Scoring facial attractiveness with deep convolutional neural networks: How training on standardized images reduces the bias of facial expressions.

OBJECTIVE: In many medical disciplines, facial attractiveness is part of the diagnosis, yet its scoring might be confounded by facial expressions. The intent was to apply deep convolutional neural networks (CNN) to identify how facial expressions affect facial attractiveness and to explore whether a dedicated training of the CNN is able to reduce the bias of facial expressions. MATERIALS AND METHODS: Frontal facial images (n = 840) of 40 female participants (mean age 24.5 years) were taken adapting a neutral facial expression and the six universal facial expressions. Facial attractiveness was computed by means of a face detector, deep convolutional neural networks, standard support vector regression for facial beauty, visual regularized collaborative filtering and a regression technique for handling visual queries without rating history. CNN was first trained on random facial photographs from a dating website and then further trained on the Chicago Face Database (CFD) to increase its suitability to medical conditions. Both algorithms scored every image for attractiveness. RESULTS: Facial expressions affect facial attractiveness scores significantly. Scores from CNN additionally trained on CFD had less variability between the expressions (range 54.3-60.9 compared to range: 32.6-49.5) and less variance within the scores (P ≤ .05), but also caused a shift in the ranking of the expressions' facial attractiveness. CONCLUSION: Facial expressions confound attractiveness scores. Training on norming images generated scores less susceptible to distortion, but more difficult to interpret. Scoring facial attractiveness based on CNN seems promising, but AI solutions must be developed on CNN trained to recognize facial expressions as distractors.

Artificial intelligence in medico-dental diagnostics of the face: a narrative review of opportunities and challenges.

OBJECTIVES: This review aims to share the current developments of artificial intelligence (AI) solutions in the field of medico-dental diagnostics of the face. The primary focus of this review is to present the applicability of artificial neural networks (ANN) to interpret medical images, together with the associated opportunities, obstacles, and ethico-legal concerns. MATERIAL AND METHODS: Narrative literature review. RESULTS: Narrative literature review. CONCLUSION: Curated facial images are widely available and easily accessible and are as such particularly suitable big data for ANN training. New AI solutions have the potential to change contemporary dentistry by optimizing existing processes and enriching dental care with the introduction of new tools for assessment or treatment planning. The analyses of health-related big data may also contribute to revolutionize personalized medicine through the detection of previously unknown associations. In regard to facial images, advances in medico-dental AI-based diagnostics include software solutions for the detection and classification of pathologies, for rating attractiveness and for the prediction of age or gender. In order for an ANN to be suitable for medical diagnostics of the face, the arising challenges regarding computation and management of the software are discussed, with special emphasis on the use of non-medical big data for ANN training. The legal and ethical ramifications of feeding patients' facial images to a neural network for diagnostic purposes are related to patient consent, data privacy, data security, liability, and intellectual property. Current ethico-legal regulation practices seem incapable of addressing all concerns and ensuring accountability. CLINICAL SIGNIFICANCE: While this review confirms the many benefits derived from AI solutions used for the diagnosis of medical images, it highlights the evident lack of regulatory oversight, the urgent need to establish licensing protocols, and the imperative to investigate the moral quality of new norms set with the implementation of AI applications in medico-dental diagnostics.

Using artificial intelligence to determine the influence of dental aesthetics on facial attractiveness in comparison to other facial modifications.

BACKGROUND: Facial aesthetics is a major motivating factor for undergoing orthodontic treatment. OBJECTIVES: To ascertain-by means of artificial intelligence (AI)-the influence of dental alignment on facial attractiveness and perceived age, compared to other modifications such as wearing glasses, earrings, or lipstick. MATERIAL AND METHODS: Forty volunteering females (mean age: 24.5) with near perfectly aligned upper front teeth [Aesthetic Component scale of the Index of Orthodontic Treatment Need (AC-IOTN) = 1 and Peer Assessment Rating Index (PAR Index) = 0 or 1] were photographed with a standardized pose while smiling, in the following settings (number of photographs = 960): without modifications, wearing eyeglasses, earrings, or lipstick. These pictures were taken with natural aligned dentition and with an individually manufactured crooked teeth mock-up (AC-IOTN = 8) to create the illusion of misaligned teeth. Images were assessed for attractiveness and perceived age, using AI, consisting of a face detector and deep convolutional neural networks trained on dedicated datasets for attractiveness and age prediction. Each image received an attractiveness score from 0 to 100 and one value for an age prediction. The scores were descriptively reviewed for each setting, and the facial modifications were tested statistically whether they affected the attractiveness score. The relationship between predicted age and attractiveness scores was examined with linear regression models. RESULTS: All modifications showed a significant effect (for all: P < 0.001) on facial attractiveness. In faces with misaligned teeth, wearing eyeglasses (-17.8%) and earrings (-3.2%) had an adverse effect on facial aesthetics. Tooth alignment (+6.9%) and wearing lipstick (+7.9%) increased attractiveness. There was no relevant effect of any assessed modifications or tooth alignment on perceived age (all: <1.5 years). Mean attractiveness score declined with predicted age, except when wearing glasses, in which case attractiveness was rated higher with increasing predicted age. CONCLUSIONS: Alignment of teeth improves facial attractiveness to a similar extent than wearing lipstick, but has no discernable effect on perceived age. Wearing glasses reduces attractiveness considerably, but this effect vanishes with age.

Gingivitis as a risk factor in periodontal disease.

BACKGROUND: Dental plaque has been proven to initiate and promote gingival inflammation. Histologically, various stages of gingivitis may be characterized prior to progression of a lesion to periodontitis. Clinically, gingivitis is well recognized. MATERIAL & METHODS: Longitudinal studies on a patient cohort of 565 middle class Norwegian males have been performed over a 26-year period to reveal the natural history of initial periodontitis in dental-minded subjects between 16 and 34 years of age at the beginning of the study. RESULTS: Sites with consistent bleeding (GI=2) had 70% more attachment loss than sites that were consistently non-inflamed (GI=0). Teeth with sites that were consistently non-inflamed had a 50-year survival rate of 99.5%, while teeth with consistently inflamed gingivae yielded a 50-year survival rate of 63.4%. CONCLUSION: Based on this longitudinal study on the natural history of periodontitis in a dentally well-maintained male population it can be concluded that persistent gingivitis represents a risk factor for periodontal attachment loss and for tooth loss.

Method of visualisation influences accuracy of measurements in cone-beam computed tomography.

This study evaluated the potential impact of different visualisation methods of cone-beam computed tomography (CBCT) on the accuracy of linear measurements of calcified structures, and assessed their interchangeability. High resolution (0.125 mm voxel) CBCT scans were obtained from eight cadaveric heads. The distance between the alveolar bone ridge and the incisal edge was determined for all mandibular incisors and canines, both anatomically and with measurements based on the following five CBCT visualisation methods: isosurface, direct volume rendering, multiplanar reformatting (MPR), maximum intensity projection of the volume of interest (VOIMIP), and average intensity projection of the volume of interest (VOIAvIP). All radiological methods were tested for repeatability and compared with anatomical results for accuracy, and limits of agreement were established. Interchangeability was evaluated by reviewing disparities between the methods and disclosing deterministic differences. Fine intra- and inter-observer repeatability was asserted for all visualisation methods (intraclass correlation coefficient ≤0.81). Measurements were most accurate when performed on MPR images and performed most disappointingly on isosurface-based images. Direct volume rendering, VOIMIP and VOIAvIP achieved acceptable results. It can be concluded that visualisation methods influence the accuracy of CBCT measurements. The isosurface viewing method is not recommended, and multiplanar reformatted images should be favoured for linear measurements of calcified structures.