for gold restorations and 97.8% for ceramic restorations. CONCLUSIONS: It was possible to categorize different types of posterior restorations on intraoral photographs automatically with a good diagnostic accuracy. CLINICAL SIGNIFICANCE: Dental diagnostics might be supported by artificial intelligence-based algorithms in the future. However, further improvements are needed to increase accuracy and practicability.

Digital dental photography. Part 2: Purposes and uses.

Although the primary purpose of using digital photography in dentistry is for recording various aspects of clinical information in the oral cavity, other benefits also accrue. Detailed here are the uses of digital images for dento-legal documentation, education, communication with patients, dental team members and colleagues and for portfolios, and marketing. These uses enhance the status of a dental practice and improve delivery of care to patients.

Lay person's perception of smile aesthetics in dental and facial views.

OBJECTIVE: To compare the aesthetic perception of different anterior visible occlusions in different facial and dental views (frontal view, lower facial third view and dental view) by lay persons. DESIGN: Cross-sectional survey, Lima, Peru, 2002. SUBJECTS: The different views were rated by 91 randomly selected adult lay persons. MAIN OUTCOME MEASUREMENT: Visual Analogue Scale (VAS) ratings of aesthetic perception of the views. RESULTS: Anterior visible occlusion, photographed subject and view (p<0.001) had a significant effect on the aesthetic ratings. Also gender (p=0.001) and the interaction between gender and level of education (p=0.046) had a significant effect over the aesthetic rating. CONCLUSIONS: A lay panel perceived that the aesthetic impact of the visible anterior occlusion was greater in a dental view compared with a full facial view. The anterior visible occlusion, photographed subject, view type are factors, which influence the aesthetic perception of smiles. In addition, gender and level of education had an influence.

Use of dental photography by general dental practitioners in Great Britain.

This study assesses, by means of a postal questionnaire, the numbers of general dental practitioners who use clinical photography, and the uses to which this is applied. The questionnaire was distributed to 1000 randomly selected GDPs in Great Britain. A response rate of 76% was achieved. Of the respondents, 36% used clinical photography, with 65% of those using an intra-oral 35 mm camera, 18% a digital camera and 12% an intra-oral digital video camera. Principal uses of clinical photography were patient instruction/motivation (72%), medico-legal reasons (68%), treatment planning (63%), and liaison with laboratory (43%).

Clinical photographs--the gold standard.

This survey was carried out to allow a minimum data set required for intra- and extra-oral photographs to be established. In 1999 a questionnaire was sent to members of the Angle Society of Europe to establish their current clinical practice with regard to extra- and intra-oral photography. The Angle Society was chosen because of their stated commitment to a high standard of record keeping and of clinical care. Results showed that a full series of extra- and intra-oral photographs were taken both before and after treatment, as well as stage photographs during treatment on many cases. The need for each of these photographs will be discussed in some detail, and recommendations will be made as to what would be considered the Gold standard before, during, and after a course of orthodontic treatment.

Dental photography in support of patient documentation and communication.

Intraoral conditions, which in the course of dental treatment are subject to change, can be recorded in detail by means of photography. Pictures provide an improved documentation and the option of monitoring particular situations over longer periods of time. We propose a standardized preoperative 35-mm photographic series. For intraoral photography, special intraoral mirrors and lip-and-cheek retractors are modified as needed. Macro 35-mm cameras with macro flash are by now well-established. Such equipment combined with the technique outlined in this report make standardized photographic documentation possible without mouth-angle retractors and mirror rims obstructing the view.