Vasilios Alevizakos1, Katrin Bekes2, Richard Steffen3, Constantin von See4. 1. Research Center for Digital Technologies in Dentistry and CAD/CAM, Department of Dentistry, Faculty of Medicine and Dentistry, Danube Private University, Steiner Landstraße 124, 3500, Krems, Austria. v@alevizacos.de. 2. Department of Paediatric Dentistry, Medical University of Vienna - University Clinic of Dentistry, Sensengasse 2a, 1090, Vienna, Austria. 3. Dr. med. dent. Steffen Claire und Richard, Rathausstrasse 39, 8570, Weinfelden, Switzerland. 4. Research Center for Digital Technologies in Dentistry and CAD/CAM, Department of Dentistry, Faculty of Medicine and Dentistry, Danube Private University, Steiner Landstraße 124, 3500, Krems, Austria.
Abstract
OBJECTIVES: Molar incisor hypomineralization (MIH) is a difficult-to-diagnose developmental disorder of the teeth, mainly in children and adolescents. Due to the young age of the patients, problems typically occur with the diagnosis of MIH. The aim of the present technical note was to investigate whether a successful application of a neural network for diagnosis of MIH and other different pathologies in dentistry is still feasible. MATERIALS AND METHODS: For this study, clinical pictures of four different pathologies were collected (n = 462). These pictures were categorized in caries (n = 118), MIH (n = 115), amelogenesis imperfecta (n = 112) and dental fluorosis (n = 117). The pictures were anonymized and a specialized dentist taking into account all clinical data did the diagnosis. Then, well-investigated picture classifier neural networks were selected. All of these were convolutional neural networks (ResNet34, ResNet50, AlexNet, VGG16 and DenseNet121). The neural networks were pre-trained and transfer learning was performed on the given datasets. RESULTS: For the vgg16 network, the precision is the lowest with 83.98% as for the dense121 it shows the highest values with 92.86%. Comparing the different pathologies between the investigated neural networks, there is no trend detectable. CONCLUSION: In the long term, an implementation of artificial intelligence for the detection of specific dental pathologies is conceivable and sensible. CLINICAL RELEVANCE: Finally, this application can be integrated in the area of training and teaching in order to teach dental students as well as general practitioners for MIH and similar dental pathologies.
OBJECTIVES: Molar incisor hypomineralization (MIH) is a difficult-to-diagnose developmental disorder of the teeth, mainly in children and adolescents. Due to the young age of the patients, problems typically occur with the diagnosis of MIH. The aim of the present technical note was to investigate whether a successful application of a neural network for diagnosis of MIH and other different pathologies in dentistry is still feasible. MATERIALS AND METHODS: For this study, clinical pictures of four different pathologies were collected (n = 462). These pictures were categorized in caries (n = 118), MIH (n = 115), amelogenesis imperfecta (n = 112) and dental fluorosis (n = 117). The pictures were anonymized and a specialized dentist taking into account all clinical data did the diagnosis. Then, well-investigated picture classifier neural networks were selected. All of these were convolutional neural networks (ResNet34, ResNet50, AlexNet, VGG16 and DenseNet121). The neural networks were pre-trained and transfer learning was performed on the given datasets. RESULTS: For the vgg16 network, the precision is the lowest with 83.98% as for the dense121 it shows the highest values with 92.86%. Comparing the different pathologies between the investigated neural networks, there is no trend detectable. CONCLUSION: In the long term, an implementation of artificial intelligence for the detection of specific dental pathologies is conceivable and sensible. CLINICAL RELEVANCE: Finally, this application can be integrated in the area of training and teaching in order to teach dental students as well as general practitioners for MIH and similar dental pathologies.
Authors: K L Weerheijm; M Duggal; I Mejàre; L Papagiannoulis; G Koch; L C Martens; A-L Hallonsten Journal: Eur J Paediatr Dent Date: 2003-09 Impact factor: 2.231